Agent skill

sym-fix-ci

Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions. Trigger words include: 'fix CI', 'debug GitHub Actions', 'gh pr checks', 'CI is red', 'GitHub Actions failed', 'fix the build', and similar phrases indicating a need to investigate and resolve CI failures in a GitHub-hosted repository.

View SKILL.md on GitHub Repository
Stars 28
Forks 2

Install this agent skill to your Project

npx add-skill https://github.com/gannonh/kata/tree/main/.agents/skills/sym-fix-ci

SKILL.md

Overview

Use gh to locate failing PR checks, fetch GitHub Actions logs for actionable failures, summarize the failures, and implement fixes.

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

  • python3 "<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):
      • python3 "<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. Summarize failures.
    • Provide the failing check name, run URL (if any), and a concise log snippet.
    • Call out missing logs explicitly.
  6. Create a plan.
    • Use the create-plan skill to draft a concise plan.
  7. Implement plan.
    • Apply the plan, summarize diffs/tests, commit and push changes.
  8. Recheck status.
    • After changes, re-run the relevant tests and gh pr checks to confirm.
    • If new or existing failures remain, repeat the workflow until CI passes
  9. Summarize outcome.
    • Once CI checks pass, summarize the fix and confirm with the user before merging or proceeding to the next steps in their workflow.

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:

  • python3 "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "123"
  • python3 "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "https://github.com/org/repo/pull/123" --json
  • python3 "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --max-lines 200 --context 40

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

gannonh/kata

kata-context

Structural and semantic codebase intelligence with persistent memory — index TypeScript and Python repos into a knowledge graph with vector embeddings, query symbol dependencies, run semantic search by intent, search code patterns, fuzzy-find symbols, and persist/recall agent memories with git audit trail. Use when you need to understand code structure, find what depends on a symbol, trace dependencies, search by meaning, search for code patterns, find symbols by name, or remember/recall project decisions, patterns, and learnings.

28 2
Explore
gannonh/kata

claude-md-improver

Audit and improve CLAUDE.md files in repositories. Use when user asks to check, audit, update, improve, or fix CLAUDE.md files. Scans for all CLAUDE.md files, evaluates quality against templates, outputs quality report, then makes targeted updates. Also use when the user mentions "CLAUDE.md maintenance" or "project memory optimization".

28 2
Explore
gannonh/kata

frontend-design

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

28 2
Explore
gannonh/kata

debug-like-expert

Deep analysis debugging mode for complex issues. Activates methodical investigation protocol with evidence gathering, hypothesis testing, and rigorous verification. Use when standard troubleshooting fails or when issues require systematic root cause analysis.

28 2
Explore
gannonh/kata

swiftui

SwiftUI apps from scratch through App Store. Full lifecycle - create, debug, test, optimize, ship.

28 2
Explore
gannonh/kata

sym-address-comments

Help address review/issue comments on the open GitHub PR for the current branch using gh CLI; verify gh auth first and prompt the user to authenticate if not logged in.

28 2
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results