agentleFS
HenryQWHenryQW/skills/ci-repairbay/SKILL.md

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.

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
  1. Very specific:

    Use gh and the bundled inspector for failing GitHub Actions PR checks.

    line 8
  2. Very specific:

    Add --json; add --log-tail only when the failure snippet is insufficient.

    line 34

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. Resolve the URL or PR in repo_path; fetch its metadata and changed files.
  2. Run:

    python "<skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"

    Add --json; add --log-tail only when the failure snippet is insufficient. The script uses native gh pr checks and gh run view --log-failed output.

  3. 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.
  4. 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.
  5. 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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.