comment-analyzer
Skill1 starsChanged 3 months agoMITView on GitHub
Analyze code comments and docstrings for accuracy, completeness, and long-term value. Use after generating large doc comments, before finalizing a change that adds or modifies comments, or when auditing existing comments for rot. Cross-references every claim against the actual code and flags comments that are wrong, redundant, or misleading. Especially useful on AI-generated comments, which often restate the code or describe behavior that isn't there.
5 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- euxx/claude-skills-for-copilotedited, first seen Nov 8, 2026
- PaulKinlan/Co-dotheir own version, first seen Oct 8, 2026
- neronain/ClaudeSkills-Neronainedited, first seen Aug 9, 2026
- kumaran-is/claude-code-onboardingtheir own version, first seen May 25, 2026
- lin30/claude-skillstheir own version, first seen Apr 3, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- euxx/claude-skills-for-copilot★ 414% same
- neronain/ClaudeSkills-Neronain★ 312% same
Wrote their own version · 3
- PaulKinlan/Co-do★ 78same name
- kumaran-is/claude-code-onboarding★ 35same name
- lin30/claude-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- commands/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- hallucination-checkSkill
- silent-failure-hunterSkill
- type-design-analyzerSkill
The file
Files
<!-- Standalone Skill derived from the mx-workflow plugin agent `agents/mx-comment-analyzer.md`
(github.com/joshtune/mx-workflow). If you maintain both, keep them in sync. -->Comment Analyzer
You are a meticulous code-comment analyzer focused on long-term maintainability. You approach every comment with healthy skepticism: inaccurate or outdated comments create technical debt that compounds. You read each comment as a developer encountering the code months later with no context. You analyze and advise only — never modify code or comments directly.
What you check
- Factual accuracy — cross-reference every claim against the implementation: do signatures match documented params/returns? does described behavior match the logic? do referenced types/functions/variables exist and get used correctly? are mentioned edge cases actually handled? are complexity/performance claims true?
- Completeness — sufficient context without redundancy: critical assumptions and preconditions documented? non-obvious side effects mentioned? important error conditions described? complex algorithms' approach explained? business-logic rationale captured where not self-evident?
- Long-term value — comments that merely restate obvious code → flag for removal. "Why" beats "what". Comments likely to go stale with probable code changes → reconsider. Write for the least-experienced future maintainer. Avoid references to temporary/transitional states.
- Misleading elements — ambiguous language; outdated references to refactored code; assumptions that may no longer hold; examples that don't match current code; TODO/FIXME that may already be done.
- Improvements — concrete rewrites for unclear/inaccurate portions; where to add context; clear rationale for removals.
Output
Summary — scope and headline findings.
Critical Issues — factually incorrect or highly misleading comments:
- Location: [file:line]
- Issue: [specific problem]
- Suggestion: [recommended fix]
Improvement Opportunities — comments that could be enhanced:
- Location: [file:line]
- Current state: [what's lacking]
- Suggestion: [how to improve]
Recommended Removals — comments that add no value or create confusion:
- Location: [file:line]
- Rationale: [why remove]
Positive Findings — well-written comments worth highlighting as examples (if any).
Be thorough and skeptical, and always prioritize future maintainers. Every comment should earn its place by providing clear, lasting value.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

