Skip to main content
skill Claude Code CX Codex Cursor GitHub Copilot official · OpenAI

gh-fix-ci — Claude Code skill: what it does, how to install

Finds failing GitHub Actions checks on a pull request, inspects logs, and drafts a fix plan. The skill modifies code only after explicit approval.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add openai/skills --skill gh-fix-ci -a claude-code
Open on GitHub

What gh-fix-ci does

The skill investigates failing GitHub Actions checks on pull requests using the gh command-line tool. It relies on the bundled Python script inspect_pr_checks.py to extract logs and pinpoint failure snippets. When the create-plan skill is present, the agent uses it to structure the fix proposals.

It focuses exclusively on GitHub Actions runs. External CI providers such as Buildkite remain out of scope; the skill only reports their details link. Working with private repositories requires active gh authentication with both repo and workflow scopes.

Code changes never happen automatically. The agent presents a failure summary, asks for explicit user approval, and applies changes only after receiving confirmation.

What it helps with

  • find failing GitHub Actions checks on a pull request
  • extract failure log snippets directly in the terminal
  • draft a repair plan before applying code changes
  • filter out external CI providers like Buildkite

Example prompts for the agent

  • Debug the failing GitHub Actions checks on this pull request
  • Inspect CI failure logs for the current PR and draft a fix plan

How to install gh-fix-ci

1Skills CLI (Vercel)

npx skills add openai/skills --skill gh-fix-ci -a claude-code

2Manually: put the files in place

~/.claude/skills/gh-fix-ci/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/gh-fix-ci/

From the same set20

The whole set →
pdf official openai A skill for reading, creating and reviewing PDFs where layout matters. Useful when the agent builds a document and needs to see how it renders. Claude Code CX Codex Cursor +1 13,400installs openai-docs official openai The skill finds current OpenAI guidance for API work, Codex, model selection, migrations, and prompt updates, using official documentation. Claude Code CX Codex Cursor +1 6,100installs imagegen official openai This skill creates and edits raster images such as illustrations, textures, sprites, and mockups. Use it when the output should be a bitmap asset. Claude Code CX Codex Cursor +1 5,700installs jupyter-notebook official openai Scaffolds reproducible Jupyter notebooks for experiments and tutorials using bundled templates and a helper script. It prevents manual raw JSON editing errors. Claude Code CX Codex Cursor +1 5,600installs skill-creator official openai Official guide for drafting and updating agent skills. It structures procedures, bundled scripts, and documentation while keeping token overhead low. Claude Code CX Codex Cursor +1 4,900installs gh-address-comments official openai This skill finds the open pull request for the current branch, lists review comments, and applies the fixes you select through gh. Claude Code CX Codex Cursor +1 4,800installs cloudflare-deploy official openai This skill helps choose Cloudflare services and prepare application or infrastructure deployments through Workers, Pages, and related products. Claude Code CX Codex Cursor +1 4,300installs aspnet-core official openai Guides building, refactoring, and architecting ASP.NET Core apps using official Microsoft patterns. Helpful for Minimal APIs, Blazor, and migrations. Claude Code CX Codex Cursor +1 3,900installs

Similar

git-commit official github This skill reviews Git changes, stages related files, and creates Conventional Commits. Use it when you want an agent to make one commit or split work into separate commits. GitHub Copilot 47,165installs coding-agent openclaw This skill sends large coding tasks to Codex, Claude Code, or OpenCode as background workers. Use it for refactors, PR reviews, and issue-to-PR work. Claude Code CX Codex Cursor +1 6,500installs github openclaw A skill that teaches your agent to drive GitHub through gh: browse pull requests, read CI logs, post comments and query the API. Claude Code CX Codex Cursor +1 6,100installs gh-issues openclaw This skill finds GitHub issues, starts background fix agents, and opens PRs. Use it when you want an issue-to-PR workflow with optional review handling. Claude Code CX Codex Cursor +1 5,000installs open-code-review alibaba Skill runs the ocr CLI to review Git changes with AI. Produces line-level comments and can apply fixes on request. Claude Code CX Codex Cursor +1 6,800installs fix react The skill formats changed files and checks for remaining lint issues before a commit. Use it when code needs to pass CI checks. Claude Code CX Codex Cursor +1 2,300installs triage Matt Pocock This skill moves issues and external PRs through triage states, verification, and agent briefs. It fits maintainers managing an issue queue. Claude Code 990,453installs code-review Matt Pocock Reviews changes from a chosen reference point against repository standards and the originating spec. Use it for a branch, PR, or work in progress. Claude Code 789,521installs

Questions about gh-fix-ci

How do I install gh-fix-ci in Claude Code?

Run npx skills add openai/skills --skill gh-fix-ci -a claude-code in your terminal.

What does the gh-fix-ci skill do?

It locates failing GitHub Actions runs, retrieves relevant log snippets, and prepares a fix plan. The agent only edits code after you explicitly approve the plan.

Does the skill support external CI systems like Buildkite?

No, it only parses GitHub Actions runs. For third-party providers, it reports only the external details URL.

Source text

SKILL.md · Apache-2.0
---
name: "gh-fix-ci"
description: "Use when a user asks to debug or fix failing GitHub PR checks that run in GitHub Actions; use `gh` to inspect checks and logs, summarize failure context, draft a fix plan, and implement only after explicit approval. Treat external providers (for example Buildkite) as out of scope and report only the details URL."
---


# 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.

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. Summarize failures for the user.
   - 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 and request approval.
7. Implement after approval.
   - Apply the approved plan, summarize diffs/tests, and ask about opening a PR.
8. 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`

© openai · Apache-2.0 · openai/skills

See also

Project sponsors

Companies that keep this analytics open
Gold sponsor

Impressions, clicks and code copies — open statistics. We keep the numbers public for the same reason NeBlask itself is public. Become a sponsor