pr-review
Skill2 starsChanged 5 months agoMITView on GitHub
Structured Pull Request review — collects diff + description, identifies owner / scope / risks, invokes the senior advisor when strategic weight is present, produces a verdict and a suggested PR comment. Atomic skill, reusable in any repo where the principal is a reviewer.
195 other projects use a version of this.
Adopted by
Most recently taken up by
- IntelRealSense/librealsensetheir own version, first seen Nov 16, 2026
- wikimedia/wikipedia-iostheir own version, first seen Nov 16, 2026
- realsenseai/librealsensetheir own version, first seen Nov 16, 2026
- minio/skillstheir own version, first seen Nov 16, 2026
- lumlaolao/spike-evaltheir own version, first seen Nov 16, 2026
- AshrafDurjoy/genai-shared-patternstheir own version, first seen Nov 16, 2026
Used with
Projects with it also use clack-cli-patterns, drag-to-reorder 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.
openchamberSkillclack-cli-patterns
Use when creating or modifying OpenChamber CLI commands, prompts, terminal output, non-TTY behavior, `--quiet`, or `--json` behavior.
Also in 3 projects that use this
openchamberSkilldrag-to-reorder
Use when implementing or modifying OpenChamber sortable or drag-to-reorder behavior, especially `@dnd-kit`, touch/mobile interactions, variable-width items, or wrapping layouts.
Also in 3 projects that use this
jtenniswoodSkillexpert-reset
Reimagine this repository from first principles using the current product and user experience as the target. Use when the user says "/expert-reset", asks how the project should be rebuilt if starting again, wants bold architecture or component-structure recommendations, or wants a research-only reset plan unconstrained by current implementation details.
Also in 3 projects that use this
CES-LtdSkilloss-pr
Use when creating a pull request, after committing changes, or when user invokes /oss-pr. Covers branch management, quality checks, commit, push, and PR creation.
Also in 3 projects that use this
CES-LtdSkillpr-automation
PR Automation Orchestrator: poll open PRs, check CI, run review, fix, and merge eligible PRs. Use when: (1) Invoked by daemon via scripts/pr-automation.sh, (2) User says "/pr-automation".
Also in 3 projects that use this
- +7 more from openchamber
Other versions195 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 195
- Significant-Gravitas/AutoGPT★ 188ksame name
- pytorch/pytorch★ 106ksame name
- rtk-ai/rtk★ 87ksame name
- saadeghi/daisyui★ 43ksame name
- rustfs/rustfs★ 36ksame name
- dotnet/maui★ 23ksame name
- NVIDIA/Megatron-LM★ 18ksame name
- MiniMax-AI/skills★ 14ksame name
- btriapitsyn/openchamber★ 13ksame name
- openchamber/openchamber★ 13ksame name
185 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 repository24 other files it gives its agents.
- AGENTS.mdAGENTS.md
- control-plane/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- control-plane/CLAUDE.mdCLAUDE.md
- agentic-os-reference-syncSkill
- branch-cleanupSkill
- capture-triageSkill
- darwin-housekeepingSkill
- darwin-path-modeSkill
- decision-log-entrySkill
- eodSkill
- expert-interview-guideSkill
- feedback-intakeSkill
- harness-onboardingSkill
- ingest-contentSkill
- meeting-to-work-itemsSkill
- memory-consolidateSkill
- morning-briefSkill
- os-bootstrap-extendSkill
- os-bootstrapSkill
- scheduleSkill
- spec-cross-checkSkill
- ux-critiqueSkill
- weekly-retroSkill
The file
We split this skill into the rules it gives an agent
5 rules. 0 are common, 1 is distinctive, and 4 are very specific to this project.
0
Common
Most of the 180 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
If gh is not authenticated, the auto-gh-auth.sh hook surfaces this before the first gh call and the skill should pause for authentication.
- Very specific: line 26
NOT for: mechanical merge (gh pr merge), full-repo analysis (escalate to a specific agent), reviewing a non-PR artifact (deck, doc → use …
- Very specific: line 62
If depth >= standard and strategic weight is present → the senior advisor is invoked and its output is integrated.
- Very specific: line 78
If the repo has a decisions-locked.md, decision-log.md, or OPEN_QUESTIONS.md, scan for entries that this PR touches.
