diff --git a/plugins/aidd-context/CATALOG.md b/plugins/aidd-context/CATALOG.md index 857a8402c..a4157c169 100644 --- a/plugins/aidd-context/CATALOG.md +++ b/plugins/aidd-context/CATALOG.md @@ -60,7 +60,7 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai | `assets` | [state-matrix.md](skills/00-onboard/assets/state-matrix.md) | - | | `evals` | [scenarios.json](skills/00-onboard/evals/scenarios.json) | - | | `-` | [README.md](skills/00-onboard/README.md) | - | -| `-` | [SKILL.md](skills/00-onboard/SKILL.md) | `Detect the current project's state and open a hub of project actions - understand the project, set up or refresh the memory bank, or continue the AIDD development journey. Silently inspects the project, the AIDD setup, and which AIDD plugins are installed, then adapts the menu to that context. Use when the user says "where do I start", "onboard me", "onboard me to this project", "what should I run next", "what should I work on next", "what's the state of this project", "guide me through aidd", "guide me through aidd-context", or invokes `aidd-context:00:onboard`. Do NOT use to enumerate every installed surface from raw user intent (the discovery skill in this plugin handles that).` | +| `-` | [SKILL.md](skills/00-onboard/SKILL.md) | `Detect the current project's state and open a hub of project actions - understand the project, set up or refresh the memory bank, or continue the AIDD development journey. Silently inspects the project, the AIDD setup, and which AIDD plugins are installed, then adapts the menu to that context. Use when the user says "where do I start", "onboard me", "onboard me to this project", "what should I run next", "what should I work on next", "what's the state of this project", "guide me through aidd", "guide me through aidd-context", or invokes `aidd-context:00-onboard`. Do NOT use to enumerate every installed surface from raw user intent (the discovery skill in this plugin handles that).` | #### `skills/01-bootstrap` @@ -95,7 +95,7 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai | `evals` | [scenarios.json](skills/02-project-init/evals/scenarios.json) | - | | `-` | [README.md](skills/02-project-init/README.md) | - | | `references` | [mapping-ai-context-file.md](skills/02-project-init/references/mapping-ai-context-file.md) | - | -| `-` | [SKILL.md](skills/02-project-init/SKILL.md) | `Initialize or refresh the project memory bank and ensure AI context files contain the project memory block. Use when running `aidd init` for the first time, bootstrapping a new project, or re-running the init flow on an existing project. Do NOT use for updating individual memory files after they exist - use `aidd-context:05:learn` instead; do NOT use for editing a single rule - edit the file directly.` | +| `-` | [SKILL.md](skills/02-project-init/SKILL.md) | `Initialize or refresh the project memory bank and ensure AI context files contain the project memory block. Use when running `aidd init` for the first time, bootstrapping a new project, or re-running the init flow on an existing project. Do NOT use for updating individual memory files after they exist - use `aidd-context:05-learn` instead; do NOT use for editing a single rule - edit the file directly.` | #### `skills/03-context-generate` diff --git a/plugins/aidd-context/README.md b/plugins/aidd-context/README.md index 976480fb5..7077ec332 100644 --- a/plugins/aidd-context/README.md +++ b/plugins/aidd-context/README.md @@ -6,7 +6,7 @@ Knowledge production plugin for the AI-Driven Development framework. > Status: stable. -First time? Install with `/plugin install aidd-context@aidd-framework`, then run `aidd-context:00:onboard`. +First time? Install with `/plugin install aidd-context@aidd-framework`, then run `aidd-context:00-onboard`. Covers project bootstrap, project initialisation, generation of Claude Code context artifacts (skills, agents, rules, commands, hooks, plugins, marketplaces), Mermaid diagrams, learning, discovery, and a state-aware onboarding loop. @@ -24,7 +24,7 @@ Covers project bootstrap, project initialisation, generation of Claude Code cont ## Onboarding -New to aidd-context, or unsure what to run next? Invoke `aidd-context:00:onboard`. The skill: +New to aidd-context, or unsure what to run next? Invoke `aidd-context:00-onboard`. The skill: 1. Probes the filesystem (no questions) to snapshot what already exists - `aidd_docs/`, memory bank, rules skeleton, the `` block in your AI context file. 2. Picks ONE next aidd-context skill from the state matrix and presents a 5-option numbered menu (run / explain / handoff / swap / stop). diff --git a/plugins/aidd-context/skills/00-onboard/README.md b/plugins/aidd-context/skills/00-onboard/README.md index 83a03b8ad..1c42583bf 100644 --- a/plugins/aidd-context/skills/00-onboard/README.md +++ b/plugins/aidd-context/skills/00-onboard/README.md @@ -23,7 +23,7 @@ each action so the briefing always reflects the latest state. ## How to invoke ``` -Use skill aidd-context:00:onboard +Use skill aidd-context:00-onboard ``` The skill walks 3 atomic actions in a loop: diff --git a/plugins/aidd-context/skills/00-onboard/SKILL.md b/plugins/aidd-context/skills/00-onboard/SKILL.md index 98b4f4087..33425342f 100644 --- a/plugins/aidd-context/skills/00-onboard/SKILL.md +++ b/plugins/aidd-context/skills/00-onboard/SKILL.md @@ -1,6 +1,6 @@ --- -name: aidd-context:00:onboard -description: Detect the current project's state and open a hub of project actions - understand the project, set up or refresh the memory bank, or continue the AIDD development journey. Silently inspects the project, the AIDD setup, and which AIDD plugins are installed, then adapts the menu to that context. Use when the user says "where do I start", "onboard me", "onboard me to this project", "what should I run next", "what should I work on next", "what's the state of this project", "guide me through aidd", "guide me through aidd-context", or invokes `aidd-context:00:onboard`. Do NOT use to enumerate every installed surface from raw user intent (the discovery skill in this plugin handles that). +name: 00-onboard +description: Detect the current project's state and open a hub of project actions - understand the project, set up or refresh the memory bank, or continue the AIDD development journey. Silently inspects the project, the AIDD setup, and which AIDD plugins are installed, then adapts the menu to that context. Use when the user says "where do I start", "onboard me", "onboard me to this project", "what should I run next", "what should I work on next", "what's the state of this project", "guide me through aidd", "guide me through aidd-context", or invokes `aidd-context:00-onboard`. Do NOT use to enumerate every installed surface from raw user intent (the discovery skill in this plugin handles that). model: opus --- diff --git a/plugins/aidd-context/skills/00-onboard/actions/01-detect-state.md b/plugins/aidd-context/skills/00-onboard/actions/01-detect-state.md index 5d79ee9e9..8224a8b90 100644 --- a/plugins/aidd-context/skills/00-onboard/actions/01-detect-state.md +++ b/plugins/aidd-context/skills/00-onboard/actions/01-detect-state.md @@ -12,7 +12,7 @@ Internal working state only - **never printed to the user**. Onboard must not du The internal state covers three signal groups plus three derived values: -- Group A - AIDD setup: `aidd_docs_present`, `memory_dir_present`, `memory_files_filled`, `context_block_present`, `install_md_present`, `repo_is_empty` +- Group A - AIDD setup: `aidd_docs_present`, `memory_dir_present`, `memory_files_filled`, `context_block_present`, `repo_is_empty` - Group B - project context: `has_source_code`, `detected_stack`, `specs_present`, `plan_present`, `open_pr` - Group C - installed AIDD surface: `installed_aidd_plugins`, `installed_aidd_skills`, `only_aidd_context` - Derived: `memory_state`, `sdlc_phase`, `suggested_hub_option` @@ -24,15 +24,14 @@ The internal state covers three signal groups plus three derived values: - `test -d aidd_docs` - `test -d aidd_docs/memory && ls -1 aidd_docs/memory/*.md 2>/dev/null` - `grep -l '' CLAUDE.md AGENTS.md .github/copilot-instructions.md 2>/dev/null` - - `test -f aidd_docs/INSTALL.md` - count of files outside `aidd_docs/`, `.git/`, `node_modules/`, lockfiles, dotfiles -> if zero, `repo_is_empty=true` The context-block check covers the supported AI-context files (`CLAUDE.md`, `AGENTS.md`, `.github/copilot-instructions.md`); a tool that uses a different context filename is not detected. -3. **`memory_files_filled` heuristic**. For each memory file, compare against the corresponding template under `aidd-context:02:project-init`'s `assets/templates/memory/` directory (templates are mostly flat - `.md` - with a few under a `backend/` or `frontend/` subfolder). If at least one file differs from its template by more than YAML frontmatter and a few placeholder lines, set `memory_files_filled=true`. Derive `memory_state` (`absent` / `placeholder` / `filled`) per the matrix. +3. **`memory_files_filled` heuristic**. For each memory file, compare against the corresponding template under `aidd-context:02-project-init`'s `assets/templates/memory/` directory (templates are mostly flat - `.md` - with a few under a `backend/` or `frontend/` subfolder). If at least one file differs from its template by more than YAML frontmatter and a few placeholder lines, set `memory_files_filled=true`. Derive `memory_state` (`absent` / `placeholder` / `filled`) per the matrix. 4. **Probe Group B - project context**. - `has_source_code`: any source file outside `aidd_docs/`. - `detected_stack`: first stack manifest found (`package.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, `pom.xml`); else `none`. - - `specs_present`: requirement docs in `aidd_docs/` (user stories, PRD, or spec). + - `specs_present`: `test -d aidd_docs/specs` returns true, OR `find aidd_docs -not -path 'aidd_docs/tasks/*' \( -name '*-spec.md' -o -name '*-prd.md' -o -name '*-stories.md' \)` returns at least one file. - `plan_present`: a technical plan doc in `aidd_docs/`. - `open_pr`: the current branch has an open pull or merge request. - `sdlc_phase`: derive per the matrix rules. Conflicting or absent signals -> `unknown`. Never guess. diff --git a/plugins/aidd-context/skills/00-onboard/assets/state-matrix.md b/plugins/aidd-context/skills/00-onboard/assets/state-matrix.md index bec58a032..8bfc87af8 100644 --- a/plugins/aidd-context/skills/00-onboard/assets/state-matrix.md +++ b/plugins/aidd-context/skills/00-onboard/assets/state-matrix.md @@ -62,7 +62,12 @@ The backbone the hub and the SDLC sub-menu walk together. Legs 0 and 1 (`bootstr Cross-cutting categories (reachable from the hub, not journey legs): `memory-upkeep`, `diagram`, `generate`, `discovery`. -`memory-upkeep` resolves to the installed skill whose description covers updating or refreshing project memory **after** initial setup. It is distinct from `context-setup`, which covers the initial creation of the memory bank. If both a setup skill and an upkeep skill match, prefer the one whose description mentions updating, refreshing, or capturing learnings over the one that mentions initializing or bootstrapping. +`memory-upkeep` resolves to one of two skills depending on scope: + +- **Capture a specific learning or convention** (default) -> resolve to the installed skill whose description covers capturing or recording individual project learnings, rules, or conventions. +- **Rebuild the full memory bank** -> resolve to the installed skill whose description covers initializing or refreshing the entire project memory bank. + +When the user picks hub option 2 on a filled memory bank, default to the capture-specific-learning skill unless they explicitly ask for a full refresh. If only one skill matches either scope, use it for both. `context-setup` covers the initial creation of the memory bank and is distinct from both upkeep variants. ## Category resolution @@ -72,7 +77,7 @@ For every category that needs a skill, `02-recommend-next` resolves it: 2. Match the category function against each installed skill's `description`. 3. Exactly one fit -> use that skill. 