Gh Pr Checks Plan Fix

Overview

Use gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failure snippet, then propose a fix plan and implement after explicit approval.

• If a plan-oriented skill (for example create-plan) is available, use it; otherwise draft a concise plan inline and request approval before implementing.
• After identifying the failing check, reproduce the exact repo command locally when feasible before editing. Prefer the same command CI runs (bun run lint, pnpm test, npm run build, etc.) so you can confirm the failure and verify the fix without depending solely on remote logs.
• If the user has already explicitly approved implementation or explicitly asked you to land the fix directly on main, do not stop to re-request approval. Implement the fix, then stage only the files relevant to that approved change.

Prereq: authenticate with the standard GitHub CLI once (for example, run gh auth login), then confirm with gh auth status (repo + workflow scopes are typically required).

Inputs

• repo: path inside the repo (default .)
• pr: PR number or URL (optional; defaults to current branch PR)
• gh authentication for the repo host

Quick start

• python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"
• Add --json if you want machine-friendly output for summarization.

Workflow

1. Verify gh authentication.
   • Run gh auth status in the repo.
   • If unauthenticated, ask the user to run gh auth login (ensuring repo + workflow scopes) before proceeding.
2. Resolve the PR.
   • Prefer the current branch PR: gh pr view --json number,url.
   • If the user provides a PR number or URL, use that directly.
3. Inspect failing checks (GitHub Actions only).
   • Preferred: run the bundled script (handles gh field drift and job-log fallbacks):
     • python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"
     • Add --json for machine-friendly output.
   • Manual fallback:
     • gh pr checks <pr> --json name,state,bucket,link,startedAt,completedAt,workflow
       • If a field is rejected, rerun with the available fields reported by gh.
     • For each failing check, extract the run id from detailsUrl and run:
       • gh run view <run_id> --json name,workflowName,conclusion,status,url,event,headBranch,headSha
       • gh run view <run_id> --log
     • If the run log says it is still in progress, fetch job logs directly:
       • gh api "/repos/<owner>/<repo>/actions/jobs/<job_id>/logs" > "<path>"
4. Scope non-GitHub Actions checks.
   • If detailsUrl is not a GitHub Actions run, label it as external and only report the URL.
   • Do not attempt Buildkite or other providers; keep the workflow lean.
5. Reproduce locally before editing.
   • If the workflow or logs make the failing command clear, run the same command locally and capture the concrete failure.
   • Prefer local reproduction before code changes because it is faster to iterate and gives a direct verification target.
   • If local reproduction is blocked by missing secrets, unavailable services, or purely remote-only infrastructure, say so and continue with the best evidence from GitHub logs.
6. Summarize failures for the user.
   • Provide the failing check name, run URL (if any), and a concise log snippet.
   • Include the local reproduction result when you have one, especially if it narrows the problem more clearly than the remote logs.
   • Call out missing logs explicitly.
7. Create a plan.
   • Use the create-plan skill to draft a concise plan and request approval.
8. Implement after approval.
   • Apply the approved plan and summarize diffs/tests.
   • If the user explicitly asked to land on main, commit and push directly to main.
   • If the repo has unrelated dirty or untracked changes, stage only the files for the approved fix. Do not sweep in unrelated work.
   • Otherwise, ask about opening a PR.
9. Recheck status.
   • After changes, suggest re-running the relevant tests and gh pr checks to confirm.

Bundled Resources

scripts/inspect_pr_checks.py

Fetch failing PR checks, pull GitHub Actions logs, and extract a failure snippet. Exits non-zero when failures remain so it can be used in automation.

Usage examples:

• python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "123"
• python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "https://github.com/org/repo/pull/123" --json
• python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --max-lines 200 --context 40