review-pr
Skill4 starsChanged 4 months agoMITView on GitHub
Review PR diff against the spec before shipping — check spec compliance, conventions, scope, required security checklist, and test coverage. Outputs a structured verdict (APPROVE / REQUEST CHANGES / COMMENT). Run after self-check, before Phase 4 ship.
185 other projects use a version of this.
Adopted by
Most recently taken up by
- torrust/torrust-trackertheir own version, first seen Nov 16, 2026
- Wendor/teapod-streamtheir own version, first seen Nov 16, 2026
- testcontainers/testcontainers-javatheir own version, first seen Nov 16, 2026
- hotcodepush-team/skillstheir own version, first seen Nov 16, 2026
- chuckplayer/claude-agent-packtheir own version, first seen Nov 16, 2026
- ayoubben18/ab-methodtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use diagnose-ci-failures, review-delta and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
zerx-labSkilldiagnose-ci-failures
Diagnose CI failures for a PR using the GitHub CLI, extract error logs, and generate a plan to fix them. Use when the user asks to check CI status, pull CI issues, triage test failures, or investigate PR build failures.
Also in 3 projects that use this
n24q02mSkillreview-delta
Review only changes since last commit using impact analysis. Token-efficient delta review with automatic blast-radius detection.
Also in 3 projects that use this
GeiserXSkilldocs-loop
Use when the user asks to audit docs, check documentation for stale claims, or verify docs against the code.
Also in 3 projects that use this
GeiserXSkillfull-loop
Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.
Also in 3 projects that use this
n24q02mSkillbuild-graph
Build or update the code review knowledge graph. Run this first to initialize, or let hooks keep it updated automatically.
Also in 3 projects that use this
- +7 more from GeiserX
Other versions185 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 185
- denoland/deno★ 109ksame name
- ToolJet/ToolJet★ 41ksame name
- remix-run/remix★ 33ksame name
- tirth8205/code-review-graph★ 33ksame name
- alpinejs/alpine★ 32ksame name
- nrwl/nx★ 29ksame name
- PrefectHQ/fastmcp★ 29ksame name
- jlowin/fastmcp★ 29ksame name
- livewire/livewire★ 24ksame name
- microsoft/fluentui★ 20ksame name
175 more not listed
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 repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- clarify-scopeSkill
- create-pr-descriptionSkill
- debugSkill
- implement-tddSkill
- plan-tasksSkill
- setup-ai-contextSkill
- shipSkill
- sync-ai-contextSkill
- write-specSkill
- write-test-scenariosSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 178 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 137
Do not fix them yourself. Report clearly, let the agent/implementer decide:
- Very specific: line 139
Create a follow-up task for minor issues → note in .ai/tasks/ or create an issue
“Common” is measured: kept by at least 6 in 10 of the 178 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
Review PR
Review the PR diff against the written spec. This is not a generic "code review" — it checks whether the code matches what was committed to in the spec.
Run
Step 1 — Read context
# View the full diff about to be shipped
git diff main...HEAD # or git diff <base-branch>...HEADAlso read:
.ai/tasks/<task-name>.md— spec (Goal, Scope, Out of scope, Constraints, Plan).ai/context/conventions.md— project code conventions.ai/context/security-checklist.md— required security checks
Step 2 — Review across 5 dimensions
Evaluate each dimension, record findings using [BLOCKING] or [MINOR] format:
A. Spec compliance
- Does the code achieve the Goal in the spec?
- Are there any changes outside
## Scope? - Are there any changes that violate
## Out of scope? - Are the
## Constraintsrespected? - Have all steps in
## Planbeen implemented?
[BLOCKING]: any Out of scope item violated, or Goal not achieved.
[MINOR]: a small step in Plan is missing but does not affect the Goal.
B. Conventions
Compare each change against .ai/context/conventions.md:
- Is error handling following the correct pattern? (no silent error swallowing)
- Does naming follow the convention?
- Are there any hardcoded values?
- Is there any copy-pasted code causing duplicate logic?
[BLOCKING]: violation of a hard convention (e.g., swallowing errors in a production path).
[MINOR]: naming slightly off style, can be fixed later.
C. Scope creep
# Check which files were touched outside the defined scope
git diff --name-only main...HEADCompare the list of changed files against ## Scope in the spec.
- Are there any files modified that are not mentioned in Scope?
- If so — is that change justified? (incidental bugfix, required refactor)
[BLOCKING]: unrelated change that increases risk unnecessarily.
[MINOR]: small cleanup in a related file.
D. Test coverage
- Does each item in
## Test planof the spec have a corresponding test? - Do tests cover the happy path?
- Do tests cover at least 1 edge case?
- Were any tests deleted without a clear reason?
# View changed test files
git diff --name-only main...HEAD | grep -E "test|spec"[BLOCKING]: happy path has no tests at all.
[MINOR]: some minor edge cases missing.
E. Security checklist (required)
- Complete every item in
.ai/context/security-checklist.mdusing[x](including N/A items as[x] <item>: N/A — <reason>) - For each N/A item, is there a short reason?
- Are there any unresolved findings from the checklist?
[BLOCKING]: any unresolved finding, or any checklist item left blank (not completed with [x], including N/A-with-reason entries).
Step 3 — Summarize verdict
Output format:
## PR Review: <task-name>
**Verdict:** ✅ APPROVE | 🔄 REQUEST CHANGES | 💬 COMMENT ONLY
---
### Blocking issues (must fix before merging)
<!-- Only present if verdict is REQUEST CHANGES -->
- [BLOCKING] <dimension> — <specific description> | <file:line if available>
### Minor issues (can fix in a follow-up PR)
- [MINOR] <dimension> — <description>
### Notes
<!-- Observations that are not issues, or positive highlights -->
-
---
Spec: `.ai/tasks/<task-name>.md`
Diff: <number of changed files> files, +<lines added>/-<lines removed>Verdict rules:
✅ APPROVE— no blocking issues🔄 REQUEST CHANGES— ≥1 blocking issue, must fix before merging💬 COMMENT ONLY— no blocking issues but something worth noting
Step 4 — If there are blocking issues
Do not fix them yourself. Report clearly, let the agent/implementer decide:
- Fix in the current PR → re-run review after fixing
- Create a follow-up task for minor issues → note in
.ai/tasks/or create an issue
What is NOT reviewed here
- Style preferences not in conventions.md → do not flag
- Architectural opinions outside the task scope → do not flag (that is ADR work)
- Performance that has not been measured as a problem → do not flag
- Absolute test coverage % → only check test plan items, do not require 100%
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.