4. No fit -> the category is a **gap**: report that this action needs an AIDD plugin that is not installed, described by function only. Never invent a skill id, never name a plugin id. -5. Several fit -> list them and let the user pick. +5. Several fit -> resolve inline, before showing any menu. Replace the single `Next: ` line with a numbered pick: `Several skills match - which do you want? 1. - / 2. - `. Wait for a digit, then continue with the chosen skill. Do not show the SDLC sub-menu until this pick is resolved. ## aidd-context-installed-alone @@ -109,11 +114,10 @@ Derivation, ambiguity always resolving to `unknown`: | `memory_files_filled` | At least one memory file has more than the template's placeholder content | | `memory_state` | Derived: `absent`, `placeholder`, or `filled` | | `context_block_present` | `grep -l '' CLAUDE.md AGENTS.md .github/copilot-instructions.md` returns 1+ | -| `install_md_present` | `aidd_docs/INSTALL.md` exists | | `repo_is_empty` | No source files outside `aidd_docs/`, `.git/`, lockfiles, and dotfiles | | `has_source_code` | Source files exist outside `aidd_docs/` | | `detected_stack` | A stack manifest is present (`package.json`, `pyproject.toml`, `go.mod`, `Cargo.toml`, `pom.xml`) | -| `specs_present` | Requirement docs exist in `aidd_docs/` (user stories, PRD, or spec) | +| `specs_present` | `aidd_docs/specs/` directory exists, OR at least one file matching `*-spec.md`, `*-prd.md`, or `*-stories.md` exists anywhere in `aidd_docs/` except `aidd_docs/tasks/` | | `plan_present` | A technical plan doc exists in `aidd_docs/` | | `open_pr` | The current branch has an open pull or merge request | | `installed_aidd_plugins` | AIDD plugins enabled in the AI tool | diff --git a/plugins/aidd-context/skills/00-onboard/evals/scenarios.json b/plugins/aidd-context/skills/00-onboard/evals/scenarios.json index dc153e5c7..0c0aa7b4d 100644 --- a/plugins/aidd-context/skills/00-onboard/evals/scenarios.json +++ b/plugins/aidd-context/skills/00-onboard/evals/scenarios.json @@ -7,7 +7,7 @@ { "prompt": "Guide me through the AIDD journey", "expect_action": "detect-state" }, { "prompt": "Guide me through aidd-context", "expect_action": "detect-state" }, { "prompt": "I'm new here, onboard me", "expect_action": "detect-state" }, - { "prompt": "Run /aidd-context:00:onboard", "expect_action": "detect-state" }, + { "prompt": "Run /aidd-context:00-onboard", "expect_action": "detect-state" }, { "prompt": "Présente-moi l'état du projet et la prochaine étape", "expect_action": "detect-state" }, { "prompt": "Par où je commence sur ce projet", "expect_action": "detect-state" }, { "prompt": "Quelle est la prochaine étape AIDD", "expect_action": "detect-state" }, diff --git a/plugins/aidd-context/skills/01-bootstrap/README.md b/plugins/aidd-context/skills/01-bootstrap/README.md index bf70694fc..fcb129de7 100644 --- a/plugins/aidd-context/skills/01-bootstrap/README.md +++ b/plugins/aidd-context/skills/01-bootstrap/README.md @@ -24,7 +24,7 @@ steps. Documentation only - no code, no scaffolding. ## How to invoke ``` -Use skill aidd-context:01:bootstrap +Use skill aidd-context:01-bootstrap ``` The skill walks 5 atomic actions in sequence: diff --git a/plugins/aidd-context/skills/01-bootstrap/SKILL.md b/plugins/aidd-context/skills/01-bootstrap/SKILL.md index 849311bc3..7430764aa 100644 --- a/plugins/aidd-context/skills/01-bootstrap/SKILL.md +++ b/plugins/aidd-context/skills/01-bootstrap/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-context:01:bootstrap +name: 01-bootstrap description: Imagine and validate the technical architecture of a new SaaS through interactive Q&A, candidate-stack comparison, multi-agent audit, and an INSTALL.md output. Use when starting a new SaaS project, choosing a stack, designing the architecture pattern (monolith vs microservices vs serverless), or producing a project's INSTALL.md. Do NOT use for editing an existing project's stack, database schema design, or scaffolding actual files (this skill produces docs only, no code). --- diff --git a/plugins/aidd-context/skills/01-bootstrap/actions/04-pick-and-design.md b/plugins/aidd-context/skills/01-bootstrap/actions/04-pick-and-design.md index e1f220b49..0a1e0b1ba 100644 --- a/plugins/aidd-context/skills/01-bootstrap/actions/04-pick-and-design.md +++ b/plugins/aidd-context/skills/01-bootstrap/actions/04-pick-and-design.md @@ -57,9 +57,9 @@ graph TD 1. Print the action 03 augmented table. Ask the user to pick a candidate by letter (A / B / C). 2. If the picked candidate has verdict `⚠️`, surface the audit concerns directly: list the specific risks found in action 03, ask whether the user has a mitigation plan, and loop until satisfied or candidate is switched. 3. If the picked candidate has verdict `❌`, refuse the pick and loop back to letting the user choose differently. (Do not proceed with a known-broken stack.) -4. Fill block 4 of the checklist with the picked candidate's concrete choices. Show the user the full filled checklist (all 24 items now) and ask them to confirm "go". +4. Fill block 4 of the checklist with the picked candidate's concrete choices. Show the user the full filled checklist and ask them to confirm "go". 5. Generate the folder-structure tree following conventions from the picked stack: monorepo (`apps/`, `packages/`) for modular monolith; flat `src/` for monolith; `services/` per service for microservices; `functions/` for serverless. Reflect every component listed in block 4. -6. Generate the Mermaid module diagram by invoking `aidd-context:04:mermaid`. Pass it the list of modules and their relations derived from the folder tree. Verify the rendered diagram passes Mermaid syntax (no parser errors). +6. Generate the Mermaid module diagram by invoking `aidd-context:04-mermaid`. Pass it the list of modules and their relations derived from the folder tree. Verify the rendered diagram passes Mermaid syntax (no parser errors). 7. Print the tree + diagram together. Wait for user confirmation before action 05. ## Test diff --git a/plugins/aidd-context/skills/02-project-init/README.md b/plugins/aidd-context/skills/02-project-init/README.md index 8028e2604..65dd82153 100644 --- a/plugins/aidd-context/skills/02-project-init/README.md +++ b/plugins/aidd-context/skills/02-project-init/README.md @@ -23,7 +23,7 @@ are created lazily by `03-context-generate` when the first rule is written. ## How to invoke ``` -Use skill aidd-context:02:project-init +Use skill aidd-context:02-project-init ``` The skill walks 5 atomic actions in sequence: diff --git a/plugins/aidd-context/skills/02-project-init/SKILL.md b/plugins/aidd-context/skills/02-project-init/SKILL.md index 5ce7c8969..bcb12e739 100644 --- a/plugins/aidd-context/skills/02-project-init/SKILL.md +++ b/plugins/aidd-context/skills/02-project-init/SKILL.md @@ -1,12 +1,12 @@ --- -name: aidd-context:02:project-init -description: Initialize or refresh the project memory bank and ensure AI context files contain the project memory block. Use when running `aidd init` for the first time, bootstrapping a new project, or re-running the init flow on an existing project. Do NOT use for updating individual memory files after they exist - use `aidd-context:05:learn` instead; do NOT use for editing a single rule - edit the file directly. +name: 02-project-init +description: Initialize or refresh the project memory bank and ensure AI context files contain the project memory block. Use when running `aidd init` for the first time, bootstrapping a new project, or re-running the init flow on an existing project. Do NOT use for updating individual memory files after they exist - use `aidd-context:05-learn` instead; do NOT use for editing a single rule - edit the file directly. model: opus --- # Project Init -Bootstraps the AIDD context layer for a project: AI context files with memory block, `aidd_docs/` documentation structure, and the memory bank files. Rule directories are created lazily by `aidd-context:03:context-generate` when the first rule is written; project-init does not pre-scaffold them. +Bootstraps the AIDD context layer for a project: AI context files with memory block, `aidd_docs/` documentation structure, and the memory bank files. Rule directories are created lazily by `aidd-context:03-context-generate` when the first rule is written; project-init does not pre-scaffold them. ## Prerequisites diff --git a/plugins/aidd-context/skills/02-project-init/assets/CONTRIBUTING.md b/plugins/aidd-context/skills/02-project-init/assets/CONTRIBUTING.md index d50125986..dbff82eae 100644 --- a/plugins/aidd-context/skills/02-project-init/assets/CONTRIBUTING.md +++ b/plugins/aidd-context/skills/02-project-init/assets/CONTRIBUTING.md @@ -8,8 +8,8 @@ Use the generator skills to scaffold new content that follows the framework stru | Skill | Creates | | ---------------------------------- | -------------------- | -| `aidd-context:03:context-generate` | New skill, agent, or rule (router-based, with actions and evals) | -| `aidd-context:05:learn` | New memory or rule capturing a learning | +| `aidd-context:03-context-generate` | New skill, agent, or rule (router-based, with actions and evals) | +| `aidd-context:05-learn` | New memory or rule capturing a learning | Generator skills consume the templates inside their `assets/` folder and write the output to the correct location for your AI tool (Claude Code, Cursor, Copilot, Codex, OpenCode). @@ -19,18 +19,18 @@ All templates live alongside the skill that owns them, under `plugins//s | Where | What it scaffolds | | -------------------------------------------------- | -------------------------------------------------------- | -| `aidd-context:03:context-generate/assets/skills/` | `SKILL.md`, action, evals templates | -| `aidd-context:03:context-generate/assets/agents/` | Agent file template | -| `aidd-context:03:context-generate/assets/rules/` | Rule file template | -| `aidd-pm:03:prd/assets/` | PRD body template | -| `aidd-pm:04:spec/assets/` | Spec template and validator | -| `aidd-dev:01:plan/assets/` | Plan and master-plan templates | -| `aidd-vcs:01:commit/assets/` | Conventional commit message template | -| `aidd-vcs:02:pull-request/assets/` | Pull/merge request body template, contributing example | +| `aidd-context:03-context-generate/assets/skills/` | `SKILL.md`, action, evals templates | +| `aidd-context:03-context-generate/assets/agents/` | Agent file template | +| `aidd-context:03-context-generate/assets/rules/` | Rule file template | +| `aidd-pm:03-prd/assets/` | PRD body template | +| `aidd-pm:04-spec/assets/` | Spec template and validator | +| `aidd-dev:01-plan/assets/` | Plan and master-plan templates | +| `aidd-vcs:01-commit/assets/` | Conventional commit message template | +| `aidd-vcs:02-pull-request/assets/` | Pull/merge request body template, contributing example | ## Syncing Across Tools -If the project uses multiple AI tools (e.g. Claude Code plus Cursor), the same content must be available to each. The memory bank is shared automatically via the `` block kept in sync by `aidd-context:02:project-init`. Skills are loaded per-plugin by the runtime, so any skill installed via the marketplace is available across tools that support skills. +If the project uses multiple AI tools (e.g. Claude Code plus Cursor), the same content must be available to each. The memory bank is shared automatically via the `` block kept in sync by `aidd-context:02-project-init`. Skills are loaded per-plugin by the runtime, so any skill installed via the marketplace is available across tools that support skills. When tools differ in syntax (frontmatter, slash command name, references), follow the IDE mapping reference shipped with each plugin. diff --git a/plugins/aidd-context/skills/02-project-init/assets/README.md b/plugins/aidd-context/skills/02-project-init/assets/README.md index 4c26a54ee..d6b9e7177 100644 --- a/plugins/aidd-context/skills/02-project-init/assets/README.md +++ b/plugins/aidd-context/skills/02-project-init/assets/README.md @@ -79,7 +79,7 @@ my-project/ Each AI context file (`CLAUDE.md`, `AGENTS.md`, `.github/copilot-instructions.md`, etc.) contains an `` block. It is: -1. **Seeded** the first time by `aidd-context:02:project-init` (the skill creates the block if absent). +1. **Seeded** the first time by `aidd-context:02-project-init` (the skill creates the block if absent). 2. **Kept in sync** automatically by a session-start hook (`aidd-context/hooks/update_memory.js`) that scans `aidd_docs/memory/` and writes the current list of `.md` files into the block. You never edit the block by hand. To change what the AI sees, add or remove files under `aidd_docs/memory/`; the hook picks them up at the next session. @@ -107,18 +107,18 @@ Each plugin is independently installable; install incrementally. Smaller surface A typical change cycles through skills from several plugins. The order below is indicative; skip what you do not need and loop back as the work demands. -1. **Bootstrap** (only for a brand-new project): `aidd-context:01:bootstrap` imagines the stack and architecture, comparing candidate stacks and writing an `INSTALL.md`. Skip this step on an existing project. -2. **Project init** (once per project, re-runnable to refresh): `aidd-context:02:project-init` scaffolds `aidd_docs/`, the memory bank, and the AI context files for the tools you use. Re-running later refreshes the scaffold without overwriting your customizations. -3. **Frame the request**: `aidd-refine:01:brainstorm` to clarify, `aidd-pm:01:ticket-info` to pull tracker data, `aidd-pm:02:user-stories-create` and `aidd-pm:03:prd` or `aidd-pm:04:spec` to formalize scope. -4. **Plan**: `aidd-dev:01:plan` produces the technical plan, component behavior model, or design-image extraction. -5. **Implement and assert**: `aidd-dev:02:implement` writes code against the plan; `aidd-dev:03:assert` verifies the result. -6. **Review**: `aidd-dev:05:review` for code and functional review; `aidd-refine:02:challenge` to stress-test the result. -7. **Test**: `aidd-dev:06:test` adds or runs tests and validates user journeys. -8. **Document and learn**: `aidd-context:04:mermaid` for diagrams; `aidd-context:05:learn` to feed insights back into the memory bank or rules. -9. **Ship**: `aidd-vcs:01:commit`, `aidd-vcs:02:pull-request`, then `aidd-vcs:03:release-tag` when the work is in production. File issues with `aidd-vcs:04:issue-create`. -10. **Refactor and maintain**: `aidd-dev:07:refactor` for performance or security, `aidd-dev:04:audit` for technical-debt sweeps, `aidd-dev:08:debug` to reproduce and fix bugs. +1. **Bootstrap** (only for a brand-new project): `aidd-context:01-bootstrap` imagines the stack and architecture, comparing candidate stacks and writing an `INSTALL.md`. Skip this step on an existing project. +2. **Project init** (once per project, re-runnable to refresh): `aidd-context:02-project-init` scaffolds `aidd_docs/`, the memory bank, and the AI context files for the tools you use. Re-running later refreshes the scaffold without overwriting your customizations. +3. **Frame the request**: `aidd-refine:01-brainstorm` to clarify, `aidd-pm:01-ticket-info` to pull tracker data, `aidd-pm:02-user-stories-create` and `aidd-pm:03-prd` or `aidd-pm:04-spec` to formalize scope. +4. **Plan**: `aidd-dev:01-plan` produces the technical plan, component behavior model, or design-image extraction. +5. **Implement and assert**: `aidd-dev:02-implement` writes code against the plan; `aidd-dev:03-assert` verifies the result. +6. **Review**: `aidd-dev:05-review` for code and functional review; `aidd-refine:02-challenge` to stress-test the result. +7. **Test**: `aidd-dev:06-test` adds or runs tests and validates user journeys. +8. **Document and learn**: `aidd-context:04-mermaid` for diagrams; `aidd-context:05-learn` to feed insights back into the memory