Docs/claude code power user guide

AdvancedClaudeCode.md → ClaudeCodePowerUserGuide.md

@@ -1,4 +1,4 @@
-# Advanced Claude Code
+# Claude Code Power User Guide
 
 ## shortcuts
 
@@ -40,6 +40,8 @@ AskForUserQuestion is a built-in tool in Claude Code that prompts the user for i
 
 ## Useful Claude Code Skills
 
+Claude Code Skills are modular, file-based extensions — each one a folder with a `SKILL.md` (plus optional scripts/resources) that packages domain knowledge or a specific workflow. Claude loads a skill's full instructions only when it's relevant (matched by its description or invoked explicitly via `/skill-name`), keeping the rest of the context window free. They're how you give Claude reusable, specialized capabilities — like a particular review process, a design system, or a deployment routine — without bloating every conversation with instructions it doesn't need yet.
+
 Running the skill below will audit your skills, and it will find a bunch of potential issues or improvements in your prompts.
 
 ```bash
@@ -119,9 +121,10 @@ Running the skill below will audit your skills, and it will find a bunch of pote
 
 ### Plugin skills worth installing
 
-**skill-creator** (official marketplace). Creates skills from scratch, runs evals against them, benchmarks variance between runs and optimizes the description so the skill triggers when it should.
+**[skill-creator](https://skillsmp.com/creators/anthropics/skills/skills-skill-creator)** (official marketplace). A meta-skill that guides you through creating your own Claude Code Skill, with best practices for writing clear instructions, defining triggers and structuring files. It generates a boilerplate `SKILL.md` and folder structure from your input, runs evals against the skill, benchmarks variance between runs and optimizes the description so the skill triggers when it should.
 
 ```bash
+/plugin marketplace add anthropics/skills
 /skill-creator
 ```
 
@@ -141,3 +144,57 @@ claude plugin install mattpocock-skills@claude-plugins-official
 ```bash
 /plugin marketplace add anthropics/skills
 ```
+
+### Community skills
+
+**[Frontend Design Skill by Anthropic](https://skillsmp.com/creators/anthropics/skills/skills-frontend-design).** Guides Claude to commit to a distinctive design direction (purpose, tone, constraints, differentiation) before writing any UI code, and bans generic AI defaults like Inter, Roboto, and purple gradients — so output doesn't look templated.
+
+```text
+npx skills add https://github.com/anthropics/skills --skill frontend-design
+
+/frontend-design
+```
+
+**[Grill with Docs by Matt Pocock](https://github.com/mattpocock/skills/blob/main/skills/engineering/grill-with-docs/SKILL.md).** A Socratic, interview-style planning skill: it grills you on a proposed change one question at a time, checks your answers against the codebase and existing docs, and writes confirmed terminology and decisions back into `CONTEXT.md` and ADRs (Architecture Decision Records) as you go. Best used before starting a significant change.
+
+```text
+npx skills@latest add mattpocock/skills
+
+/grill-with-docs
+```
+
+**[Test Driven Development Workflow by Affaan-m](https://github.com/affaan-m/ECC/tree/main/skills/tdd-workflow).** Enforces a strict red-green-refactor TDD cycle (user journeys → write failing tests → minimal implementation → pass tests → refactor → verify 80%+ coverage → evidence report) for new features, bug fixes, and refactors, with Git checkpoints at each stage.
+
+```text
+npx skills add https://github.com/affaan-m/ECC --skill tdd-workflow
+
+/tdd-workflow
+```
+
+**[Code Reviewer Skill by Shubhamsaboo](https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/awesome_agent_skills/code-reviewer).** A prioritized code review skill that checks security (SQL injection, XSS, secrets) first, then performance, correctness, maintainability, and test coverage, surfacing findings by severity with concrete fix suggestions. Use it on PRs, pre-deployment code, or security audits.
+
+```text
+npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps --skill code-reviewer
+
+/code-reviewer
+```
+
+## next-steps plugin
+
+next-steps is a small productivity plugin by Thariq Shihipar (MIT, v1.0.0) that suggests what to type next after Claude finishes a turn. It isn't a skill or slash command but a [mod](README.md#mods): a function-hooks plugin (`hooks/register.tsx`).
+
+After each answer it shows up to three suggested prompts above the input box:
+
+```text
+next:
+  1: run the tests you just wrote
+  2: do the same for the settings page
+  3: /code-review high
+  0: dismiss
+```
+
+- Press `1`, `2` or `3` on an empty prompt to put that suggestion into the box as an editable draft; `0` dismisses them. The top suggestion also shows as ghost text, so `Tab` accepts it. Nothing is submitted until you press Enter.
+- Suggestions come from a fork of your session that shares its prompt cache, so it costs about one short reply and never blocks your turn. Your skills and slash commands are passed along, so a suggestion can be a command like `/code-review high`.
+- The output is treated as untrusted: escape sequences, control and invisible Unicode characters are stripped, and text containing Unicode tag characters is rejected, so a hidden prompt injection can't reach your prompt box.
+
+Config options: `minAnswerChars` (default `80`, no suggestions after shorter answers) and `suggestSkills` (default `true`, passes your skills and commands to the suggester).

README.md

@@ -55,6 +55,7 @@ A few core ideas explain most of how Claude Code behaves — each is covered in
     - [Installing an MCP server](#installing-an-mcp-server)
   - [Hooks](#hooks)
     - [Building a Hook](#building-a-hook)
+  - [Mods](#mods)
   - [Subagents](#subagents)
     - [Skills vs. Subagents](#skills-vs-subagents)
   - [Progressive Disclosure](#progressive-disclosure)
@@ -322,6 +323,20 @@ Key environment variables available in hook commands:
 
 ![Tools with Claude Code](images/claude_tools.png)
 
+## Mods
+
+Mods are a Claude Code feature launched October 1, 2026: small TypeScript functions that change how Claude Code works. You can write one yourself or ask Claude Code to write it for you.
+
+- **How they work:** Claude Code emits an event whenever it does something, and a mod hooks into those events. Unlike regular [hooks](#hooks), a mod's handlers are functions running inside Claude Code, so they can also replace or restyle what Claude Code draws itself (a tool call's row, the spinner, the question dialog). Anthropic's "Blast Radius" sample shows an explanation of a high-risk command like `rm -rf` in a side pane.
+- **Built-in mods:** some core features, such as `/diff`, are already mods. Anthropic plans to move more over time so you can shrink Claude Code to a small core and add back only what you want.
+- **Requirements:** Claude Code v2.1.287 or later (on by default), in the CLI and the Code tab of the Claude Desktop app. Behavior differs in the VS Code extension, `claude -p` and cloud sessions.
+- **Distribution:** mods ship inside [plugins](#marketplace-and-plugins), so existing plugin controls apply. Install with `/plugin install name@marketplace`; `/plugin` shows which mods a session loaded.
+- **Security:** mods have the same machine access as Claude Code, aren't sandboxed, and run inside the Claude Code process where classic endpoint security tools can't see them. Install only from trusted authors or marketplaces and check them first with `claude plugin validate`.
+
+```bash
+claude plugin validate
+```
+
 ## Subagents
 
 Subagents are agents spawned by the main agent to handle delegated or parallel subtasks. Each subagent starts fresh with its own isolated context and a limited set of tools, keeping it focused on one job.