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.
- Depends on the
plan skill for drafting and approving the fix plan.
Prereq: ensure gh is authenticated (for example, run gh auth login once), then run gh auth status with escalated permissions (include workflow/repo scopes) so gh commands succeed. If sandboxing blocks gh auth status, rerun it with sandbox_permissions=require_escalated.
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
- Verify gh authentication.
- Run
gh auth status in the repo with escalated scopes (workflow/repo) after running gh auth login.
- If sandboxed auth status fails, rerun the command with
sandbox_permissions=require_escalated to allow network/keyring access.
- If unauthenticated, ask the user to log in before proceeding.
- 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.
- 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>"
- 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.
- Summarize failures for the user.
- Provide the failing check name, run URL (if any), and a concise log snippet.
- Call out missing logs explicitly.
- Create a plan.
- Use the
plan skill to draft a concise plan and request approval.
- Implement after approval.
- Apply the approved plan, summarize diffs/tests, and ask about opening a PR.
- 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
Converted and distributed by TomeVault — claim your Tome and manage your conversions.
1---2name: gh-fix-ci-53description: Inspect GitHub PR checks with gh, pull failing GitHub Actions logs, summarize failure context, then create a fix plan and implement after user approval. Use when a user asks to debug or fix failing PR CI/CD checks on GitHub Actions and wants a plan + code changes; for external checks (e.g., Buildkite), only report the details URL and mark them out of scope. Use when this capability is needed.4---56# Gh Pr Checks Plan Fix78## Overview910Use 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.1112- Depends on the `plan` skill for drafting and approving the fix plan.1314Prereq: ensure `gh` is authenticated (for example, run `gh auth login` once), then run `gh auth status` with escalated permissions (include workflow/repo scopes) so `gh` commands succeed. If sandboxing blocks `gh auth status`, rerun it with `sandbox_permissions=require_escalated`.1516## Inputs1718- `repo`: path inside the repo (default `.`)19- `pr`: PR number or URL (optional; defaults to current branch PR)20- `gh` authentication for the repo host2122## Quick start2324- `python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"`25- Add `--json` if you want machine-friendly output for summarization.2627## Workflow28291. Verify gh authentication.30 - Run `gh auth status` in the repo with escalated scopes (workflow/repo) after running `gh auth login`.31 - If sandboxed auth status fails, rerun the command with `sandbox_permissions=require_escalated` to allow network/keyring access.32 - If unauthenticated, ask the user to log in before proceeding.332. Resolve the PR.34 - Prefer the current branch PR: `gh pr view --json number,url`.35 - If the user provides a PR number or URL, use that directly.363. Inspect failing checks (GitHub Actions only).37 - Preferred: run the bundled script (handles gh field drift and job-log fallbacks):38 - `python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"`39 - Add `--json` for machine-friendly output.40 - Manual fallback:41 - `gh pr checks <pr> --json name,state,bucket,link,startedAt,completedAt,workflow`42 - If a field is rejected, rerun with the available fields reported by `gh`.43 - For each failing check, extract the run id from `detailsUrl` and run:44 - `gh run view <run_id> --json name,workflowName,conclusion,status,url,event,headBranch,headSha`45 - `gh run view <run_id> --log`46 - If the run log says it is still in progress, fetch job logs directly:47 - `gh api "/repos/<owner>/<repo>/actions/jobs/<job_id>/logs" > "<path>"`484. Scope non-GitHub Actions checks.49 - If `detailsUrl` is not a GitHub Actions run, label it as external and only report the URL.50 - Do not attempt Buildkite or other providers; keep the workflow lean.515. Summarize failures for the user.52 - Provide the failing check name, run URL (if any), and a concise log snippet.53 - Call out missing logs explicitly.546. Create a plan.55 - Use the `plan` skill to draft a concise plan and request approval.567. Implement after approval.57 - Apply the approved plan, summarize diffs/tests, and ask about opening a PR.588. Recheck status.59 - After changes, suggest re-running the relevant tests and `gh pr checks` to confirm.6061## Bundled Resources6263### scripts/inspect_pr_checks.py6465Fetch 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.6667Usage examples:6869- `python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "123"`70- `python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "https://github.com/org/repo/pull/123" --json`71- `python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --max-lines 200 --context 40`7273---74> Converted and distributed by [TomeVault](https://tomevault.io/claim/outlinedriven) — claim your Tome and manage your conversions.75<!-- tomevault:4.0:skill_md:2026-04-11 -->