bank or rules. +9. **Ship**: `aidd-vcs:01-commit`, `aidd-vcs:02-pull-request`, then `aidd-vcs:03-release-tag` when the work is in production. File issues with `aidd-vcs:04-issue-create`. +10. **Refactor and maintain**: `aidd-dev:07-refactor` for performance or security, `aidd-dev:04-audit` for technical-debt sweeps, `aidd-dev:08-debug` to reproduce and fix bugs. -When you want the whole synchronous pipeline run in one go (spec, plan, implementation, finalize), invoke `aidd-dev:00:sdlc`. +When you want the whole synchronous pipeline run in one go (spec, plan, implementation, finalize), invoke `aidd-dev:00-sdlc`. --- @@ -126,7 +126,7 @@ When you want the whole synchronous pipeline run in one go (spec, plan, implemen Beyond the synchronous path above, `aidd-orchestrator` runs the SDLC asynchronously on labeled issues (webhook or cron). This is extra: most projects do not need it. Use only when you want the AI to pick up `to-implement` issues without a human pressing a key. -Inside the synchronous path, `aidd-dev:00:sdlc` is the Dev SDLC orchestrator that drives spec, plan, implementation, finalize in one go when you want the whole pipeline at once. +Inside the synchronous path, `aidd-dev:00-sdlc` is the Dev SDLC orchestrator that drives spec, plan, implementation, finalize in one go when you want the whole pipeline at once. --- diff --git a/plugins/aidd-context/skills/03-context-generate/README.md b/plugins/aidd-context/skills/03-context-generate/README.md index 90fedd9ec..c9a79b8c4 100644 --- a/plugins/aidd-context/skills/03-context-generate/README.md +++ b/plugins/aidd-context/skills/03-context-generate/README.md @@ -30,7 +30,7 @@ Evaluations are declared before implementation; every action carries a `## Test` ## How to invoke ``` -Use skill aidd-context:03:context-generate +Use skill aidd-context:03-context-generate ``` For skill generation, the skill walks 6 atomic actions: diff --git a/plugins/aidd-context/skills/03-context-generate/SKILL.md b/plugins/aidd-context/skills/03-context-generate/SKILL.md index 7cc0748bf..0df0944fb 100644 --- a/plugins/aidd-context/skills/03-context-generate/SKILL.md +++ b/plugins/aidd-context/skills/03-context-generate/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-context:03:context-generate +name: 03-context-generate model: opus description: Generate context artifacts (skills, agents, rules, commands, hooks, plugins, marketplaces) across the host AI tool(s) the project uses. Use when the user wants to create, refactor, add or remove actions in a skill, migrate a legacy slash command into a router-based skill, or generate a new agent, rule, command, hook, plugin, or marketplace. Do NOT use for editing a single action inside an existing skill (edit directly), writing MCP servers, or modifying project-level files. --- diff --git a/plugins/aidd-context/skills/03-context-generate/actions/skills/04-draft-skill.md b/plugins/aidd-context/skills/03-context-generate/actions/skills/04-draft-skill.md index cff6e37ca..4e1777cb9 100644 --- a/plugins/aidd-context/skills/03-context-generate/actions/skills/04-draft-skill.md +++ b/plugins/aidd-context/skills/03-context-generate/actions/skills/04-draft-skill.md @@ -23,7 +23,7 @@ blocked_tools: ## Process 1. Read `@../../assets/skills/skill-template.md`. Build one canonical `SKILL.md` from the user's intent. -2. Fill the frontmatter per R5 and the naming constraints in `@../../references/skill-authoring.md`. If `invocation_mode = manual`, add `disable-model-invocation: true`. Apply field-level reconciliation from `@../../references/ai-mapping.md` for each tool (drop unsupported fields, rename as needed). +2. Fill the frontmatter per R5 and the naming constraints in `@../../references/skill-authoring.md`. **`name` MUST equal the skill's folder name**: kebab, lowercase letters/digits/hyphens only, `<=64` chars, NO colon, NO plugin prefix, NO namespace chain (never `plugin:NN:slug` - that silently fails to load on most hosts; the host builds the invocation token from plugin + folder itself). Per tool the folder, hence `name`, is `` for Claude Code / Cursor / OpenCode / GitHub Copilot, and `aidd-` for Codex CLI (its skills dir uses that prefix). If `invocation_mode = manual`, add `disable-model-invocation: true`. Apply field-level reconciliation from `@../../references/ai-mapping.md` for each tool (drop unsupported fields, rename as needed). 3. Write the action table from the plan: `#`, slug, role, required input. 4. Sequential → chain `01 → 02 → ...`; non-sequential → trigger-to-action mapping. 5. Render once per confirmed tool. For each confirmed tool, resolve the skills root from `@../../references/ai-mapping.md` (for example: Claude Code → `.claude/skills/`, Cursor → `.cursor/skills/`, Codex CLI → `.agents/skills/aidd-/`). Prepend `target_base` to the resolved path before writing (e.g. when `target_base = ""`: `.claude/skills//SKILL.md`; when `target_base = "plugins/my-plugin/"`: `plugins/my-plugin/.claude/skills//SKILL.md`). Never write relative to the plugin install directory. diff --git a/plugins/aidd-context/skills/03-context-generate/references/skill-authoring.md b/plugins/aidd-context/skills/03-context-generate/references/skill-authoring.md index be373ba5c..3fe1d6b9e 100644 --- a/plugins/aidd-context/skills/03-context-generate/references/skill-authoring.md +++ b/plugins/aidd-context/skills/03-context-generate/references/skill-authoring.md @@ -38,7 +38,7 @@ The router. Contains a YAML frontmatter block and a markdown body. Frontmatter fields - see `@command.md` for the full table (skills and commands share the same frontmatter schema). The most relevant for skills: -- `name` (string, kebab-case, <=64 chars) - falls back to the folder name. +- `name` (string, kebab-case, <=64 chars) - must equal the skill's folder name; never a colon/namespaced chain (see Hard constraints). - `description` (recommended) - drives auto-invocation. Must include explicit triggers AND a "Do NOT use" clause. - `disable-model-invocation` (boolean) - `true` makes the skill user-only. - `allowed-tools` - pre-approved tools while the skill runs. @@ -122,11 +122,25 @@ Two valid patterns, one per domain type. The `## Available actions` table in SKILL.md MUST always number entries (`01`, `02`, ...) even when the action files themselves are not prefixed. The numbers are lint anchors used by `scripts/validate-actions.js` to cross-reference; they do not imply execution order unless the skill is sequential. -### Hard constraints (Anthropic spec) +### Hard constraints (Agent Skills spec) -- SKILL.md frontmatter `name`: lowercase, letters/digits/hyphens only, <= 64 chars. Reserved words forbidden: `anthropic`, `claude`. +- SKILL.md frontmatter `name`: lowercase letters, digits, and single hyphens only - regex `^[a-z0-9]+(-[a-z0-9]+)*$`, <= 64 chars. It MUST equal the skill's folder name. No colons, no slashes, no dots, no plugin prefix, no namespace. Reserved words forbidden: `anthropic`, `claude`. - SKILL.md frontmatter `description`: <= 1024 chars, non-empty, third person, no XML tags. +### The `name` field is NOT the invocation token + +A frequent mistake is to put the full invocation chain in `name` (e.g. `name: aidd-dev:04:audit`). Do NOT. The `name` field is just the skill's local identity and must equal its folder (`04-audit`). The host builds the invocation token itself from the plugin name plus the skill folder: + +| Host | Invocation token built from `plugin` + `name` | +| ---- | --------------------------------------------- | +| Claude Code | `/aidd-dev:04-audit` (one colon = namespace separator, host-generated) | +| GitHub Copilot | `04-audit` (bare; a colon/prefix in `name` makes the skill SILENTLY fail to load) | +| Cursor / Codex CLI / OpenCode | their own scheme from the same `name` | + +So there is no single cross-tool invocation string you can author. The stable identity is the pair (plugin name in `plugin.json`, skill `name` = folder); each host renders the address. Authoring the colon chain in `name` does the opposite of consistency: it is non-conformant and silently breaks loading on every host except Claude Code (where it only survives via an unfixed bug). + +When referring to a skill from prose (hand-offs, docs), use the `plugin:folder` form (`aidd-dev:07-refactor`) as a readable pointer, never the double-colon `aidd-dev:07:refactor`. + ### Language Skills are written in **English only** - frontmatter, body, action files, references, assets, and any output blocks the skill emits at runtime. This holds regardless of the conversation language. Rationale: portability across repos and teams, and consistency with every existing skill in the canon. diff --git a/plugins/aidd-context/skills/04-mermaid/README.md b/plugins/aidd-context/skills/04-mermaid/README.md index a39cdea86..bf1dcc1ed 100644 --- a/plugins/aidd-context/skills/04-mermaid/README.md +++ b/plugins/aidd-context/skills/04-mermaid/README.md @@ -24,7 +24,7 @@ direction `LR` and targets Mermaid 10.8.0+. ## How to invoke ``` -Use skill aidd-context:04:mermaid +Use skill aidd-context:04-mermaid ``` The skill runs one action with a six-step loop: diff --git a/plugins/aidd-context/skills/04-mermaid/SKILL.md b/plugins/aidd-context/skills/04-mermaid/SKILL.md index 13ffe235f..bba9bb7b6 100644 --- a/plugins/aidd-context/skills/04-mermaid/SKILL.md +++ b/plugins/aidd-context/skills/04-mermaid/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-context:04:mermaid +name: 04-mermaid description: Generate high-quality Mermaid diagrams from markdown content using a structured plan-validate workflow. --- diff --git a/plugins/aidd-context/skills/05-learn/README.md b/plugins/aidd-context/skills/05-learn/README.md index e4b9d8485..737d24b94 100644 --- a/plugins/aidd-context/skills/05-learn/README.md +++ b/plugins/aidd-context/skills/05-learn/README.md @@ -24,7 +24,7 @@ context files so the new knowledge is in scope on the next turn. ## How to invoke ``` -Use skill aidd-context:05:learn +Use skill aidd-context:05-learn ``` The skill walks 3 atomic actions: diff --git a/plugins/aidd-context/skills/05-learn/SKILL.md b/plugins/aidd-context/skills/05-learn/SKILL.md index 481862933..ccb6adf58 100644 --- a/plugins/aidd-context/skills/05-learn/SKILL.md +++ b/plugins/aidd-context/skills/05-learn/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-context:05:learn +name: 05-learn description: Capture and store project-level learnings, conventions, and decisions surfaced during work into memory, decisions, or rules. Use proactively when the user states a durable project rule or convention ("for next", "always do X", "from now on", "going forward", "rule:", "convention:"), records a technical decision and its rationale, deprecates something, or notes an insight that should outlive the current task. Do NOT use for personal or AI-preference reminders (those belong to user memory), routine code edits, minor fixes, or anything already captured. --- diff --git a/plugins/aidd-context/skills/06-discovery/README.md b/plugins/aidd-context/skills/06-discovery/README.md index 8148fbff4..481dbb3fa 100644 --- a/plugins/aidd-context/skills/06-discovery/README.md +++ b/plugins/aidd-context/skills/06-discovery/README.md @@ -33,7 +33,7 @@ recommendation without invoking the target. ## How to invoke ``` -Use skill aidd-context:06:discovery +Use skill aidd-context:06-discovery ``` The skill picks one action based on what the user is enumerating: diff --git a/plugins/aidd-context/skills/06-discovery/SKILL.md b/plugins/aidd-context/skills/06-discovery/SKILL.md index eb3ab2f68..6a0e67785 100644 --- a/plugins/aidd-context/skills/06-discovery/SKILL.md +++ b/plugins/aidd-context/skills/06-discovery/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-context:06:discovery +name: 06-discovery description: Enumerate installed surfaces of the AI tool (skills, agents, commands, plugins, MCP servers, rules, hooks, memory files) and recommend the best match for the user's stated intent. Use proactively whenever the user asks the model to list, show, enumerate, find, or pick among any of these surfaces - including imperative phrasings ("list hooks", "show me the rules", "enumerate skills", "find a memory file", "which agent reviews code"), question phrasings ("what's available?", "what hooks do we have?", "which rule applies here?", "what memory files do we have?"), and indirect phrasings ("what can I use for X?", "do we have something that does Y?"). Always pick this skill over scanning the filesystem with grep, find, ls, or reading action files directly when the user is enumerating a surface. Do NOT use for picking a specific item inside one plugin (the plugin's own onboard handles that), creating a new surface, or executing a recommended item (this skill only points; the user invokes). --- diff --git a/plugins/aidd-context/skills/06-discovery/scripts/list-rules.mjs b/plugins/aidd-context/skills/06-discovery/scripts/list-rules.mjs index 7d9fd678c..43b95c368 100755 --- a/plugins/aidd-context/skills/06-discovery/scripts/list-rules.mjs +++ b/plugins/aidd-context/skills/06-discovery/scripts/list-rules.mjs @@ -5,7 +5,7 @@ * * Inventory project rules across every installed AI tool surface. * - * Tools and locations (see aidd-context:03:context-generate/references/ai-mapping.md): + * Tools and locations (see aidd-context:03-context-generate/references/ai-mapping.md): * - Claude Code: .claude/rules/**\/*.md * - Cursor: .cursor/rules/**\/*.mdc * - GitHub Copilot: .github/instructions/**\/*.instructions.md diff --git a/plugins/aidd-dev/README.md b/plugins/aidd-dev/README.md index 2488116d3..349b66e15 100644 --- a/plugins/aidd-dev/README.md +++ b/plugins/aidd-dev/README.md @@ -6,7 +6,7 @@ Code transformation plugin for the AI-Driven Development framework. > Status: stable. -First time? Install with `/plugin install aidd-dev@aidd-framework`, then run `aidd-dev:00:sdlc`. +First time? Install with `/plugin install aidd-dev@aidd-framework`, then run `aidd-dev:00-sdlc`. Covers the full SDLC coding loop: orchestrator, planning, implementation, assertions, audits, code review, testing, refactoring, debugging, and the for-sure workflow. Also hosts AI agents. diff --git a/plugins/aidd-dev/agents/implementer.md b/plugins/aidd-dev/agents/implementer.md index 395d570c0..6895e7282 100644 --- a/plugins/aidd-dev/agents/implementer.md +++ b/plugins/aidd-dev/agents/implementer.md @@ -56,7 +56,7 @@ Your output is complete when: - Before package installation or generated build work, make sure `.gitignore` excludes `.env`, `.env.local`, `.env.