pr-analysis
Skill56 starsChanged 34 days agoApache-2.0View on GitHub
Use this workflow skill for a deep, read-only PR review covering intent, code quality, regression risk, test gaps, and feedback status; prefer it over check-ci when the request is broader than CI triage.
5 other projects use a version of this.
Adopted by
Most recently taken up by
- jokob-sk/NetAlertXtheir own version, first seen Nov 1, 2026
- netalertx/NetAlertXtheir own version, first seen Nov 1, 2026
- harness/harness-skillstheir own version, first seen Nov 1, 2026
- kevin-lee/ai-dumping-groundtheir own version, first seen Oct 10, 2026
- The-Resonance-Team/skillstheir own version, first seen Sep 3, 2026
Other versions5 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 5
- jokob-sk/NetAlertX★ 7.4ksame name
- netalertx/NetAlertX★ 7.4ksame name
- harness/harness-skills★ 127same name
- kevin-lee/ai-dumping-ground★ 3same name
- The-Resonance-Team/skills★ 2same 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 repository35 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/AGENTS.mdAGENTS.md
- android/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- .github/CLAUDE.mdCLAUDE.md
- ios/CLAUDE.mdCLAUDE.md
- auto-mobile-code-reviewSkill
- ci-failure-triageSkill
- github-pr-feedbackSkill
- ios-swift-ciSkill
- node-prepushSkill
- prepush-androidSkill
- shell-prepushSkill
- android-gradlewSkill
- auto-mobile-code-reviewSkill
- bun-tasksSkill
- check-ciSkill
- ci-failure-triageSkill
- dead-codeSkill
- device-session-lifecycleSkill
- fan-out-fan-inSkill
- github-cliSkill
- github-pr-feedbackSkill
- ios-swift-ciSkill
- manual-testSkill
- node-prepushSkill
- observeSkill
- prepush-androidSkill
- push-my-prsSkill
- push-prSkill
- researchSkill
- shell-prepushSkill
- ship-issueSkill
- testSkill
- validateSkill
The file
We split this skill into the rules it gives an agent
6 rules. 0 are common, 3 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 5 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 15
Always collect GraphQL review-thread state: unresolved and outdated threads are not represented reliably by flat comment views.
- Distinctive: line 18
Read full changed files from the PR branch and the base branch, not just diff hunks.
- Distinctive: line 20
If validation is warranted, run the lightest relevant repo validation rather than a blanket heavy build.
- Very specific: line 25
Prefer gh for PR metadata and CI data.
- Distinctive: line 30
Keep the analysis read-only unless the user explicitly asks for fixes.
- Very specific: line 31
When saving large diffs or logs, put them in scratch/.
“Common” is measured: kept by at least 6 in 10 of the 5 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 Analysis
Perform a read-only PR review that covers intent, correctness, regression risk, tests, and existing feedback.
Workflow
- Resolve the PR with
gh pr view <pr> --json ...and capture the head branch, base branch, title, and body. - Gather context with
gh pr diff,gh pr diff --stat,gh pr checks, and all paginated review, inline, and conversation comments plus review verdicts. - Always collect GraphQL review-thread state: unresolved and outdated threads are not
represented reliably by flat comment views. Reuse
github-pr-feedbackfor the collection and the ledger. - Read full changed files from the PR branch and the base branch, not just diff hunks.
- Find related callers, interfaces, and tests in the local codebase.
- If validation is warranted, run the lightest relevant repo validation rather than a blanket heavy build.
- Produce findings first, then open questions, then a short summary.
Repo Rules
- Prefer
ghfor PR metadata and CI data. - Prefer repo validations:
- TypeScript:
bun run lint,bun run build,bun test - Fast checks:
bash scripts/all_fast_validate_checks.sh - Android or iOS only when the PR actually touches those areas
- TypeScript:
- Keep the analysis read-only unless the user explicitly asks for fixes.
- When saving large diffs or logs, put them in
scratch/.
Output Structure
- Findings ordered by severity with
file:linereferences - Open questions or assumptions
- Brief change summary and residual risks
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.