ci-repairbay
Skill1 starsChanged 4 months agoApache-2.0View on GitHub
Use when a user asks to inspect, diagnose, or fix failing GitHub PR checks that run in GitHub Actions. Inspection requests stay read-only; explicit fix requests authorize scoped local changes and validation.
In this repository19 other files it gives its agents.
- AGENTS.mdAGENTS.md
- agent-aeoSkill
- agent-memorySkill
- beanquerySkill
- delegated-developmentSkill
- ghSkill
- issue-blueprintSkill
- issue-workbenchSkill
- minifluxSkill
- og-imageSkill
- opSkill
- pencil-to-figma-migrationSkill
- pr-comment-sweepSkill
- pr-launchpadSkill
- repo-surveyorSkill
- review-checkpointSkill
- review-repairbaySkill
- shipyardSkill
- skill-optimizerSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 0 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use gh and the bundled inspector for failing GitHub Actions PR checks.
- Very specific: line 34
Add --json; add --log-tail only when the failure snippet is insufficient.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CI Repairbay
Use gh and the bundled inspector for failing GitHub Actions PR checks.
Inspection, diagnosis, explanation, and review are read-only. An explicit fix
request authorizes only the smallest local fix and relevant non-destructive
validation. External writes, destructive actions, and material scope expansion
still require authorization.
Memory
Direct invocation owns $agent-memory; nested invocation defers it to the
caller. Capture only confirmed reusable CI root causes, repository guardrails,
or durable fix decisions—not status, logs, run IDs, or transient failures.
Inputs
repo_path: target repository, default.; pass as--repo.pr: optional number or URL; default current-branch PR.
Workflow
- Resolve the URL or PR in
repo_path; fetch its metadata and changed files. Run:
python "<skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"Add
--json; add--log-tailonly when the failure snippet is insufficient. The script uses nativegh pr checksandgh run view --log-failedoutput.- Report each failing check, run URL, concise evidence, and missing logs without overstating certainty. Non-GitHub Actions URLs are external and report-only. Inspection or diagnosis stops here.
- For an explicit fix, inspect the root cause, apply the smallest traceable local change, and run the focused repository check. Direct fixes remain uncommitted and unpushed unless the user requested publication. When nested Shipyard explicitly delegates commit-and-push authority, inspect the final scoped code diff, commit only those fixes, and push before returning. Nesting alone is not authority. If failure is unrelated to the diff, ask before expanding scope.
- Re-run the inspector or failed local check, not duplicate
gh pr checks, and report remaining external, flaky, pending, or unverified risk.
Finish with:
status=PASS|BLOCKED|PENDING artifacts=<path-or-none> summary=<one line>PASS means the requested diagnosis is complete, blockers are fixed, or only
waived/external checks remain. BLOCKED means a fix needs authorization,
credentials, logs, or another provider. PENDING means a rerun is still active.
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.