*.local`, `node_modules/`, `dist/`, `.astro/`, coverage output, and tool caches. - Never stage or commit generated artifacts (`node_modules/`, `dist/`, `.astro/`, coverage output, caches). - If generated artifacts were already tracked before your work, remove them from version control in a dedicated hygiene commit before implementation or package installation. Do not mix those deletions with feature commits. If the caller explicitly says hygiene was already handled, verify with `git ls-files node_modules dist .astro coverage`. -- **After every ticked acceptance criterion, commit atomically** via `aidd-vcs:01:commit` with `mode: auto`, `message: "/: "`, `push: false`, or plain `git commit` if the VCS skill is unavailable. One acceptance criterion = one commit. Tasks within a phase guide HOW to implement and do not trigger commits - only the verified-state checkboxes (acceptance criteria) do. This is non-negotiable: the audit trail is the safety net. +- **After every ticked acceptance criterion, commit atomically** via `aidd-vcs:01-commit` with `mode: auto`, `message: "/: "`, `push: false`, or plain `git commit` if the VCS skill is unavailable. One acceptance criterion = one commit. Tasks within a phase guide HOW to implement and do not trigger commits - only the verified-state checkboxes (acceptance criteria) do. This is non-negotiable: the audit trail is the safety net. - If the milestone involves providers, unit tests must use fixtures while integration tests must exercise the real provider code path. HTTP mocks/cassettes are acceptable only at the network boundary. - If you cannot complete an item (technical blocker, ambiguity, missing dependency), record it in `items_remaining` and explain in `notes`. Don't fake completion. - Be honest about `completion_score`. Underreporting is acceptable. Overreporting breaks the loop and produces silent failures. @@ -77,13 +77,13 @@ Your output is complete when: # Skills you may invoke -- `aidd-dev:01:plan` (read-only - for context) -- `aidd-dev:03:assert` -- `aidd-dev:06:test` -- `aidd-dev:08:debug` -- `aidd-dev:04:audit` -- `aidd-dev:07:refactor` -- `aidd-vcs:01:commit` +- `aidd-dev:01-plan` (read-only - for context) +- `aidd-dev:03-assert` +- `aidd-dev:06-test` +- `aidd-dev:08-debug` +- `aidd-dev:04-audit` +- `aidd-dev:07-refactor` +- `aidd-vcs:01-commit` Anything else is out of bounds. diff --git a/plugins/aidd-dev/agents/planner.md b/plugins/aidd-dev/agents/planner.md index fc6be602f..b61177198 100644 --- a/plugins/aidd-dev/agents/planner.md +++ b/plugins/aidd-dev/agents/planner.md @@ -8,7 +8,7 @@ model: opus You are the Planner. Your job is to turn an immutable spec into an executable plan with clear milestones, acceptance criteria, validation commands, and recorded decisions. -The top-level `aidd-dev:00:sdlc` skill owns the implementation loop. Do not try to spawn implementer or reviewer agents. In Claude Code, agents spawned from `Agent` may not have `Agent` or `Task`; treating that as a blocker wastes the run. Return plans and structured decisions only. +The top-level `aidd-dev:00-sdlc` skill owns the implementation loop. Do not try to spawn implementer or reviewer agents. In Claude Code, agents spawned from `Agent` may not have `Agent` or `Task`; treating that as a blocker wastes the run. Return plans and structured decisions only. # Inputs @@ -40,7 +40,7 @@ plan_status: in_progress | done | blocked notes: ``` -`plan_path` and `child_paths` reflect what `aidd-dev:01:plan` actually wrote - the skill picks the path (typically `aidd_docs/tasks//-?<#ticket>-.md` for simple plans, plus `*-master.md` and `*-part-N.md` for master plans). Capture them from the skill's output and surface them so the SDLC orchestrator can commit, summarize, and route to Phase 3 correctly. +`plan_path` and `child_paths` reflect what `aidd-dev:01-plan` actually wrote - the skill picks the path (typically `aidd_docs/tasks//-?<#ticket>-.md` for simple plans, plus `*-master.md` and `*-part-N.md` for master plans). Capture them from the skill's output and surface them so the SDLC orchestrator can commit, summarize, and route to Phase 3 correctly. # Definition of Ready @@ -85,11 +85,11 @@ The plan is complete when: # Skills you may invoke -- `aidd-refine:01:brainstorm` -- `aidd-refine:02:challenge` -- `aidd-context:04:mermaid` -- `aidd-context:05:learn` -- `aidd-dev:01:plan` +- `aidd-refine:01-brainstorm` +- `aidd-refine:02-challenge` +- `aidd-context:04-mermaid` +- `aidd-context:05-learn` +- `aidd-dev:01-plan` Anything else is out of bounds. diff --git a/plugins/aidd-dev/agents/reviewer.md b/plugins/aidd-dev/agents/reviewer.md index 87b84ba03..6724f0128 100644 --- a/plugins/aidd-dev/agents/reviewer.md +++ b/plugins/aidd-dev/agents/reviewer.md @@ -96,8 +96,8 @@ The way you compute `quality_score` depends on the validator format. # Skills you may invoke -- `aidd-dev:05:review` -- `aidd-dev:04:audit` +- `aidd-dev:05-review` +- `aidd-dev:04-audit` Anything else is out of bounds. diff --git a/plugins/aidd-dev/skills/00-sdlc/SKILL.md b/plugins/aidd-dev/skills/00-sdlc/SKILL.md index faa9fb84b..fc460db26 100644 --- a/plugins/aidd-dev/skills/00-sdlc/SKILL.md +++ b/plugins/aidd-dev/skills/00-sdlc/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:00:sdlc +name: 00-sdlc description: Pure orchestrator for the full AIDD development flow. Use when a human (or Gardener) needs to take a free-form request from idea to shipped code, end-to-end. Coordinates spec generation, planning, implementation, review, and shipping by composing other skills and agents. Supports two modes - `auto` (default, no human interaction) and `interactive` (pauses for human confirmation at key gates). Holds no business logic of its own; every step is delegated. --- diff --git a/plugins/aidd-dev/skills/01-plan/README.md b/plugins/aidd-dev/skills/01-plan/README.md index abb666ab1..9962491ac 100644 --- a/plugins/aidd-dev/skills/01-plan/README.md +++ b/plugins/aidd-dev/skills/01-plan/README.md @@ -27,7 +27,7 @@ images. The plan file is the single source of truth that downstream skills ## How to invoke ``` -Use skill aidd-dev:01:plan +Use skill aidd-dev:01-plan ``` The skill exposes 3 actions: diff --git a/plugins/aidd-dev/skills/01-plan/SKILL.md b/plugins/aidd-dev/skills/01-plan/SKILL.md index e7c789dea..a951e4fc5 100644 --- a/plugins/aidd-dev/skills/01-plan/SKILL.md +++ b/plugins/aidd-dev/skills/01-plan/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:01:plan +name: 01-plan description: Generate technical implementation plans, define component behaviors, and extract design details from images. model: opus context: fork diff --git a/plugins/aidd-dev/skills/02-implement/README.md b/plugins/aidd-dev/skills/02-implement/README.md index 6c0ad8e6e..8708a7773 100644 --- a/plugins/aidd-dev/skills/02-implement/README.md +++ b/plugins/aidd-dev/skills/02-implement/README.md @@ -23,7 +23,7 @@ loops until the agent reports 100 % completion. ## How to invoke ``` -Use skill aidd-dev:02:implement +Use skill aidd-dev:02-implement ``` Pass the plan path or content as `$ARGUMENTS`. The skill exposes 1 action: diff --git a/plugins/aidd-dev/skills/02-implement/SKILL.md b/plugins/aidd-dev/skills/02-implement/SKILL.md index 4540f7426..2f5c4efa6 100644 --- a/plugins/aidd-dev/skills/02-implement/SKILL.md +++ b/plugins/aidd-dev/skills/02-implement/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:02:implement +name: 02-implement description: Execute an implementation plan phase by phase via the implementer agent, iterating until 100% completeness. context: fork agent: implementer diff --git a/plugins/aidd-dev/skills/03-assert/README.md b/plugins/aidd-dev/skills/03-assert/README.md index ec35715db..c0a9c0698 100644 --- a/plugins/aidd-dev/skills/03-assert/README.md +++ b/plugins/aidd-dev/skills/03-assert/README.md @@ -27,7 +27,7 @@ structure), and browser-based frontend UI checks. ## How to invoke ``` -Use skill aidd-dev:03:assert +Use skill aidd-dev:03-assert ``` The skill exposes 3 actions: diff --git a/plugins/aidd-dev/skills/03-assert/SKILL.md b/plugins/aidd-dev/skills/03-assert/SKILL.md index 458a9b457..326463809 100644 --- a/plugins/aidd-dev/skills/03-assert/SKILL.md +++ b/plugins/aidd-dev/skills/03-assert/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:03:assert +name: 03-assert description: Assert features work as intended - general assertions, architecture conformance, and frontend UI validation. model: sonnet --- diff --git a/plugins/aidd-dev/skills/04-audit/README.md b/plugins/aidd-dev/skills/04-audit/README.md index 506cc035c..f4cc8621b 100644 --- a/plugins/aidd-dev/skills/04-audit/README.md +++ b/plugins/aidd-dev/skills/04-audit/README.md @@ -26,7 +26,7 @@ wanted. ## How to invoke ``` -Use skill aidd-dev:04:audit +Use skill aidd-dev:04-audit ``` Run-one or run-all: diff --git a/plugins/aidd-dev/skills/04-audit/SKILL.md b/plugins/aidd-dev/skills/04-audit/SKILL.md index 6a634780b..d4f98968b 100644 --- a/plugins/aidd-dev/skills/04-audit/SKILL.md +++ b/plugins/aidd-dev/skills/04-audit/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:04:audit +name: 04-audit description: Read-only codebase audit across quality pillars (code-quality, architecture, security, dependencies, performance, tests, ui). Diagnoses and reports findings; never edits code. Use when the user wants to assess, audit, or health-check a codebase or one dimension of it, then hands off to the act-skills (refactor, test, impeccable) to fix. Do NOT use for fixing the findings (hand off to refactor/test/impeccable), per-PR code review (use 05-review), or validating that a feature works (use 03-assert). model: opus --- diff --git a/plugins/aidd-dev/skills/04-audit/actions/01-code-quality.md b/plugins/aidd-dev/skills/04-audit/actions/01-code-quality.md index 66457c757..cc2f4ae08 100644 --- a/plugins/aidd-dev/skills/04-audit/actions/01-code-quality.md +++ b/plugins/aidd-dev/skills/04-audit/actions/01-code-quality.md @@ -24,7 +24,7 @@ findings_count: - **Tech debt (structural)**: dead and unreachable code, unused exports/types/helpers, stale TODOs, vestigial flags, cyclomatic complexity and file/function/component length above project thresholds, nesting depth, error handling caught at the wrong boundary or silently swallowed. - Use dedicated tools when available (e.g. an unused-export finder); never assert dead code without evidence. 3. **Rate each finding.** Severity (🔴 / 🟡 / 🟢) and effort (S/M/L) per `@../assets/audit-template.md` legend. Quote a concrete `file:line` for every finding. Category is always `code-quality`. -4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off fixes to `aidd-dev:07:refactor`), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. +4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off fixes to `aidd-dev:07-refactor`), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. ## Test diff --git a/plugins/aidd-dev/skills/04-audit/actions/02-architecture.md b/plugins/aidd-dev/skills/04-audit/actions/02-architecture.md index 48ab25231..f5685ef97 100644 --- a/plugins/aidd-dev/skills/04-audit/actions/02-architecture.md +++ b/plugins/aidd-dev/skills/04-audit/actions/02-architecture.md @@ -25,7 +25,7 @@ findings_count: - **God-modules**: detect modules with an abnormally large surface area (too many exports, too many responsibilities) that signal architectural erosion. - When ADRs or C4 diagrams are absent, note "no architecture docs found - conformance check skipped" in Coverage > Skipped and limit the scan to observable coupling heuristics. 3. **Rate each finding.** Severity (🔴 / 🟡 / 🟢) and effort (S/M/L) per `@../assets/audit-template.md` legend. Quote a concrete `file:line` for every finding. Category is always `architecture`. -4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (conformance gaps feed re-planning; structural fixes hand off to `aidd-dev:07:refactor`), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. +4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (conformance gaps feed re-planning; structural fixes hand off to `aidd-dev:07-refactor`), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. ## Test diff --git a/plugins/aidd-dev/skills/04-audit/actions/03-security.md b/plugins/aidd-dev/skills/04-audit/actions/03-security.md index 3c167598c..e504f549b 100644 --- a/plugins/aidd-dev/skills/04-audit/actions/03-security.md +++ b/plugins/aidd-dev/skills/04-audit/actions/03-security.md @@ -28,7 +28,7 @@ findings_count: - **Insecure defaults**: missing TLS enforcement, overly permissive CORS, disabled security headers, debug flags left on in non-dev code. - Use static analysis tools when available; flag only findings supported by code evidence. Do not infer from naming alone. 3. **Rate each finding.** Severity (🔴 / 🟡 / 🟢) and effort (S/M/L) per `@../assets/audit-template.md` legend. Quote a concrete `file:line` for every finding. Category is always `security`. -4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off fixes to `aidd-dev:07:refactor` for security), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. +4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off fixes to `aidd-dev:07-refactor` for security), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. ## Test diff --git a/plugins/aidd-dev/skills/04-audit/actions/04-dependencies.md b/plugins/aidd-dev/skills/04-audit/actions/04-dependencies.md index a64885271..c0ab991a1 100644 --- a/plugins/aidd-dev/skills/04-audit/actions/04-dependencies.md +++ b/plugins/aidd-dev/skills/04-audit/actions/04-dependencies.md @@ -26,7 +26,7 @@ findings_count: - **Unused declared dependencies**: flag packages listed in the manifest but with no import found in the scanned source. - **Lockfile integrity and supply-chain**: verify the lockfile is present and committed; flag direct git/URL dependencies and any package with no integrity hash. 3. **Rate each finding.