review-pr
Skill0 starsChanged 2 months agoMITView on GitHub
Reviews a pull request against the acceptance criteria of its ticket, plus the standards corpus, and reports findings ranked by severity. Use when the user asks to review a PR or merge request.
185 other projects use a version of this.
Adopted by
Most recently taken up by
- data-privacy-stack/presidiotheir own version, first seen Nov 9, 2026
- pgmpy/pgmpytheir own version, first seen Nov 9, 2026
- enes-alatas/spooltheir own version, first seen Nov 8, 2026
- microsoft/presidiotheir own version, first seen Nov 8, 2026
- domengabrovsek/agent-configtheir own version, first seen Nov 8, 2026
- domengabrovsek/claudetheir own version, first seen Nov 8, 2026
Used with
Projects with it also use diagnose-ci-failures, docs-loop 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
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
- GeiserXSkill
full-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
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
- n24q02mSkill
build-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★ 28ksame name
- jlowin/fastmcp★ 28ksame 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 repository2 other files it gives its agents.
- release-notesSkill
- incidentSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 178 edited versions we read keep these.
3
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-only. Reads the diff and the ticket, writes findings.
- Distinctive: line 49
Do not report what the linter already reports.
- Distinctive: line 50
No finding invented to fill a report.
“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
Read-only. Reads the diff and the ticket, writes findings. Never pushes, never approves, never merges.
Steps
Get the ticket first. A review without acceptance criteria is a style review, which is the least valuable kind. Pull the ticket referenced in the branch name or PR title.
gh pr view <n> --json title,body,headRefName,files gh pr diff <n>- Check each acceptance criterion against the diff, one at a time. Say which line satisfies it. A criterion with no corresponding code is the most valuable finding in the whole review, and the one automated tools miss.
- Then the standards in
standards/INDEX.md— route by what the diff touches, do not load the whole corpus. - Then correctness, in this order: error handling across boundaries, missing test for a new branch of logic, N+1 queries, unbounded loops over external calls, secrets in code, migrations that lock a table.
Output
Ranked by severity, worst first. For each:
<file>:<line> — <one sentence: the defect>
Fails: <what breaks, with concrete inputs>Then, separately, a Criteria not covered list.
Rules
- Every finding must have a failure scenario. Concrete inputs, wrong output. If you cannot write one, it is a preference and belongs under a "minor" heading or nowhere.
- Do not report what the linter already reports.
- No finding invented to fill a report. "Nothing blocking" is a real result and a review that says it stays trustworthy.
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.