spec-reviewer
Skill1 starsChanged 41 days agoMITView on GitHub
Reviews a spec against the feature description for completeness. Returns PASS or FAIL. Invoked by spec-writer, not directly.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- behavioralstate/spectheir own version, first seen Nov 1, 2026
- tjespers/claude-skillstheir own version, first seen Mar 12, 2026
- EnzeD/skillstheir own version, first seen Feb 5, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- EnzeD/skills★ 9same name
- behavioralstate/spec★ 4same name
- tjespers/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 repository38 other files it gives its agents.
- agent-conductSkill
- bugfixSkill
- code-smellsSkill
- deliverSkill
- final-responseSkill
- frontend-designSkill
- go-conventionsSkill
- go-implementorSkill
- go-reviewerSkill
- go-test-strengthSkill
- implementation-principlesSkill
- nextflow-conventionsSkill
- nextflow-implementorSkill
- nextflow-reviewerSkill
- nextjs-fastapi-conventionsSkill
- nextjs-fastapi-implementorSkill
- nextjs-fastapi-reviewerSkill
- orchestratorSkill
- phase-creatorSkill
- phase-reviewerSkill
- prose-principlesSkill
- pr-resolverSkill
- pr-reviewerSkill
- python-conventionsSkill
- python-implementorSkill
- python-reviewerSkill
- spec-authorSkill
- spec-proofreaderSkill
- spec-writerSkill
- subagentsSkill
- swift-conventionsSkill
- swift-implementorSkill
- swift-reviewerSkill
- testing-principlesSkill
- tightenSkill
- unslopSkill
- verificationSkill
- writing-for-agentsSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 4 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
4
Distinctive
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 8
Read and follow agent-conduct before starting.
- Distinctive: line 41
Verify alignment with the conventions skill: business logic separated from entry points, external deps mockable, existing code reused, …
- Distinctive: line 53
Do NOT edit the spec - only report findings.
- Distinctive: line 54
Do NOT check text quality (that's spec-proofreader's job).
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Spec Reviewer Skill
Read and follow agent-conduct before starting.
You have clean context. Independently verify that the spec fully covers the user's requested feature.
Input
- Feature description (including clarifying Q&A).
- Spec path.
- Conventions skill text.
Procedure
1. Read the spec and feature description.
2. Check coverage
For every requirement in the feature description:
- A user story addresses it.
- Acceptance tests would verify it (explicit enough for concrete assertions).
- Edge cases and error conditions are covered.
3. Check for gaps
- Missing functionality (requirements without stories/tests).
- Incomplete stories (missing error/edge case tests).
- Untestable tests (vague expected outcomes).
- Missing architecture components.
- Missing integration tests for CLI/API/end-to-end flows.
4. Check architecture
Verify alignment with the conventions skill: business logic separated from entry points, external deps mockable, existing code reused, proper file organisation.
5. Verdict
- PASS - spec fully covers the feature. Note minor non-blocking suggestions.
- FAIL - specific, actionable feedback: missing requirements, vague tests, architectural issues, and what to add/change.
Rules
- Do NOT edit the spec - only report findings.
- Do NOT check text quality (that's spec-proofreader's job).
- Focus exclusively on feature coverage and testable acceptance criteria.
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.