** Severity (🔴 / 🟡 / 🟢) and effort (S/M/L) per `@../assets/audit-template.md` legend. Quote a concrete `file:line` (manifest or lockfile line) for every finding. Category is always `dependencies`. -4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off upgrades to `aidd-dev:07:refactor` or manual upgrade), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. +4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off upgrades to `aidd-dev:07-refactor` or manual upgrade), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. ## Test diff --git a/plugins/aidd-dev/skills/04-audit/actions/05-performance.md b/plugins/aidd-dev/skills/04-audit/actions/05-performance.md index 6280c9686..919e7e7fa 100644 --- a/plugins/aidd-dev/skills/04-audit/actions/05-performance.md +++ b/plugins/aidd-dev/skills/04-audit/actions/05-performance.md @@ -28,7 +28,7 @@ findings_count: - **Missing memoization on hot paths**: flag expensive pure computations inside render or tight loops that are not memoized. - When no profiler or bundle analyzer is available, degrade to static heuristics and record "no profiler - static heuristics only" in Coverage > Skipped. Never assert a runtime bottleneck without evidence. 3. **Rate each finding.** Severity (🔴 / 🟡 / 🟢) and effort (S/M/L) per `@../assets/audit-template.md` legend. Quote a concrete `file:line` for every finding. Category is always `performance`. -4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off fixes to `aidd-dev:07:refactor` for performance), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. +4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off fixes to `aidd-dev:07-refactor` for performance), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. ## Test diff --git a/plugins/aidd-dev/skills/04-audit/actions/06-tests.md b/plugins/aidd-dev/skills/04-audit/actions/06-tests.md index d37ac3574..3a6e7d73a 100644 --- a/plugins/aidd-dev/skills/04-audit/actions/06-tests.md +++ b/plugins/aidd-dev/skills/04-audit/actions/06-tests.md @@ -19,7 +19,7 @@ findings_count: ## Process 1. **Load scope.** Default to the full codebase when `scope` is absent; otherwise restrict scanning to the provided glob or directory. -2. **Scan the tests lens** below, preferring a coverage report when available. Stay in this pillar - whether a feature behaves correctly belongs to `aidd-dev:03:assert`; runtime cost to `05-performance`. +2. **Scan the tests lens** below, preferring a coverage report when available. Stay in this pillar - whether a feature behaves correctly belongs to `aidd-dev:03-assert`; runtime cost to `05-performance`. - **Critical-path coverage gaps**: identify code paths (auth flows, data mutations, error handling) that have no corresponding test; use a coverage report when available, degrade to static inspection of test-file presence when absent. - **Tests asserting implementation instead of behavior**: flag tests that couple to internal method names, private state, or implementation details rather than observable outputs. - **Flaky tests**: flag tests that use arbitrary `sleep` calls, rely on timing, or have known intermittent failures recorded in CI history or inline comments. @@ -27,7 +27,7 @@ findings_count: - **Test pyramid imbalance**: flag suites with disproportionately many end-to-end or integration tests and few unit tests, raising maintenance cost and feedback speed. - When no coverage tool is available, record "no coverage tool - static inspection only" in Coverage > Skipped and limit findings to structurally observable issues. Do not invent coverage numbers. 3. **Rate each finding.** Severity (🔴 / 🟡 / 🟢) and effort (S/M/L) per `@../assets/audit-template.md` legend. Quote a concrete `file:line` for every finding. Category is always `tests`. -4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off new or fixed tests to `aidd-dev:06:test`), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. +4. **Write the report** using `@../assets/audit-template.md`: fill the Findings table (one row per issue, severity-first), ranked Top actions (hand off new or fixed tests to `aidd-dev:06-test`), and the Coverage section. In a full audit run, contribute these finding rows to the single merged report per the skill output contract instead of writing a separate file. Read-only: emit the report and stop; do not edit code. ## Test diff --git a/plugins/aidd-dev/skills/05-review/README.md b/plugins/aidd-dev/skills/05-review/README.md index 30d8d3b03..72003c6f7 100644 --- a/plugins/aidd-dev/skills/05-review/README.md +++ b/plugins/aidd-dev/skills/05-review/README.md @@ -28,7 +28,7 @@ and quality scores. Never edits the artifact. ## How to invoke ``` -Use skill aidd-dev:05:review +Use skill aidd-dev:05-review ``` The skill exposes 2 actions: diff --git a/plugins/aidd-dev/skills/05-review/SKILL.md b/plugins/aidd-dev/skills/05-review/SKILL.md index a9a1c5e99..5de8c5f9f 100644 --- a/plugins/aidd-dev/skills/05-review/SKILL.md +++ b/plugins/aidd-dev/skills/05-review/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:05:review +name: 05-review description: Read-only review of a diff (a PR or working changes) - code quality against project rules, and feature behavior against the plan's acceptance criteria. Surfaces findings with a verdict; never patches. Use to review changes in progress. Do NOT use for a whole-codebase health check (use 04-audit), fixing the findings (hand off to 07-refactor / 02-implement / 08-debug), or validating a feature runs (use 03-assert). model: opus context: fork @@ -8,7 +8,7 @@ agent: reviewer # Skill: review -Read-only review of a diff (a PR or working changes): code quality against project rules, and feature behavior against the plan's acceptance criteria. It surfaces findings and a verdict; it never edits code. The fix hands off to the act-skills (`07-refactor` for code, `02-implement` / `08-debug` for behavior gaps). Diff-scoped - for a whole-codebase read-only diagnosis use `aidd-dev:04:audit` instead. +Read-only review of a diff (a PR or working changes): code quality against project rules, and feature behavior against the plan's acceptance criteria. It surfaces findings and a verdict; it never edits code. The fix hands off to the act-skills (`07-refactor` for code, `02-implement` / `08-debug` for behavior gaps). Diff-scoped - for a whole-codebase read-only diagnosis use `aidd-dev:04-audit` instead. ## Agent delegation diff --git a/plugins/aidd-dev/skills/05-review/actions/01-review-code.md b/plugins/aidd-dev/skills/05-review/actions/01-review-code.md index 6e75b3f0f..63978f697 100644 --- a/plugins/aidd-dev/skills/05-review/actions/01-review-code.md +++ b/plugins/aidd-dev/skills/05-review/actions/01-review-code.md @@ -1,6 +1,6 @@ # 01 - Review Code -Deep code review of a diff against project rules and clean-code principles. Read-only: surface quality violations only, never patch them - hand fixes off to `aidd-dev:07:refactor`. +Deep code review of a diff against project rules and clean-code principles. Read-only: surface quality violations only, never patch them - hand fixes off to `aidd-dev:07-refactor`. ## Inputs @@ -26,7 +26,7 @@ severity_breakdown: 2. **Deep review every changed line.** Apply project conventions and global clean-code principles. No runtime checks. 3. **Findings only.** Focus on issues on the changed lines; do not propose feature-level changes. Rate each with the 3-level severity (🔴 critical / 🟡 warning / 🟢 minor) and cite a `file:line`. Suggested fixes are described, not patched (read-only). 4. **Set the verdict** per the template: `blocked` if any unaddressed 🔴, `changes-requested` if 🟡 (or a fixable 🔴), else `approve`. -5. **Format the report** using `@../assets/review-code-template.md` (Expected changes, Findings, Coverage, Follow-up). Top fixes hand off to `aidd-dev:07:refactor`. +5. **Format the report** using `@../assets/review-code-template.md` (Expected changes, Findings, Coverage, Follow-up). Top fixes hand off to `aidd-dev:07-refactor`. 6. **Write to disk** at `aidd_docs/tasks//-.review.md`. Create the month directory when missing. ## Test diff --git a/plugins/aidd-dev/skills/05-review/actions/02-review-functional.md b/plugins/aidd-dev/skills/05-review/actions/02-review-functional.md index 2c57586d8..d8ae4b896 100644 --- a/plugins/aidd-dev/skills/05-review/actions/02-review-functional.md +++ b/plugins/aidd-dev/skills/05-review/actions/02-review-functional.md @@ -1,6 +1,6 @@ # 02 - Review Functional -Verify the implemented feature matches the plan's acceptance criteria, flows, and edge cases. Static review of the current diff against plan intent. No app execution, no browser, no code-quality checks. Read-only: surface gaps, never patch them - hand a missing behavior off to `aidd-dev:02:implement`, a broken one to `aidd-dev:08:debug`. +Verify the implemented feature matches the plan's acceptance criteria, flows, and edge cases. Static review of the current diff against plan intent. No app execution, no browser, no code-quality checks. Read-only: surface gaps, never patch them - hand a missing behavior off to `aidd-dev:02-implement`, a broken one to `aidd-dev:08-debug`. ## Inputs diff --git a/plugins/aidd-dev/skills/05-review/assets/review-code-template.md b/plugins/aidd-dev/skills/05-review/assets/review-code-template.md index 32297f92a..2fbff2910 100644 --- a/plugins/aidd-dev/skills/05-review/assets/review-code-template.md +++ b/plugins/aidd-dev/skills/05-review/assets/review-code-template.md @@ -24,7 +24,7 @@ What the diff was meant to deliver (from the ticket or plan). Tick what the diff ## Findings -One row per issue, on the CHANGED lines only (this is a diff review, not a codebase audit). Every row cites a `file:line`. Sort by severity. Read-only: describe the fix, do not patch it - hand fixes off to `aidd-dev:07:refactor`. +One row per issue, on the CHANGED lines only (this is a diff review, not a codebase audit). Every row cites a `file:line`. Sort by severity. Read-only: describe the fix, do not patch it - hand fixes off to `aidd-dev:07-refactor`. Severity: 🔴 critical (must not merge as-is), 🟡 warning (should fix), 🟢 minor (nit). Category (one of): `standards`, `architecture`, `code-health`, `security`, `error-handling`, `performance`, `frontend`, `backend`. @@ -43,5 +43,5 @@ Dimensions examined on the diff (a dimension with no finding is still listed her ## Follow-up -- **Top fixes** (ranked, hand off to `aidd-dev:07:refactor`): {{top_fixes}} +- **Top fixes** (ranked, hand off to `aidd-dev:07-refactor`): {{top_fixes}} - **Notes**: {{additional_notes}} diff --git a/plugins/aidd-dev/skills/05-review/assets/review-functional-template.md b/plugins/aidd-dev/skills/05-review/assets/review-functional-template.md index 17216bacc..9de9d828d 100644 --- a/plugins/aidd-dev/skills/05-review/assets/review-functional-template.md +++ b/plugins/aidd-dev/skills/05-review/assets/review-functional-template.md @@ -29,7 +29,7 @@ One row per acceptance criterion. Severity uses the shared 3-level scale (it app ## Missing behaviors -Acceptance criteria with no trace in the diff (hand off implementation to `aidd-dev:02:implement`; if a criterion is implemented but broken, hand off to `aidd-dev:08:debug`). +Acceptance criteria with no trace in the diff (hand off implementation to `aidd-dev:02-implement`; if a criterion is implemented but broken, hand off to `aidd-dev:08-debug`). - [ ] {{criterion not found in diff}} diff --git a/plugins/aidd-dev/skills/06-test/README.md b/plugins/aidd-dev/skills/06-test/README.md index 183de310a..452e78260 100644 --- a/plugins/aidd-dev/skills/06-test/README.md +++ b/plugins/aidd-dev/skills/06-test/README.md @@ -26,7 +26,7 @@ then drives test creation until quality criteria are met. ## How to invoke ``` -Use skill aidd-dev:06:test +Use skill aidd-dev:06-test ``` The skill exposes 2 actions: diff --git a/plugins/aidd-dev/skills/06-test/SKILL.md b/plugins/aidd-dev/skills/06-test/SKILL.md index b489b1e9e..aa1e8bd84 100644 --- a/plugins/aidd-dev/skills/06-test/SKILL.md +++ b/plugins/aidd-dev/skills/06-test/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:06:test +name: 06-test description: Write and iterate on tests until they pass, and validate user journeys end-to-end in the browser. model: sonnet --- diff --git a/plugins/aidd-dev/skills/07-refactor/README.md b/plugins/aidd-dev/skills/07-refactor/README.md index c72a47b07..cedcd2da8 100644 --- a/plugins/aidd-dev/skills/07-refactor/README.md +++ b/plugins/aidd-dev/skills/07-refactor/README.md @@ -27,7 +27,7 @@ reports, refactor fixes. ## How to invoke ``` -Use skill aidd-dev:07:refactor +Use skill aidd-dev:07-refactor ``` Run-one or run-all: diff --git a/plugins/aidd-dev/skills/07-refactor/SKILL.md b/plugins/aidd-dev/skills/07-refactor/SKILL.md index 0a524e113..a0a88431e 100644 --- a/plugins/aidd-dev/skills/07-refactor/SKILL.md +++ b/plugins/aidd-dev/skills/07-refactor/SKILL.md @@ -1,11 +1,11 @@ --- -name: aidd-dev:07:refactor +name: 07-refactor description: Improve code without breaking behavior across four axes - cleanup (clean-code + tech debt), performance, security, architecture. Scans and fixes, or fixes the findings of an audit report pushed in by the caller. Use when the user wants to refactor, clean up, optimize, harden, or restructure code. Do NOT use for read-only diagnosis (use 04-audit), adding tests (use 06-test), or UI redesign (use the impeccable skill). --- # Skill: refactor -The act-side of code improvement: it changes code to make it better. Behavior-preserving for cleanup, performance, and architecture; security may change behavior on purpose to close a hole. The read-only diagnosis counterpart is `aidd-dev:04:audit` - refactor fixes, audit reports. +The act-side of code improvement: it changes code to make it better. Behavior-preserving for cleanup, performance, and architecture; security may change behavior on purpose to close a hole. The read-only diagnosis counterpart is `aidd-dev:04-audit` - refactor fixes, audit reports. ## Available actions @@ -31,13 +31,13 @@ This skill NEVER loads or invokes the audit skill - that would make refactor dep - **Standalone (default).