review-report
Skill1 starsChanged 9 days agoMITView on GitHub
Use when asked to review or critique finished implementation work ("review this", "code review", "look at the PR"), or when a completed stage needs checking against its design doc.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- Hiveteq/review-reporttheir own version, first seen Nov 1, 2026
- halkn/skillstheir own version, first seen Oct 25, 2026
- chrysogonus/power-agentstheir own version, first seen Oct 13, 2026
- taoluo/claude-skillstheir own version, first seen May 6, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- chrysogonus/power-agents★ 4same name
- taoluo/claude-skills★ 2same name
- halkn/skills★ 0same name
- Hiveteq/review-report★ 0same 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 repository13 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- brainstormingSkill
- commitSkill
- design-doc-templateSkill
- dev-kickoffSkill
- dev-resumeSkill
- doc-auditSkill
- reverse-engineeringSkill
- roadmap-planningSkill
- setupSkill
- teardownSkill
- verify-checklistSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
After reviewing implementation results, write the report following this guide.
- Distinctive: line 15
When an implementation stage (mak:coder or direct) is complete and results need review
- Distinctive: line 16
When checking that the implementation matches the design doc
- Distinctive: line 17
When a combined quality judgement including the project's verification results is needed
- Distinctive: line 58
If the verification results could not be confirmed directly, state "could not run directly — based on coder's report"
- Very specific: line 60
After a slice/stage completion review, hand off to mak:doc-audit to check whether other documents referencing this change still hold
- Distinctive: line 62
If there are no issues, close concisely with "✅ All checks passed".
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Review Report Guide
After reviewing implementation results, write the report following this guide.
Report template: ${CLAUDE_PLUGIN_ROOT}/skills/review-report/assets/review-report.template.md (in English; render the report in the user's language, keeping the structure).
When to Use
- When an implementation stage (mak:coder or direct) is complete and results need review
- When checking that the implementation matches the design doc
- When a combined quality judgement including the project's verification results is needed
Review Procedure
- Read the design doc — find the relevant design doc (per the
mak:design-doc-templatesave-path rule, default.claude/mak/plan/) and note its §Scope of Changes and §Verification Plan - Read convention docs — the project's convention documents (e.g.
docs/*.md, README) and the relevant sections ofCLAUDE.md - Compare the implementation — read the files in the design doc's scope and confirm they match the design intent
- Check verification results — prefer those reported via
mak:verify-checklist; if absent or doubtful, run the project's declared verification commands directly and attach results - Check coding principles — look for violations of the kit's coding principles (Simplicity / Precise Changes — the Warning checklist below). If the project defines its own Coding Rules, check those as well
- Write the report — classify issues by severity and output
Issue Classification
| Grade | Criteria | Action |
| 🔴 Critical | Build failure, type error, test failure, security vulnerability, implementation that contradicts the approved design's behavior or breaks a data contract | Must fix, then re-review |
| 🟡 Warning | Code-quality issues, naming inconsistency, unnecessary changes, incomplete features | Fix recommended; prioritize and decide |
| 🟢 Pass | Implemented as designed; verification passed | Nothing notable |
| 📝 Note | Potential issues found outside this review's scope; future improvement ideas | Do not fix; record as separate issues |
Warning Checklist
Classify the following as 🟡 Warning when found:
- Unrequested features / excessive abstraction / speculative flexibility or configuration (Simplicity)
- Error handling or validation for impossible scenarios (Simplicity)
- Unrequested "improvement" of adjacent code/comments/formatting (Precise Changes)
- Unrequested refactoring of working code (Precise Changes)
- Changed lines not directly connected to the user's request (Precise Changes)
- Uncleaned unused imports/variables/functions introduced by the change (Precise Changes)
Pre-existing unused code (outside this review's scope) goes to 📝 Note and is not fixed.
Report Format
${CLAUDE_PLUGIN_ROOT}/skills/review-report/assets/review-report.template.md is the single source of truth for the report format. Fill in each section of the template as-is. State at the top of the output: "This report follows the mak:review-report skill format."
Cautions
- The reviewer reports only and never modifies code directly
- Record findings outside this review's scope only under 📝 Note; do not unilaterally decide to expand scope. If Critical or Warning issues exist, report to the main thread that re-delegation to
mak:coderis needed — do not re-delegate directly - If the verification results could not be confirmed directly, state "could not run directly — based on coder's report"
- Distinguish "no issues" from "could not verify"
- After a slice/stage completion review, hand off to
mak:doc-auditto check whether other documents referencing this change still hold
If there are no issues, close concisely with "✅ All checks passed".
References
- Template:
${CLAUDE_PLUGIN_ROOT}/skills/review-report/assets/review-report.template.md
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.