check-pr
Skill2 starsChanged 9 months agoMITView on GitHub
Checks a GitHub pull request for unresolved review comments, failing status checks, and incomplete PR descriptions. Waits for pending checks to complete, categorizes issues as actionable or informational, and optionally fixes and resolves them. Use when the user wants to check a PR, address review feedback, or prepare a PR for merge.
We split this skill into the rules it gives an agent
10 rules. 6 are common, 1 is distinctive, and 3 are very specific to this project.
6
Common
Most of the 8 edited versions we read keep these.
1
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
- Common: line 28
If a PR number was provided, use it.
- Very specific: line 43
Before analyzing, ensure all status checks have completed.
- Common: line 52
If any are failing, identify which ones and the failure reason.
- Very specific: line 63
Look for bot review comments (e.g.
- Common: line 94
If there are actionable items:
- Common: line 97
Ask the user if they want to fix the issues.
- Distinctive: line 98
If yes, make the fixes, commit, and push.
- Common: line 102
After addressing comments, resolve the corresponding review threads.
- Very specific: line 126
If hasNextPage is true, repeat with -f cursor=ENDCURSOR to get remaining threads.
- Common: line 143
If checking a chain of PRs, process them sequentially.
“Common” is measured: kept by at least 6 in 10 of the 8 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
Check PR
Analyze a pull request for review comments, status checks, and description completeness, then help address any issues found.
Inputs
- PR number (optional): If not provided, detect the PR for the current branch.
Instructions
1. Identify the PR
If a PR number was provided, use it. Otherwise, detect it:
gh pr view --json number -q .number2. Fetch PR details
gh pr view <PR_NUMBER> --json title,body,state,reviews,comments,headRefName,statusCheckRollup
gh api repos/{owner}/{repo}/pulls/<PR_NUMBER>/comments3. Wait for pending checks
Before analyzing, ensure all status checks have completed. If any checks are PENDING or IN_PROGRESS, poll every 30 seconds until all checks reach a terminal state (success or failure). This ensures that review bot comments (Greptile, linters, etc.) are available before analysis.
4. Analyze the PR
Once all checks are complete, evaluate these areas:
A. Status Checks
- Are all CI checks passing?
- If any are failing, identify which ones and the failure reason.
B. PR Description
- Is the description complete and follows team conventions?
- Are all required sections filled in?
- Are there TODOs or placeholders that need updating?
C. Review Comments
- Inline code review comments that need addressing
- Look for bot review comments (e.g. from
greptile-apps[bot], linters, etc.) - Human reviewer comments
D. General Comments
- Discussion comments on the PR
- Bot comments (Vercel deploy previews, etc.) — usually informational
5. Categorize issues
For each issue found, categorize as:
| Category | Meaning |
| Actionable | Code changes, test improvements, or fixes needed |
| Informational | Verification notes, questions, or FYIs that don't require changes |
| Already addressed | Issues that appear to be resolved by subsequent commits |
6. Report findings
Present a summary table:
| Area | Issue | Status | Action Needed |
| Status Checks | CI build failing | Failing | Fix type error in src/api.ts |
| Review | "Add null check" — @reviewer | Actionable | Add guard clause |
| Description | TODO placeholder in test plan | Actionable | Fill in test plan |
| Review | "Looks good" — @teammate | Informational | None |
7. Fix issues (if requested)
If there are actionable items:
- Switch to the PR's branch if not already on it.
- Ask the user if they want to fix the issues.
- If yes, make the fixes, commit, and push.
8. Resolve review threads
After addressing comments, resolve the corresponding review threads.
First, fetch unresolved thread IDs (paginate if needed — see the GraphQL reference):
gh api graphql -f query='
query($cursor: String) {
repository(owner: "OWNER", name: "REPO") {
pullRequest(number: PR_NUMBER) {
reviewThreads(first: 100, after: $cursor) {
pageInfo { hasNextPage endCursor }
nodes {
id
isResolved
comments(first: 1) {
nodes { body path }
}
}
}
}
}
}'If hasNextPage is true, repeat with -f cursor=ENDCURSOR to get remaining threads.
Then resolve threads that have been addressed or are informational:
gh api graphql -f query='
mutation {
resolveReviewThread(input: {threadId: "THREAD_ID"}) {
thread { isResolved }
}
}'Batch multiple resolutions into a single mutation using aliases (t1, t2, etc.).
9. Multiple PRs
If checking a chain of PRs, process them sequentially.
Output format
Summarize:
- PR title and current state
- Status checks summary (passing/failing/pending)
- Total issues found
- Actionable items with descriptions
- Items that can be ignored with reasons
- Recommended next steps
Other versions9 projects use a version of this.
Word for word · 0
None found.
Edited · 7
- paperclipai/paperclip★ 110k18% same
- greptileai/skills★ 43133% same
- basementstudio/website-2k25★ 26233% same
- haseeb-heaven/gworkspace-agent★ 8236% same
- kellykampen/agent-skills★ 233% same
- ever-works/skills★ 118% same
- yxhta/skills★ 139% same
Wrote their own version · 2
- danielcherubini/skills★ 14same name
- shinobiashi/claude-skills★ 0same 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 repositoryOne other file it gives its agents.
- greploopSkill
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