** The action scans its axis with its own lens, then fixes. Self-contained; this is the existing behavior. - **Audit-fed (optional).** If the caller PUSHES an `audit_report` (a path to a report under `aidd_docs/tasks/audits/`, or pasted findings), the action takes that report's findings for its axis as the fix list and skips its own scan. -The bridge is the report artifact (data), not a cross-skill reference. For a broad read-only diagnosis before fixing, the user may run `aidd-dev:04:audit` first and push its report in - a suggestion, never a dependency. +The bridge is the report artifact (data), not a cross-skill reference. For a broad read-only diagnosis before fixing, the user may run `aidd-dev:04-audit` first and push its report in - a suggestion, never a dependency. ## Conventions - Severity on any finding uses the shared 3-level scale: 🔴 critical, 🟡 warning, 🟢 minor (aligned with audit, so a pushed audit report flows in without translation). - Behavior-preserving for cleanup, performance, and architecture: public inputs and outputs stay identical; verify via tests, type checks, or a side-by-side run. Security may alter behavior to close a vulnerability - call that out explicitly. -- Stay inside the axis. Boundaries mirror audit: dependency upgrades (CVE bumps, version maintenance) are out of scope here; test creation belongs to `aidd-dev:06:test`; UI redesign to the impeccable skill. +- Stay inside the axis. Boundaries mirror audit: dependency upgrades (CVE bumps, version maintenance) are out of scope here; test creation belongs to `aidd-dev:06-test`; UI redesign to the impeccable skill. ## Actions diff --git a/plugins/aidd-dev/skills/07-refactor/actions/04-architecture.md b/plugins/aidd-dev/skills/07-refactor/actions/04-architecture.md index ee03bfb9b..44358ad02 100644 --- a/plugins/aidd-dev/skills/07-refactor/actions/04-architecture.md +++ b/plugins/aidd-dev/skills/07-refactor/actions/04-architecture.md @@ -19,7 +19,7 @@ changes_applied: - { file: , change: , severity: "🔴|🟡|🟢" } verification: deferred_to_plan: - - + - ``` ## Process diff --git a/plugins/aidd-dev/skills/08-debug/README.md b/plugins/aidd-dev/skills/08-debug/README.md index 18bbee127..10775b765 100644 --- a/plugins/aidd-dev/skills/08-debug/README.md +++ b/plugins/aidd-dev/skills/08-debug/README.md @@ -27,7 +27,7 @@ apply a targeted fix. Drives the loop from issue to PR. ## How to invoke ``` -Use skill aidd-dev:08:debug +Use skill aidd-dev:08-debug ``` The skill exposes 3 actions: diff --git a/plugins/aidd-dev/skills/08-debug/SKILL.md b/plugins/aidd-dev/skills/08-debug/SKILL.md index d1473aeff..f809908c8 100644 --- a/plugins/aidd-dev/skills/08-debug/SKILL.md +++ b/plugins/aidd-dev/skills/08-debug/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:08:debug +name: 08-debug description: Reproduce and fix bugs systematically using test-driven workflow, root cause analysis, and hypothesis validation. model: opus --- diff --git a/plugins/aidd-dev/skills/09-for-sure/SKILL.md b/plugins/aidd-dev/skills/09-for-sure/SKILL.md index 4d96755cd..f558d744c 100644 --- a/plugins/aidd-dev/skills/09-for-sure/SKILL.md +++ b/plugins/aidd-dev/skills/09-for-sure/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-dev:09:for-sure +name: 09-for-sure description: Iterative agent loop that tracks attempts and retries until a success condition is met. Use when the user says "for sure", "make sure", "keep trying until", "loop until done", "don't stop until", or needs guaranteed completion of a task with explicit success criteria. --- diff --git a/plugins/aidd-orchestrator/README.md b/plugins/aidd-orchestrator/README.md index f45474095..3c90de175 100644 --- a/plugins/aidd-orchestrator/README.md +++ b/plugins/aidd-orchestrator/README.md @@ -6,7 +6,7 @@ Orchestration plugin for the AI-Driven Development framework. > Status: stable for use case `async-dev`; other use cases on the roadmap are experimental. -First time? Install with `/plugin install aidd-orchestrator@aidd-framework`, then run `aidd-orchestrator:00:async-dev` with `action=setup` (or just describe what you want — the router decides). +First time? Install with `/plugin install aidd-orchestrator@aidd-framework`, then run `aidd-orchestrator:00-async-dev` with `action=setup` (or just describe what you want; the router decides). Composes capabilities into deterministic, auditable flows. Each skill is one orchestration brick; several use cases coexist inside the same plugin. diff --git a/plugins/aidd-orchestrator/skills/00-async-dev/README.md b/plugins/aidd-orchestrator/skills/00-async-dev/README.md index f40b7c551..14352618d 100644 --- a/plugins/aidd-orchestrator/skills/00-async-dev/README.md +++ b/plugins/aidd-orchestrator/skills/00-async-dev/README.md @@ -20,15 +20,15 @@ Single entry point for the async-dev pipeline. Hybrid router that picks one of t ## How to invoke ```text -Use skill aidd-orchestrator:00:async-dev +Use skill aidd-orchestrator:00-async-dev ``` With an explicit sub-flow keyword (preferred from CI): ```text -Use skill aidd-orchestrator:00:async-dev with action=setup -Use skill aidd-orchestrator:00:async-dev with action=run on issue #42 -Use skill aidd-orchestrator:00:async-dev with action=review on PR #17 +Use skill aidd-orchestrator:00-async-dev with action=setup +Use skill aidd-orchestrator:00-async-dev with action=run on issue #42 +Use skill aidd-orchestrator:00-async-dev with action=review on PR #17 ``` The router reads `$ARGUMENTS`, then trigger env, then repo state, then natural intent. See [`references/routing.md`](references/routing.md) for the full decision tree. diff --git a/plugins/aidd-orchestrator/skills/00-async-dev/SKILL.md b/plugins/aidd-orchestrator/skills/00-async-dev/SKILL.md index c79082d12..781f540c7 100644 --- a/plugins/aidd-orchestrator/skills/00-async-dev/SKILL.md +++ b/plugins/aidd-orchestrator/skills/00-async-dev/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-orchestrator:00:async-dev +name: 00-async-dev description: Single entry point for the async-dev pipeline (setup, run, review). Hybrid router decides which sub-flow to execute from $ARGUMENTS keyword (`setup` / `run` / `review`), trigger source (label `to-implement` / `to-review`, comment `@claude /implement` / `/review`), repo state (workflow + config presence, PR linked to issue), or natural-language intent. Use when the user says "set up async dev", "run async dev on issue #N", "address review on PR #N", "/async-dev", "claude on issues", or when triggered by a webhook with the matching labels or comments. Do NOT use for plain status checks on the async pipeline or for SDLC orchestration unrelated to issue/PR automation. --- @@ -25,7 +25,7 @@ Walk in order. First match wins. 2. **Trigger env.** When invoked from CI (`GITHUB_EVENT_NAME` set): - Label payload `to-implement` → `run`. - Label payload `to-review` → `review`. - - Comment body matches `@claude /implement` (or `/aidd-dev:02:implement`) → `run`. + - Comment body matches `@claude /implement` (or `/aidd-dev:02-implement`) → `run`. - Comment body matches `@claude /review` → `review`. 3. **Repo state.** - Missing `.github/workflows/aidd-async.yml` AND missing `.claude/aidd-orchestrator.json` → `setup`. diff --git a/plugins/aidd-orchestrator/skills/00-async-dev/actions/setup/09-bootstrap-scheduling.md b/plugins/aidd-orchestrator/skills/00-async-dev/actions/setup/09-bootstrap-scheduling.md index c36f87d52..7f659f5eb 100644 --- a/plugins/aidd-orchestrator/skills/00-async-dev/actions/setup/09-bootstrap-scheduling.md +++ b/plugins/aidd-orchestrator/skills/00-async-dev/actions/setup/09-bootstrap-scheduling.md @@ -46,7 +46,7 @@ Schedules `scripts/aidd-async-poll.sh` via the cheapest path that fits the user' - Set `path = "local_daemon"`. - **B (manual)**: print `./scripts/aidd-async-poll.sh` and a reminder that nothing runs until invoked. Set `path = "manual"`. - **D (Desktop task)**: print the four UI bullets from the reference (Path D), filled with the working directory, schedule, and prompt. Warn about the per-tick Tasks quota. Set `path = "desktop_task_pending"`. - - **E (cloud routine)**: invoke the runtime `/schedule` skill via the `Skill` tool with a cron expression (must be at least hourly) and the prompt `Use skill aidd-orchestrator:00:async-dev with action=run on the next ready issue in /`. Capture the routine id. Set `path = "schedule_routine"`. + - **E (cloud routine)**: invoke the runtime `/schedule` skill via the `Skill` tool with a cron expression (must be at least hourly) and the prompt `Use skill aidd-orchestrator:00-async-dev with action=run on the next ready issue in /`. Capture the routine id. Set `path = "schedule_routine"`. 5. Emit the structured result. ## Test diff --git a/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/local-poll-template.sh b/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/local-poll-template.sh index 00fdff723..b8ba6deab 100644 --- a/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/local-poll-template.sh +++ b/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/local-poll-template.sh @@ -76,7 +76,7 @@ process_label() { done <<< "$issues" } -process_label "$TO_IMPLEMENT" "Use skill aidd-orchestrator:00:async-dev with action=run on issue #NUM in $REPO" -process_label "$TO_REVIEW" "Use skill aidd-orchestrator:00:async-dev with action=review for issue #NUM in $REPO" +process_label "$TO_IMPLEMENT" "Use skill aidd-orchestrator:00-async-dev with action=run on issue #NUM in $REPO" +process_label "$TO_REVIEW" "Use skill aidd-orchestrator:00-async-dev with action=review for issue #NUM in $REPO" log "done" diff --git a/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/workflow-template.yml b/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/workflow-template.yml index 60ded2be6..01ad3e456 100644 --- a/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/workflow-template.yml +++ b/plugins/aidd-orchestrator/skills/00-async-dev/assets/setup/workflow-template.yml @@ -157,7 +157,7 @@ jobs: - name: Run aidd-orchestrator pipeline uses: anthropics/claude-code-action@v1 with: - prompt: "Use skill aidd-orchestrator:00:async-dev with action=run on issue #${{ needs.dispatch.outputs.issue_number }} (trigger_kind=${{ needs.dispatch.outputs.trigger_kind }}, trigger_comment_url=${{ needs.dispatch.outputs.trigger_comment_url }}). Fetch every comment newer than the last bot activity on the issue and feed them to the SDLC delegation as additional user direction." + prompt: "Use skill aidd-orchestrator:00-async-dev with action=run on issue #${{ needs.dispatch.outputs.issue_number }} (trigger_kind=${{ needs.dispatch.outputs.trigger_kind }}, trigger_comment_url=${{ needs.dispatch.outputs.trigger_comment_url }}). Fetch every comment newer than the last bot activity on the issue and feed them to the SDLC delegation as additional user direction." __CLAUDE_AUTH_LINE__ __GITHUB_WRITE_TOKEN_LINE__ plugins: | @@ -252,7 +252,7 @@ jobs: - name: Run aidd-orchestrator review loop uses: anthropics/claude-code-action@v1 with: - prompt: "Use skill aidd-orchestrator:00:async-dev with action=review on PR #${{ needs.dispatch.outputs.issue_number }} (trigger_kind=${{ needs.dispatch.outputs.trigger_kind }}, trigger_comment_url=${{ needs.dispatch.outputs.trigger_comment_url }}, source_issue_number=${{ needs.dispatch.outputs.source_issue_number }}). Collect comments from both the PR and its linked issue newer than the last iteration before deciding stop vs continue." + prompt: "Use skill aidd-orchestrator:00-async-dev with action=review on PR #${{ needs.dispatch.outputs.issue_number }} (trigger_kind=${{ needs.dispatch.outputs.trigger_kind }}, trigger_comment_url=${{ needs.dispatch.outputs.trigger_comment_url }}, source_issue_number=${{ needs.dispatch.outputs.source_issue_number }}). Collect comments from both the PR and its linked issue newer than the last iteration before deciding stop vs continue." __CLAUDE_AUTH_LINE__ __GITHUB_WRITE_TOKEN_LINE__ plugins: | diff --git a/plugins/aidd-orchestrator/skills/00-async-dev/references/routing.md b/plugins/aidd-orchestrator/skills/00-async-dev/references/routing.md index 397072f6f..d6ec55736 100644 --- a/plugins/aidd-orchestrator/skills/00-async-dev/references/routing.md +++ b/plugins/aidd-orchestrator/skills/00-async-dev/references/routing.md @@ -1,6 +1,6 @@ # Routing — decision tree -Full contract for picking a sub-flow inside `aidd-orchestrator:00:async-dev`. The router walks these signals in order; the first match wins. +Full contract for picking a sub-flow inside `aidd-orchestrator:00-async-dev`. The router walks these signals in order; the first match wins. --- @@ -11,8 +11,8 @@ If `$ARGUMENTS` contains exactly `setup`, `run`, or `review` as a standalone cas This is the contract the bundled CI workflow relies on: ```yaml -prompt: "Use skill aidd-orchestrator:00:async-dev with action=run on issue #..." -prompt: "Use skill aidd-orchestrator:00:async-dev with action=review on PR #..." +prompt: "Use skill aidd-orchestrator:00-async-dev with action=run on issue #..." +prompt: "Use skill aidd-orchestrator:00-async-dev with action=review on PR #..." ``` The router parses `action=` from the prompt body. Plain `setup` / `run` / `review` words elsewhere in the body do NOT match — only the explicit `action=` form, or `$ARGUMENTS` set to exactly one of the three keywords. @@ -33,8 +33,8 @@ When invoked from a GitHub workflow, the router has access to the event context: Comment regex (case-insensitive): -- `run`: `@claude\s+/(implement|aidd-dev:02:implement|run)` -- `review`: `@claude\s+/(review|aidd-dev:05:review)` +- `run`: `@claude\s+/(implement|aidd-dev:02-implement|run)` +- `review`: `@claude\s+/(review|aidd-dev:05-review)` --- @@ -85,7 +85,7 @@ The router NEVER silently switches sub-flow when the request and the state disag Examples: - **User says "run" but config is absent.