- Distinctive: line 110
Always end with a concrete next step:
“Common” is measured: kept by at least 6 in 10 of the 180 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
Skill: pr-review
Preconditions
ghCLI is installed and authenticated against the relevant remote (gh auth statusreturns OK).gitcwd is the target repo (or therepoinput is supplied asowner/repo).- The senior advisor agent is available if depth ≥ standard and strategic weight is present.
If gh is not authenticated, the auto-gh-auth.sh hook surfaces this before the first gh call and the skill should pause for authentication.
When to use
Whenever a PR shows up that the principal needs to review — own repo or any repo where review is needed.
NOT for: mechanical merge (gh pr merge), full-repo analysis (escalate to a specific agent), reviewing a non-PR artifact (deck, doc → use deck-review or artifact-reviewer).
Inputs
pr_number(required) — PR number.repo(optional) —owner/repoif not in the PR's cwd; defaults to current repo.depth(optional) —"quick"(summary only),"standard"(default — analysis + senior advisor if applicable),"deep"(senior advisor always + architectural diff).
Output structure
## PR #N — <title> (author: <login>)
**Scope:** diff +X / -Y across N files | branch `<head>` | mergeState: `<status>`
**Strengths:**
- ...
**Points to validate (non-blocking):**
- ...
**Material risk identified:**
- ... (or "none")
**Senior-advisor recommendation?** Yes/No — <one-line justification>
**Verdict:** APPROVE / REFINE & RETURN / REJECT — <one line>
**Suggested PR comment** (if REFINE):
> [text ready to paste into `gh pr comment`]If depth >= standard and strategic weight is present → the senior advisor is invoked and its output is integrated.
Sequence
Step 1 — Collect PR data
gh pr view <pr_number> --json title,author,headRefName,mergeable,additions,deletions,changedFiles,body,baseRefName
gh pr diff <pr_number>
gh pr checks <pr_number>Step 2 — Read context
If the repo has a decisions-locked.md, decision-log.md, or OPEN_QUESTIONS.md, scan for entries that this PR touches. Cross-reference scope to known locked premises.
Step 3 — Identify scope and risk class
| Class | Criterion | Default depth |
| Trivial | Doc-only, formatting, one-line | quick |
| Standard | Single module / spec scope, < 200 LOC | standard |
| Cross-cutting | Touches > 3 modules OR architectural decision OR spec amendment | deep |
| Governance | Touches control-plane/, .claude/, hooks, CLAUDE.md, rules/ | deep + senior advisor |
Step 4 — Senior-advisor invocation
Invoke the senior advisor (Walter equivalent) when any of:
- Cross-cutting or governance class.
- Reviewer flags carry strategic weight or interpretation risk.
- The PR proposes a deviation from a locked decision.
- Author and reviewer disagree in the comments and the disagreement is not yet resolved.
Skip the senior advisor when:
- Trivial / doc-only changes with no policy implication.
- Mechanical refactor with full test coverage.
- Author has already addressed prior senior-advisor pressure-test in commits.
Step 5 — Produce verdict
- APPROVE — no material risk, scope clear, tests adequate (if applicable). Comment optional.
- REFINE & RETURN — at least one material issue with a concrete remediation path. Suggested comment ready to paste.
- REJECT — fundamental scope or correctness problem. Recommend the author close the PR or restart with a different approach. Comment explains why.
Step 6 — Hand off
Always end with a concrete next step:
- "Suggested action: paste the comment above, then ping the author."
- "Auto-merge candidate — would you like me to merge after CI passes?"
- "Escalate to senior-advisor pressure-test (depth=deep)?"
Anti-patterns
- Approving without reading the diff. A summary is not a review.
- Bypassing the senior advisor on governance-class PRs — even if it feels routine.
- Suggesting changes that exceed the PR's scope — refactor proposals belong in a new PR, not in this comment.
- Vague verdicts — "looks fine" is not a verdict. APPROVE / REFINE / REJECT and one sentence of justification.
Integration with the no-direct-merge rule
This skill never merges. Merging requires gh pr merge, which is blocked by block-pr-merge.sh for repos with shared / public visibility. The reviewer's job is to APPROVE or REFINE; the principal still holds the merge decision.
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.

