review-merge-readiness
Skill337 starsChanged 10 months agoMITView on GitHub
Request/execute structured code review: use after completing important tasks, at end of each execution batch, or before merge. Based on git diff range, compare against plan and requirements, output issue list by Critical/Important/Minor severity, and provide clear verdict on merge readiness. Trigger words: request code review, PR review, merge readiness, production readiness.
In this repository40 other files it gives its agents.
- review-clean-codeSkill
- review-doc-consistencySkill
- review-merge-readinessSkill
- workflow-execute-plansSkill
- workflow-template-extractorSkill
- workflow-template-seederSkill
- cloudflareSkill
- deep-researchSkill
- mcp-cloudflareSkill
- mcp-stripeSkill
- mcp-supabaseSkill
- publish-x-articleSkill
- review-clean-codeSkill
- review-doc-consistencySkill
- review-qualitySkill
- review-react-best-practicesSkill
- review-seo-auditSkill
- skill-creatorSkill
- skill-evolutionSkill
- skill-improverSkill
- stripeSkill
- supabaseSkill
- tool-ast-grep-rulesSkill
- tool-better-authSkill
- tool-design-style-selectorSkill
- tool-hooks-doctorSkill
- tool-openclawSkill
- tool-programmatic-seoSkill
- tool-schema-markupSkill
- tool-systematic-debuggingSkill
- tool-ui-ux-pro-maxSkill
- tool-x-article-publisherSkill
- workflow-brainstormSkill
- workflow-creatorSkill
- workflow-execute-plansSkill
- workflow-feature-shipperSkill
- workflow-project-intakeSkill
- workflow-ship-fasterSkill
- workflow-template-extractorSkill
- workflow-template-seederSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 7 are distinctive, and 5 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
5
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 15
After completing important features
- Very specific: line 16
After each batch in workflow-execute-plans ends (default 3 tasks per batch)
- Distinctive: line 17
Before merging to main branch
- Distinctive: line 20
When stuck (get a fresh perspective)
- Distinctive: line 21
Before major refactoring (establish baseline first)
- Distinctive: line 22
After fixing complex bugs (verify no new regressions)
- Very specific: line 28
Prefer using "baseline before plan/task started" as BASE_SHA:
- Distinctive: line 36
If you want to review just the most recent commit within a small task:
- Very specific: line 60
Use template: review-merge-readiness/code-reviewer.md, fill in placeholders and execute.
- Distinctive: line 64
Check each item per template checklist and output same structured result (Strengths + Issues by severity + Verdict).
- Very specific: line 88
If you just need a "can we merge?" verdict: use this skill.
- Very specific: line 89
If you want a deep health check: additionally invoke review-clean-code.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Requesting Code Review (Structured Review: Requirements Alignment + Production Readiness)
Goal: Make code review a repeatable process, not random comments.
Core principle: Review early, review often.
When Review is Required
Mandatory:
- After completing important features
- After each batch in
workflow-execute-plansends (default 3 tasks per batch) - Before merging to main branch
Optional but valuable:
- When stuck (get a fresh perspective)
- Before major refactoring (establish baseline first)
- After fixing complex bugs (verify no new regressions)
How to Initiate (Minimum Information Set)
1) Determine Review Scope (git SHA)
Prefer using "baseline before plan/task started" as BASE_SHA:
# Common approach: use main as baseline
BASE_SHA=$(git merge-base HEAD main 2>/dev/null || git merge-base HEAD master)
HEAD_SHA=$(git rev-parse HEAD)If you want to review just the most recent commit within a small task:
BASE_SHA=$(git rev-parse HEAD~1)
HEAD_SHA=$(git rev-parse HEAD)2) Prepare Review Basis (Plan / Requirements)
Review must provide:
- WHAT_WAS_IMPLEMENTED: What you just completed (1-3 bullet points)
- PLAN_OR_REQUIREMENTS: Corresponding plan excerpt or requirements document path (e.g.,
run_dir/03-plans/feature-plan.md)
3) Get diff (Evidence)
git diff --stat "$BASE_SHA..$HEAD_SHA"
git diff "$BASE_SHA..$HEAD_SHA"Review Execution Methods (Choose One)
Method A: Sub-Agent Review (if your system supports it)
Use template: review-merge-readiness/code-reviewer.md, fill in placeholders and execute.
Method B: Self Review (works without sub-agent)
Check each item per template checklist and output same structured result (Strengths + Issues by severity + Verdict).
Review Output Format (Must Be Structured)
Output must include:
- Strengths: Specific positives (at least 1)
- Issues: Categorized by severity:
- Critical (Must Fix): Security/data loss/functionality bugs/would cause production incidents
- Important (Should Fix): Obviously poor architecture/missing error handling/test gaps/requirements misalignment
- Minor (Nice to Have): Style/small optimizations/documentation polish
- Assessment: Merge readiness (Yes/No/With fixes) + 1-2 sentence technical reasoning
Each Issue must include:
- Location:
file:line - What's wrong
- Why it matters
- How to fix (provide minimal change suggestion)
Relationship with Other Review Skills
review-clean-code: More focused on "maintainability/cleanliness", suitable for deep code smell investigationreview-react-best-practices: More focused on React/Next.js performance patterns (waterfalls/bundle/re-renders). Use when the diff touches React UI, data fetching, or performance-sensitive areas.- This skill: More focused on "requirements alignment/production readiness/merge verdict" conclusion-oriented review
If you just need a "can we merge?" verdict: use this skill.
If you want a deep health check: additionally invoke review-clean-code.
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.