** - Surface the conflict and stop: `Setup must complete before run. Run /aidd-orchestrator:00:async-dev with action=setup first.` + Surface the conflict and stop: `Setup must complete before run. Run /aidd-orchestrator:00-async-dev with action=setup first.` - **Workflow webhook fires `to-implement` but the issue already has an open closing PR.** Route to `review` (the PR is the active surface). Comment on the issue: `Issue #N has open PR #M — routed to review instead of run. Apply the `to-review` label to PR #M to trigger review explicitly.` - **Label `to-implement` AND label `to-review` both present.** diff --git a/plugins/aidd-orchestrator/skills/00-async-dev/references/setup/local-mode-scheduling.md b/plugins/aidd-orchestrator/skills/00-async-dev/references/setup/local-mode-scheduling.md index 41a13e846..80b13652f 100644 --- a/plugins/aidd-orchestrator/skills/00-async-dev/references/setup/local-mode-scheduling.md +++ b/plugins/aidd-orchestrator/skills/00-async-dev/references/setup/local-mode-scheduling.md @@ -103,7 +103,7 @@ Convenient when you want the routine to keep running even with the laptop off. * 1. In any Claude Code session, run `/schedule`. 2. Cron: `0 * * * *` (every hour) or coarser. -3. Prompt: `Use skill aidd-orchestrator:00:async-dev with action=run on the next ready issue in {owner}/{repo}.` +3. Prompt: `Use skill aidd-orchestrator:00-async-dev with action=run on the next ready issue in {owner}/{repo}.` ## Sanity check before scheduling anything diff --git a/plugins/aidd-pm/README.md b/plugins/aidd-pm/README.md index d6f0931b3..acd140270 100644 --- a/plugins/aidd-pm/README.md +++ b/plugins/aidd-pm/README.md @@ -6,7 +6,7 @@ Product management plugin for the AI-Driven Development framework. > Status: stable. -First time? Install with `/plugin install aidd-pm@aidd-framework`, then run `aidd-pm:01:ticket-info`. +First time? Install with `/plugin install aidd-pm@aidd-framework`, then run `aidd-pm:01-ticket-info`. Covers ticket information retrieval, user story creation, product requirement documents, and spec generation for downstream agents. diff --git a/plugins/aidd-pm/skills/01-ticket-info/README.md b/plugins/aidd-pm/skills/01-ticket-info/README.md index 389bbb9b3..fece34b3b 100644 --- a/plugins/aidd-pm/skills/01-ticket-info/README.md +++ b/plugins/aidd-pm/skills/01-ticket-info/README.md @@ -23,13 +23,13 @@ the project memory. ## How to invoke ``` -Use skill aidd-pm:01:ticket-info on +Use skill aidd-pm:01-ticket-info on ``` Or, with no id, let the skill auto-detect from the current git branch: ``` -Use skill aidd-pm:01:ticket-info +Use skill aidd-pm:01-ticket-info ``` ## Outputs diff --git a/plugins/aidd-pm/skills/01-ticket-info/SKILL.md b/plugins/aidd-pm/skills/01-ticket-info/SKILL.md index e3055f51f..9ef4743c4 100644 --- a/plugins/aidd-pm/skills/01-ticket-info/SKILL.md +++ b/plugins/aidd-pm/skills/01-ticket-info/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-pm:01:ticket-info +name: 01-ticket-info description: Retrieve and display ticket information from the configured ticketing tool. Use when the user says "ticket info", "show ticket", "get ticket", "ticket details", "what's ", or invokes `/ticket-info`. Do NOT use for creating issues, commenting on tickets, changing status, or reassigning. --- diff --git a/plugins/aidd-pm/skills/02-user-stories-create/README.md b/plugins/aidd-pm/skills/02-user-stories-create/README.md index cabd880ab..c0038ec5b 100644 --- a/plugins/aidd-pm/skills/02-user-stories-create/README.md +++ b/plugins/aidd-pm/skills/02-user-stories-create/README.md @@ -23,7 +23,7 @@ ticketing tool once you validate the draft. ## How to invoke ``` -Use skill aidd-pm:02:user-stories-create for +Use skill aidd-pm:02-user-stories-create for ``` The skill clarifies in at most 3 questions per round, drafts the stories, diff --git a/plugins/aidd-pm/skills/02-user-stories-create/SKILL.md b/plugins/aidd-pm/skills/02-user-stories-create/SKILL.md index 4a5288456..1286159a1 100644 --- a/plugins/aidd-pm/skills/02-user-stories-create/SKILL.md +++ b/plugins/aidd-pm/skills/02-user-stories-create/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-pm:02:user-stories-create +name: 02-user-stories-create description: Generate INVEST-compliant user stories from a feature description. Use when the user says "user stories", "create user stories", "write user stories for X", "INVEST stories", "draft stories", or invokes `/user-stories-create`. Do NOT use for writing code, drafting a full PRD, refining a single existing story, or copying ready text into a tracker. --- diff --git a/plugins/aidd-pm/skills/03-prd/README.md b/plugins/aidd-pm/skills/03-prd/README.md index 5cb430a86..bb4576a3b 100644 --- a/plugins/aidd-pm/skills/03-prd/README.md +++ b/plugins/aidd-pm/skills/03-prd/README.md @@ -24,7 +24,7 @@ Stays at the "what and why" level; never crosses into implementation detail. ## How to invoke ``` -Use skill aidd-pm:03:prd for +Use skill aidd-pm:03-prd for ``` The skill parses the input, drafts each section per template, shows the diff --git a/plugins/aidd-pm/skills/03-prd/SKILL.md b/plugins/aidd-pm/skills/03-prd/SKILL.md index 24746e102..d2e4b1930 100644 --- a/plugins/aidd-pm/skills/03-prd/SKILL.md +++ b/plugins/aidd-pm/skills/03-prd/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-pm:03:prd +name: 03-prd description: Generate a structured Product Requirements Document from a feature description or user stories, validated with the user before save. Use when the user says "prd", "draft prd", "write prd", "product requirements for X", "generate a prd", or invokes `/prd`. Do NOT use for writing user stories, drafting a technical implementation plan, or writing source code. --- diff --git a/plugins/aidd-pm/skills/04-spec/README.md b/plugins/aidd-pm/skills/04-spec/README.md index bbefac834..80d2829d6 100644 --- a/plugins/aidd-pm/skills/04-spec/README.md +++ b/plugins/aidd-pm/skills/04-spec/README.md @@ -26,13 +26,13 @@ locked once validated. Build a fresh spec from a request or an existing PRD: ``` -Use skill aidd-pm:04:spec build for +Use skill aidd-pm:04-spec build for ``` Refine an existing spec from reviewer findings: ``` -Use skill aidd-pm:04:spec refine on with +Use skill aidd-pm:04-spec refine on with ``` The router picks the action from the inputs: presence of `existing_spec` diff --git a/plugins/aidd-pm/skills/04-spec/SKILL.md b/plugins/aidd-pm/skills/04-spec/SKILL.md index 890c5184a..b72ce1252 100644 --- a/plugins/aidd-pm/skills/04-spec/SKILL.md +++ b/plugins/aidd-pm/skills/04-spec/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-pm:04:spec +name: 04-spec description: Generate or refine a project spec from a free-form human request, an existing PRD, or reviewer findings. Use when the user says "draft spec", "spec for X", "refine the spec", "generate spec from prd", "/spec", or when an orchestrator needs a normalized contract before planning. Do NOT use for writing source code, drafting a full PRD, or modifying a validated and locked spec. --- diff --git a/plugins/aidd-refine/CATALOG.md b/plugins/aidd-refine/CATALOG.md index 6b27e6eee..393d8a8a1 100644 --- a/plugins/aidd-refine/CATALOG.md +++ b/plugins/aidd-refine/CATALOG.md @@ -82,7 +82,7 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai | `references` | [locked-sets.json](skills/04-shadow-areas/references/locked-sets.json) | - | | `references` | [probe-style.md](skills/04-shadow-areas/references/probe-style.md) | - | | `references` | [severity-rubric.md](skills/04-shadow-areas/references/severity-rubric.md) | - | -| `-` | [SKILL.md](skills/04-shadow-areas/SKILL.md) | `Analytical scan of a markdown artifact (idea, user-stories, PRD, spec) to surface blind spots - unstated assumption, missing actor, missing failure mode, ambiguous term, missing acceptance criterion, missing edge case, and missing dependency - emitting a structured shadow report grouped by category and sorted by severity. Use when the user says "find blind spots in this spec", "what's missing in this PRD", "shadow report", "shadow analysis", "scan for gaps", "find what's missing", "spot blind spots", "review for gaps", or asks for an analytical gap scan of a written artifact. Do NOT use for interactive clarification through iterative Q&A (use aidd-refine:01:brainstorm for that), implementing features, writing tests, or reviewing code style.` | +| `-` | [SKILL.md](skills/04-shadow-areas/SKILL.md) | `Analytical scan of a markdown artifact (idea, user-stories, PRD, spec) to surface blind spots - unstated assumption, missing actor, missing failure mode, ambiguous term, missing acceptance criterion, missing edge case, and missing dependency - emitting a structured shadow report grouped by category and sorted by severity. Use when the user says "find blind spots in this spec", "what's missing in this PRD", "shadow report", "shadow analysis", "scan for gaps", "find what's missing", "spot blind spots", "review for gaps", or asks for an analytical gap scan of a written artifact. Do NOT use for interactive clarification through iterative Q&A (use aidd-refine:01-brainstorm for that), implementing features, writing tests, or reviewing code style.` | #### `skills/05-fact-check` @@ -96,5 +96,5 @@ Auto-generated index of skills, agents, references and assets shipped by the `ai | `-` | [README.md](skills/05-fact-check/README.md) | - | | `references` | [claim-categories.md](skills/05-fact-check/references/claim-categories.md) | - | | `references` | [verification-cascade.md](skills/05-fact-check/references/verification-cascade.md) | - | -| `-` | [SKILL.md](skills/05-fact-check/SKILL.md) | `Verify factual claims in a piece of text against authoritative sources and rewrite it with footnote citations, hedging any claim that cannot be confirmed. Runs a cheapest-first verification cascade (project memory and docs, then codebase inspection, then web lookup) and reports both sources when they disagree. Use when the user says "fact-check this", "verify that claim", "are you sure about that", "is that actually true", "cite your sources", "where did you get that fact", "did you make that up", "double-check the version you gave me", "vérifie cette information", or "es-tu sûr de ça". Do NOT use to auto-guard the AI's own output (this skill only fires on an explicit request), to judge code logic correctness, or to clarify vague requirements through iterative Q&A - use `aidd-refine:01:brainstorm` for that.` | +| `-` | [SKILL.md](skills/05-fact-check/SKILL.md) | `Verify factual claims in a piece of text against authoritative sources and rewrite it with footnote citations, hedging any claim that cannot be confirmed. Runs a cheapest-first verification cascade (project memory and docs, then codebase inspection, then web lookup) and reports both sources when they disagree. Use when the user says "fact-check this", "verify that claim", "are you sure about that", "is that actually true", "cite your sources", "where did you get that fact", "did you make that up", "double-check the version you gave me", "vérifie cette information", or "es-tu sûr de ça". Do NOT use to auto-guard the AI's own output (this skill only fires on an explicit request), to judge code logic correctness, or to clarify vague requirements through iterative Q&A - use `aidd-refine:01-brainstorm` for that.` | diff --git a/plugins/aidd-refine/README.md b/plugins/aidd-refine/README.md index e317cddf5..09acb2ee8 100644 --- a/plugins/aidd-refine/README.md +++ b/plugins/aidd-refine/README.md @@ -6,7 +6,7 @@ Meta-cognition plugin for the AI-Driven Development framework. > Status: stable. -First time? Install with `/plugin install aidd-refine@aidd-framework`, then run `aidd-refine:01:brainstorm`. +First time? Install with `/plugin install aidd-refine@aidd-framework`, then run `aidd-refine:01-brainstorm`. Five skills that refine inputs and outputs through reflection: clarify vague requests, challenge prior work for correctness, toggle a condensed output mode, analytically scan artifacts for blind spots, and verify factual claims against authoritative sources. diff --git a/plugins/aidd-refine/hooks/condense-stats.js b/plugins/aidd-refine/hooks/condense-stats.js index f9051acf1..88e827611 100644 --- a/plugins/aidd-refine/hooks/condense-stats.js +++ b/plugins/aidd-refine/hooks/condense-stats.js @@ -2,7 +2,7 @@ /** * condense-stats.js * - * UserPromptSubmit hook for aidd-refine:03:condense :: action 02-stats. + * UserPromptSubmit hook for aidd-refine:03-condense :: action 02-stats. * * Triggers on user prompts that ask for condense stats. Reads the current * Claude Code session transcript, detects intensity transitions emitted by diff --git a/plugins/aidd-refine/skills/01-brainstorm/README.md b/plugins/aidd-refine/skills/01-brainstorm/README.md index 948b9ef59..530fa17a1 100644 --- a/plugins/aidd-refine/skills/01-brainstorm/README.md +++ b/plugins/aidd-refine/skills/01-brainstorm/README.md @@ -23,7 +23,7 @@ explicitly approves the result. ## How to invoke ``` -Use skill aidd-refine:01:brainstorm +Use skill aidd-refine:01-brainstorm ``` The skill walks 5 atomic actions: diff --git a/plugins/aidd-refine/skills/01-brainstorm/SKILL.md b/plugins/aidd-refine/skills/01-brainstorm/SKILL.md index 919cbf89c..994506a3f 100644 --- a/plugins/aidd-refine/skills/01-brainstorm/SKILL.md +++ b/plugins/aidd-refine/skills/01-brainstorm/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-refine:01:brainstorm +name: 01-brainstorm description: Interactive brainstorming session to clarify and refine requests through iterative questioning. Use when user mentions unclear requirements, vague ideas, or needs clarification on features. Do