You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
Repository navigation
docs(products): give every product card a product context block - #4923
Before an agent shapes product work it needs to know who the product serves, what outcome matters, which limits bind and what is out of scope. Most product cards never said so, so that context was missing or guessed.
What
Every product card now opens with a short product context block: who it serves and the outcome they want, its binding constraints, its non-goals, and where demand and usage evidence comes from. Each line is taken from the product's own documentation or this repository's contract, and says UNKNOWN where no source exists. The survey report line and the eval re-run from the issue are not part of this change.
Each card now opens with four lines: who the product serves and the outcome
that matters, its binding constraints, its non-goals, and where its demand and
usage evidence comes from. Every line is taken from the product's own README,
AGENTS.md or this repository's contract, or says UNKNOWN.
Part of #4841
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
🤖 Generated by the Agentic Engineer (interactive Claude Code session)
User trial at 20f2b5e195c1c60f79b3d412287f039a827c10af
I read every card as an agent picking up product work would, and checked the change mechanically on this branch:
All 17 cards under the product skills folder carry exactly one block, with one each of the Serves/Outcome, Constraints, Non-goals and Evidence lines, right below the card's title.
Each card grew by exactly 5 lines (four lines and a blank line) and lost none, inside the issue's limit.
21 of the 68 lines are UNKNOWN, mostly non-goals and evidence: no product README, AGENTS.md or contract states them, so none was invented. The named evidence sources are the ones the products already document: the plugin usage exports and skill evaluations (agent-plugins), aggregate Umami data (business-site) and Coroot (platform).
fleet-gitops is private, so its block uses only facts already public in this repository's contract.
The affected self-tests pass, apart from three that also fail on an unmodified main checkout here because they need submodules this clone does not populate. CI runs them with the submodules.
Not met here (why this says Part of #4841): the survey's report line for Feature and Epic issues without a success signal or out-of-scope line, and the re-run of the product-context eval scenarios in devantler-tech/agent-plugins#651.
Note: CodeRabbit is an incremental review system and does not re-review already reviewed commits. This command is applicable only when automatic reviews are paused.
No actionable comments were generated in the recent review.
Walkthrough
Seventeen product skill cards now document product-specific audiences, intended outcomes, constraints, non-goals, and evidence. Some cards identify evidence sources; others mark evidence or non-goals as UNKNOWN. The changes are documentation updates and do not alter public entities.
The change adds product context to the cards; no merge-blocking issue is evident.
Pre-merge checks: 4
Check name
Status
Explanation
Title check
The title clearly and concisely describes the main change: adding a product context block to every product card.
Description check
The description explains why and how the product context blocks were added, including their fields, evidence sources, UNKNOWN values, and scope exclusions.
Linked Issues check
Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check
Check skipped because no linked issues were found for this pull request.
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.
Included review availability: This review used your included allowance. Your plan provides up to 1 included review per hour; 0 remain after this review.
Recent review details
Additional context used
LanguageTool
.claude/skills/products/agent-plugins/SKILL.md
[grammar] ~9-~9: Ensure spelling is correct
Context: ...te paths; bundled skills keep their own licences - Non-goals: UNKNOWN - **Evidence:*...
(QB_NEW_EN_ORTHOGRAPHY_ERROR_IDS_1)
SkillSpector (2.12.0)
.claude/skills/products/platform/SKILL.md
[error] 31: [PE3] Credential Access: Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
Remediation: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
(Privilege Escalation (PE3))
.claude/skills/products/project-board/SKILL.md
[error] 3: [YR4] YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]: YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
Remediation: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
(YARA Match (YR4))
[warning] 34: [OH3] Unbounded Output: Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.
Remediation: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
Before an agent shapes product work it needs to know who the product serves, what outcome matters, which limits bind and what is out of scope. Most product cards never said so, so that context was missing or guessed.
What
Every product card now opens with a short product context block: who it serves and the outcome they want, its binding constraints, its non-goals, and where demand and usage evidence comes from. Each line is taken from the product's own documentation or this repository's contract, and says UNKNOWN where no source exists. The survey report line and the eval re-run from the issue are not part of this change.
Part of #4841
🤖 Generated with Claude Code