pr-reviewer
Skill294 starsChanged yesterdayMITView on GitHub
Use when the user names a branch with any review intent ("review PR for branch X", "is branch Y good to merge", "check the changes on Z"). Not for the uncommitted working tree, or for authoring new tests or page objects (see `ai-native-workflow`).
23 other projects use a version of this.
Adopted by
Most recently taken up by
- LIXIAO199115/skillrigtheir own version, first seen Nov 15, 2026
- getpapi/papitheir own version, first seen Nov 1, 2026
- kcayme/k-agentstheir own version, first seen Nov 1, 2026
- odykyi/gh-skillstheir own version, first seen Oct 25, 2026
- archiforge/agent-crafttheir own version, first seen Oct 20, 2026
- jpantsjoha/ai-native-developer-experiencetheir own version, first seen Oct 16, 2026
Other versions23 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 23
- pyuvm/pyuvm★ 574same name
- Fu-Jie/awesome-openwebui★ 326same name
- Fu-Jie/openwebui-extensions★ 326same name
- proflead/codex-skills-library★ 153same name
- h0tp-ftw/ankimon★ 83same name
- glincker/claude-code-marketplace★ 37same name
- jpantsjoha/ai-native-developer-experience★ 13same name
- getpapi/papi★ 11same name
- tstapler/dotfiles★ 8same name
- gvre/skills★ 7same name
13 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 repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ai-native-workflowSkill
- api-testingSkill
- common-tasksSkill
- configSkill
- data-strategySkill
- debuggingSkill
- enumsSkill
- fixturesSkill
- helpersSkill
- page-objectsSkill
- playwright-cliSkill
- refactor-valuesSkill
- selectorsSkill
- skill-creatorSkill
- test-standardsSkill
- type-safetySkill
- ai-native-workflowSkill
- api-testingSkill
- common-tasksSkill
- configSkill
- data-strategySkill
- debuggingSkill
- enumsSkill
- fixturesSkill
- helpersSkill
- page-objectsSkill
- playwright-cliSkill
- pr-reviewerSkill
- refactor-valuesSkill
- selectorsSkill
- skill-creatorSkill
- test-standardsSkill
- type-safetySkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 23 edited versions we read keep these.
2
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 12
Route every changed path to its skills and read them: before judging; the Constitution applies everywhere.
- Very specific: line 22
Read the whole diff first: git diff "$BASE"...HEAD --stat, then git diff "$BASE"...HEAD.
- Distinctive: line 43
Run the scan script, then walk the checklist against the diff.
“Common” is measured: kept by at least 6 in 10 of the 23 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
PR Reviewer
Critical
- Read-only until the report is delivered. Fixes only when the user asks after reading it; a commit only on explicit approval.
- Always the three-dot diff against the remote base (
git diff "$BASE"...HEADwithBASE=origin/<name>); a two-dot diff reviews commits the author never wrote. - Route every changed path to its skills and read them before judging; the Constitution applies everywhere.
- Run the checks, do not only read:
scripts/verify-changed.shand the affected specs. - The Constitution checklist is a gate before the report:
scripts/scan-constitution.shin this skill's directory, thenreferences/constitution-checklist.mdwithfile:lineevidence; every ❌ is a finding. - Every finding is tied to a rule, a bug or a missing case; a style opinion without a rule is noise.
- Env failures are not branch failures. A run that dies on a missing env var or token is reported as such; never invent or stub a credential.
- A schema loosened to swallow a runtime surprise is a must-fix finding (
z.strictObject→z.object,.optional(),.nullable(),.catchall(), a widened validator); the sanctioned fix istest.skip+// FIXME. Never--approveor--request-changeson the user's behalf.
Procedure
scripts/checkout-branch.sh <branch> [base]resolves the base, refuses a dirty tree, fetches and switches, printsBASEandORIGINAL_REF; aSTOPline means ask the user.- Read the whole diff first:
git diff "$BASE"...HEAD --stat, thengit diff "$BASE"...HEAD. Route with the table and read each listed skill; a path outside the table takes the closest indexed skill.
Changed path Read tests/**/api/**api-testing,test-standards,type-safetytests/**/e2e/**,tests/**/functional/**test-standards,page-objects,fixturestests/**/*.setup.tshelpers,fixtures,test-standardspages/**page-objects,selectors,playwright-clifixtures/api/schemas/**type-safety,api-testingfixtures/**fixtures,helperstest-data/factories/**data-strategy,type-safetytest-data/static/**data-strategy,refactor-values,type-safetyenums/**, new membersenumsenums/**,test-data/static/**, changed existing valuesrefactor-valuesconfig/**confighelpers/**helpersany **/*.tstype-safetyscripts/verify-changed.sh "$BASE"(eslint, prettier, tsc on the changed files), then the affected specs perreferences/verification.md.- Review the diff against the routed skills: the Constitution rows for the area, contract fidelity, consistency with the nearest sibling file, real bugs (wrong assertion,
.find()on a possibly empty response, copy-paste leftovers), coverage gaps, scope creep. - Run the scan script, then walk the checklist against the diff; ➖ only when the branch does not touch the area, "could not evaluate" recorded as such, never as ✅.
- Report in chat with
assets/report-template.mdand the confidence rubric inreferences/reporting.md; post to the PR only when asked. Thengit switch "$ORIGINAL_REF". - Offer fixes ("Want me to implement any of these findings?"); apply only the chosen ones per the routed skills, re-run step 4, then ask before committing (Conventional Commit subject, co-author trailer).
References
references/constitution-checklist.md: step 6, the 31-row gate.references/verification.md: step 4, the tsc detour, running the affected specs, the env limit.references/reporting.md: step 7, the confidence rubric and posting to GitHub.assets/report-template.md: step 7, the report shape.assets/review-prompt.md: a paste-ready invocation for the user.scripts/checkout-branch.sh,scripts/verify-changed.sh,scripts/scan-constitution.sh: steps 1, 4 and 6.
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.

