two-stage-review
Skill1 starsChanged 7 months agoMITView on GitHub
Two-stage code review protocol. Stage 1: spec compliance (does code match spec?). Stage 2: code quality (is code well-written?). Stage 2 only runs after Stage 1 passes. Use after every implementation task in the Bayes Ship pipeline.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- pyinx/ceo-skills-plugintheir own version, first seen Jan 19, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- pyinx/ceo-skills-plugin★ 14same 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 repository43 other files it gives its agents.
- accessibilitySkill
- agent-evalSkill
- agentic-engineeringSkill
- ai-regression-testingSkill
- api-designSkill
- atomic-planningSkill
- backend-patternsSkill
- coding-standards-eccSkill
- context-engineeringSkill
- frontend-patternsSkill
- git-worktreesSkill
- langchain-dependenciesSkill
- langchain-fundamentalsSkill
- langchain-middlewareSkill
- langchain-ragSkill
- langgraph-fundamentalsSkill
- langgraph-persistenceSkill
- minimalist-skillSkill
- output-skillSkill
- redesign-skillSkill
- security-scanSkill
- ship-architectSkill
- ship-autoSkill
- ship-bugfixSkill
- ship-deploySkill
- ship-discoverSkill
- ship-executeSkill
- ship-finish-branchSkill
- ship-newSkill
- ship-planSkill
- ship-researchSkill
- ship-resumeSkill
- ship-reviewSkill
- ship-settingsSkill
- ship-specSkill
- ship-statusSkill
- ship-testSkill
- ship-worktreeSkill
- soft-skillSkill
- systematic-debuggingSkill
- taste-skillSkill
- test-driven-developmentSkill
- verification-before-completionSkill
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 7 are distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 21
If spec compliance fails: re-dispatch to implementer with specific feedback listing what's missing or what's extra.
- Distinctive: line 25
Only runs AFTER Stage 1 passes.
- Distinctive: line 31
Test quality (are the tests actually testing meaningful behavior?)
- Distinctive: line 37
Warning: Should fix. Fix in current cycle.
- Distinctive: line 42
Never skip either stage
- Distinctive: line 43
Never combine stages into one review
- Distinctive: line 44
Never let the implementer review their own work (use a separate subagent)
≈ “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
Two-Stage Review
Why two stages
Reviewing code quality on an implementation that doesn't match the spec is wasted effort. The spec compliance check gates the quality check.
Stage 1: Spec compliance review
The reviewer is SKEPTICAL. It does NOT trust the implementer's self-report.
Check:
- Does the implementation match the spec exactly?
- Are there MISSING requirements from the spec?
- Is there OVER-BUILDING (code that does more than the spec requires)?
- YAGNI violations? Features not in the spec?
If spec compliance fails: re-dispatch to implementer with specific feedback listing what's missing or what's extra. Do NOT proceed to Stage 2.
Stage 2: Code quality review
Only runs AFTER Stage 1 passes.
Check:
- Code style and conventions (against coding-standards skill if installed)
- Potential bugs or edge cases
- Security issues (against security skill if applicable)
- Test quality (are the tests actually testing meaningful behavior?)
- Naming clarity and code readability
- Unnecessary complexity
Report by severity:
- Critical: Blocks progress. Must fix before commit.
- Warning: Should fix. Fix in current cycle.
- Note: Optional improvement. Log for later.
Rules
- Never skip either stage
- Never combine stages into one review
- Never let the implementer review their own work (use a separate subagent)
- Reviewers read actual code and git diffs, not the implementer's description
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.