NOT use for clear technical specs, implementation details, or when requirements are already well-defined. --- diff --git a/plugins/aidd-refine/skills/02-challenge/README.md b/plugins/aidd-refine/skills/02-challenge/README.md index 9b317f8d7..c415880bb 100644 --- a/plugins/aidd-refine/skills/02-challenge/README.md +++ b/plugins/aidd-refine/skills/02-challenge/README.md @@ -24,7 +24,7 @@ to ship, iterate, or rework. ## How to invoke ``` -Use skill aidd-refine:02:challenge +Use skill aidd-refine:02-challenge ``` The skill is single-action - the router dispatches to `challenge` whenever diff --git a/plugins/aidd-refine/skills/02-challenge/SKILL.md b/plugins/aidd-refine/skills/02-challenge/SKILL.md index 359fce1e3..0a51675a8 100644 --- a/plugins/aidd-refine/skills/02-challenge/SKILL.md +++ b/plugins/aidd-refine/skills/02-challenge/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-refine:02:challenge +name: 02-challenge description: Rethink prior work to verify correctness against an agreed plan, classifying findings as deal-breakers, suggestions, or correct, with a confidence score. Use when the user says "challenge this", "rethink your plan", "is this correct", "review my last decision", "challenge my decision", "challenge what you did", "is my decision right", "criticize this", "find flaws", or asks for a critical review of just-completed work. Do NOT use for line-by-line code review against a style guide, implementing features, writing tests, or generating new code. --- diff --git a/plugins/aidd-refine/skills/03-condense/README.md b/plugins/aidd-refine/skills/03-condense/README.md index aff7f72e8..af75df338 100644 --- a/plugins/aidd-refine/skills/03-condense/README.md +++ b/plugins/aidd-refine/skills/03-condense/README.md @@ -28,7 +28,7 @@ token usage and estimated savings for the current session. ## How to invoke ``` -Use skill aidd-refine:03:condense +Use skill aidd-refine:03-condense ``` The router dispatches by intent: diff --git a/plugins/aidd-refine/skills/03-condense/SKILL.md b/plugins/aidd-refine/skills/03-condense/SKILL.md index 1d220ee27..675335450 100644 --- a/plugins/aidd-refine/skills/03-condense/SKILL.md +++ b/plugins/aidd-refine/skills/03-condense/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-refine:03:condense +name: 03-condense description: Toggle terse output mode with intensity levels (lite, full, ultra) so prose drops articles, filler, and pleasantries while code, quoted errors, and security warnings stay verbatim. Also reports real token usage and estimated savings under condense mode for the current session. Use when the user says "condense", "condense output", "be more concise", "shorter answers", "tighten output", "/condense", "/condense full", "/condense ultra", "stop condense", "normal mode", "/condense-stats", "how much have we saved", or "token savings". Do NOT use for editing existing prose, summarizing a long document, or compressing source code (only output style is affected, not content). --- diff --git a/plugins/aidd-refine/skills/04-shadow-areas/README.md b/plugins/aidd-refine/skills/04-shadow-areas/README.md index 43606611e..efb26a5d0 100644 --- a/plugins/aidd-refine/skills/04-shadow-areas/README.md +++ b/plugins/aidd-refine/skills/04-shadow-areas/README.md @@ -21,20 +21,20 @@ direct-question probe the author can act on, and written to a structured ## When NOT to use - The artifact does not yet exist and the user needs to clarify a vague intent - through iterative questioning - use the `aidd-refine:01:brainstorm` skill. + through iterative questioning - use the `aidd-refine:01-brainstorm` skill. - The request is to review code style or check implementation correctness. - The user needs a general chat about what to do next, not a gap analysis. ## How to invoke ``` -Use skill aidd-refine:04:shadow-areas +Use skill aidd-refine:04-shadow-areas ``` Provide either a file path or inline text as the source: ``` -Use skill aidd-refine:04:shadow-areas with +Use skill aidd-refine:04-shadow-areas with ``` The router dispatches based on whether a prior report is already present: diff --git a/plugins/aidd-refine/skills/04-shadow-areas/SKILL.md b/plugins/aidd-refine/skills/04-shadow-areas/SKILL.md index 5b85ee93c..3df59f34c 100644 --- a/plugins/aidd-refine/skills/04-shadow-areas/SKILL.md +++ b/plugins/aidd-refine/skills/04-shadow-areas/SKILL.md @@ -1,6 +1,6 @@ --- -name: aidd-refine:04:shadow-areas -description: Analytical scan of a markdown artifact (idea, user-stories, PRD, spec) to surface blind spots - unstated assumption, missing actor, missing failure mode, ambiguous term, missing acceptance criterion, missing edge case, and missing dependency - emitting a structured shadow report grouped by category and sorted by severity. Use when the user says "find blind spots in this spec", "what's missing in this PRD", "shadow report", "shadow analysis", "scan for gaps", "find what's missing", "spot blind spots", "review for gaps", or asks for an analytical gap scan of a written artifact. Do NOT use for interactive clarification through iterative Q&A (use aidd-refine:01:brainstorm for that), implementing features, writing tests, or reviewing code style. +name: 04-shadow-areas +description: Analytical scan of a markdown artifact (idea, user-stories, PRD, spec) to surface blind spots - unstated assumption, missing actor, missing failure mode, ambiguous term, missing acceptance criterion, missing edge case, and missing dependency - emitting a structured shadow report grouped by category and sorted by severity. Use when the user says "find blind spots in this spec", "what's missing in this PRD", "shadow report", "shadow analysis", "scan for gaps", "find what's missing", "spot blind spots", "review for gaps", or asks for an analytical gap scan of a written artifact. Do NOT use for interactive clarification through iterative Q&A (use aidd-refine:01-brainstorm for that), implementing features, writing tests, or reviewing code style. --- # Shadow Areas diff --git a/plugins/aidd-refine/skills/05-fact-check/README.md b/plugins/aidd-refine/skills/05-fact-check/README.md index 485137876..170d6a030 100644 --- a/plugins/aidd-refine/skills/05-fact-check/README.md +++ b/plugins/aidd-refine/skills/05-fact-check/README.md @@ -23,19 +23,19 @@ they disagree. request. A permanent "always verify" guard belongs in an always-loaded rule. - To judge code logic correctness or review code style. - To clarify vague requirements through iterative Q&A - use the - `aidd-refine:01:brainstorm` skill. + `aidd-refine:01-brainstorm` skill. ## How to invoke ``` -Use skill aidd-refine:05:fact-check +Use skill aidd-refine:05-fact-check ``` Provide the text to check - the prior answer, a quoted passage, or a pasted block: ``` -Use skill aidd-refine:05:fact-check on +Use skill aidd-refine:05-fact-check on ``` The skill runs a fixed three-step pipeline: diff --git a/plugins/aidd-refine/skills/05-fact-check/SKILL.md b/plugins/aidd-refine/skills/05-fact-check/SKILL.md index a832b212c..af670ba61 100644 --- a/plugins/aidd-refine/skills/05-fact-check/SKILL.md +++ b/plugins/aidd-refine/skills/05-fact-check/SKILL.md @@ -1,6 +1,6 @@ --- -name: aidd-refine:05:fact-check -description: Verify factual claims in a piece of text against authoritative sources and rewrite it with footnote citations, hedging any claim that cannot be confirmed. Runs a cheapest-first verification cascade (project memory and docs, then codebase inspection, then web lookup) and reports both sources when they disagree. Use when the user says "fact-check this", "verify that claim", "are you sure about that", "is that actually true", "cite your sources", "where did you get that fact", "did you make that up", "double-check the version you gave me", "vérifie cette information", or "es-tu sûr de ça". Do NOT use to auto-guard the AI's own output (this skill only fires on an explicit request), to judge code logic correctness, or to clarify vague requirements through iterative Q&A - use `aidd-refine:01:brainstorm` for that. +name: 05-fact-check +description: Verify factual claims in a piece of text against authoritative sources and rewrite it with footnote citations, hedging any claim that cannot be confirmed. Runs a cheapest-first verification cascade (project memory and docs, then codebase inspection, then web lookup) and reports both sources when they disagree. Use when the user says "fact-check this", "verify that claim", "are you sure about that", "is that actually true", "cite your sources", "where did you get that fact", "did you make that up", "double-check the version you gave me", "vérifie cette information", or "es-tu sûr de ça". Do NOT use to auto-guard the AI's own output (this skill only fires on an explicit request), to judge code logic correctness, or to clarify vague requirements through iterative Q&A - use `aidd-refine:01-brainstorm` for that. --- # Fact-check diff --git a/plugins/aidd-vcs/README.md b/plugins/aidd-vcs/README.md index dd91a5b3b..7f24ea67f 100644 --- a/plugins/aidd-vcs/README.md +++ b/plugins/aidd-vcs/README.md @@ -6,7 +6,7 @@ VCS workflow plugin for the AI-Driven Development framework. > Status: stable. -First time? Install with `/plugin install aidd-vcs@aidd-framework`, then run `aidd-vcs:01:commit`. +First time? Install with `/plugin install aidd-vcs@aidd-framework`, then run `aidd-vcs:01-commit`. Typical flow: `01:commit` after each unit of work; `02:pull-request` when the branch is ready; `03:release-tag` at release time; `04:issue-create` from anywhere. diff --git a/plugins/aidd-vcs/skills/01-commit/README.md b/plugins/aidd-vcs/skills/01-commit/README.md index 318c2ca28..0cba0c3f7 100644 --- a/plugins/aidd-vcs/skills/01-commit/README.md +++ b/plugins/aidd-vcs/skills/01-commit/README.md @@ -23,7 +23,7 @@ optionally pushing the branch when the caller asks for it. ## How to invoke ``` -Use skill aidd-vcs:01:commit +Use skill aidd-vcs:01-commit ``` Or via the slash command: diff --git a/plugins/aidd-vcs/skills/01-commit/SKILL.md b/plugins/aidd-vcs/skills/01-commit/SKILL.md index ff307cf27..e25cb7900 100644 --- a/plugins/aidd-vcs/skills/01-commit/SKILL.md +++ b/plugins/aidd-vcs/skills/01-commit/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-vcs:01:commit +name: 01-commit description: Create an atomic git commit with conventional message format. Use when the user says "commit", "git commit", "create a commit", "commit my changes", "commit and push", or invokes `/commit`. Do NOT use for amending existing commits, force-pushing, rebasing, opening pull requests, or release tagging. --- diff --git a/plugins/aidd-vcs/skills/02-pull-request/README.md b/plugins/aidd-vcs/skills/02-pull-request/README.md index 0ab59bc49..82dbe60f4 100644 --- a/plugins/aidd-vcs/skills/02-pull-request/README.md +++ b/plugins/aidd-vcs/skills/02-pull-request/README.md @@ -24,7 +24,7 @@ as a draft for manual promotion. ## How to invoke ``` -Use skill aidd-vcs:02:pull-request +Use skill aidd-vcs:02-pull-request ``` Or via the slash command: `/pull-request`. diff --git a/plugins/aidd-vcs/skills/02-pull-request/SKILL.md b/plugins/aidd-vcs/skills/02-pull-request/SKILL.md index 2c726498a..638e29cbb 100644 --- a/plugins/aidd-vcs/skills/02-pull-request/SKILL.md +++ b/plugins/aidd-vcs/skills/02-pull-request/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-vcs:02:pull-request +name: 02-pull-request description: Create a draft pull or merge request from the current branch. Use when the user says "open a pr", "open a pull request", "create a pr", "create a merge request", "open mr", "draft a pr for this branch", or invokes `/pull-request`. Do NOT use for committing changes, pushing a branch directly, tagging releases, merging an existing request, or amending commits. --- diff --git a/plugins/aidd-vcs/skills/03-release-tag/README.md b/plugins/aidd-vcs/skills/03-release-tag/README.md index c4417b712..7041cc936 100644 --- a/plugins/aidd-vcs/skills/03-release-tag/README.md +++ b/plugins/aidd-vcs/skills/03-release-tag/README.md @@ -24,7 +24,7 @@ annotated git tag, and pushes it. ## How to invoke ``` -Use skill aidd-vcs:03:release-tag +Use skill aidd-vcs:03-release-tag ``` Or via the slash command: `/release-tag`. diff --git a/plugins/aidd-vcs/skills/03-release-tag/SKILL.md b/plugins/aidd-vcs/skills/03-release-tag/SKILL.md index ca1cd9789..884151f7c 100644 --- a/plugins/aidd-vcs/skills/03-release-tag/SKILL.md +++ b/plugins/aidd-vcs/skills/03-release-tag/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-vcs:03:release-tag +name: 03-release-tag description: Cut a semver release with annotated tag and release notes. Use when the user says "release", "tag", "tag this release", "bump version", "release v1.2.0", "cut a release", or invokes `/release-tag`. Do NOT use for plain commits without a tag, opening pull requests, pushing a branch only, or amending existing tags. --- diff --git a/plugins/aidd-vcs/skills/04-issue-create/README.md b/plugins/aidd-vcs/skills/04-issue-create/README.md index 4bf22a154..1aee05e6a 100644 --- a/plugins/aidd-vcs/skills/04-issue-create/README.md +++ b/plugins/aidd-vcs/skills/04-issue-create/README.md @@ -23,7 +23,7 @@ enough context to be actionable, validated with the user before creation. ## How to invoke ``` -Use skill aidd-vcs:04:issue-create +Use skill aidd-vcs:04-issue-create ``` Or via the slash command: `/issue-create`. diff --git a/plugins/aidd-vcs/skills/04-issue-create/SKILL.md b/plugins/aidd-vcs/skills/04-issue-create/SKILL.md index 2e8c347ea..0f28c5667 100644 --- a/plugins/aidd-vcs/skills/04-issue-create/SKILL.md +++ b/plugins/aidd-vcs/skills/04-issue-create/SKILL.md @@ -1,5 +1,5 @@ --- -name: aidd-vcs:04:issue-create +name: 04-issue-create description: Create an issue in the configured ticketing tool. Use when the user says "new issue", "create an issue", "file a bug", "file an issue", "report bug", "open an issue", or invokes `/issue-create`. Do NOT use for committing changes, opening pull requests, tagging releases, or commenting on existing issues. ---