Skip to main content
skill CX Codex

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

openai-gh-fix-ci reads the failing GitHub Actions checks on a pull request, pulls the logs, names the cause and drafts a fix. Edits land only after you approve the plan.

Apache-2.0 ★ 540 updated 2026-07-14

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add trailofbits/skills-curated
/plugin install openai-gh-fix-ci@skills-curated
Open on GitHub

What openai-gh-fix-ci does

Ask it why a pull request is red and it works through the checks with the GitHub CLI. It resolves the PR, lists what failed, opens the run logs and quotes the part that broke. Then it stops and writes a plan.

The bundled scripts/inspect_pr_checks.py does the fetching and copes with gh field changes; when a run log is still streaming, it falls back to the job log endpoint. --json gives structured output, while --max-lines and --context trim what you see. If a create-plan skill exists in the project, the plan comes from there.

Run gh auth login once with repo and workflow scopes, and keep Python around for the script. Checks from other providers, Buildkite for instance, get a details URL and nothing more. After the fix the skill suggests re-running tests and gh pr checks.

What it helps with

  • trace a red CI check back to the failing line
  • get a short log excerpt instead of the whole run output
  • draft a fix plan before any file is touched
  • tell a GitHub Actions check from an outside provider
  • re-run checks and confirm the branch is green

Example prompts for the agent

  • Look at my PR checks and tell me what broke.
  • Pull the logs for the failing check on PR #123 and sketch a fix plan, don't edit anything yet.
  • Run inspect_pr_checks.py with --json and explain the failure.

How to install openai-gh-fix-ci

1Plugin marketplace

/plugin marketplace add trailofbits/skills-curated
/plugin install openai-gh-fix-ci@skills-curated

This installs the whole openai-gh-fix-ci plugin with all its skills

2Skills CLI (Vercel)

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

3Manually: put the files in place

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

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

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about openai-gh-fix-ci

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

From the marketplace: first /plugin marketplace add trailofbits/skills-curated, then /plugin install openai-gh-fix-ci@skills-curated.

What does Anthropic-gh-fix-ci do?

It finds failing PR checks that run in GitHub Actions, reads their logs and shows the snippet where things broke. Then it drafts a fix plan and applies it once you agree.

What do I need before using it?

An authenticated GitHub CLI with repo and workflow scopes (gh auth login, confirmed by gh auth status). The bundled inspect_pr_checks.py needs Python.

Source text

SKILL.md · Apache-2.0
---
name: openai-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. Originally from OpenAI's curated skills catalog.
allowed-tools:
- Bash
- Read
- Grep
- Glob
- Write
- Edit
---

# 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 "{baseDir}/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 "{baseDir}/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 "{baseDir}/scripts/inspect_pr_checks.py" --repo "." --pr "123"`
- `python "{baseDir}/scripts/inspect_pr_checks.py" --repo "." --pr "https://github.com/org/repo/pull/123" --json`
- `python "{baseDir}/scripts/inspect_pr_checks.py" --repo "." --max-lines 200 --context 40`

## When to Use

<!-- TODO: review -->

## When NOT to Use

<!-- TODO: review -->

© OpenAI · Apache-2.0 · trailofbits/skills-curated

Similar skills

All skills for Git and GitHub →

From the same set51

The whole set →
openai-yeet openai-yeet takes your changes from a dirty working tree to a draft pull request in one run through GitHub CLI. Handy when the whole chain has to happen at once. CX Codex +1 ★ 540repo stars openai-sentry The openai-sentry Claude Code skill reads Sentry issues and events through the API and summarizes production errors in a compact report. CX Codex +1 ★ 540repo stars python-code-simplifier python-code-simplifier refines recently modified Python code for clarity and maintainability without altering existing program logic or outputs. CX Codex ★ 540repo stars openai-playwright openai-playwright is a Claude Code skill that controls a real browser from the terminal. It runs for page navigation, form entry, data collection, screenshots, and UI debugging. CX Codex +1 ★ 540repo stars openai-jupyter-notebook openai-jupyter-notebook is a Claude Code skill that generates, structures, and edits clean Jupyter notebooks (.ipynb) for analytical experiments and step-by-step guides. CX Codex +1 ★ 540repo stars security-awareness The security-awareness skill guides an agent through phishing checks, domain verification, and safer handling of credentials. Use it when an agent works with email, links, or sensitive data. CX Codex +1 ★ 540repo stars openai-netlify-deploy openai-netlify-deploy — a Claude skill that runs a Netlify deploy end to end: sign-in check, site linking or creation, dependency install, then a preview or production release. CX Codex +1 ★ 540repo stars ffuf-web-fuzzing ffuf-web-fuzzing guides Claude Code through web fuzzing using ffuf during authorized penetration testing engagements. CX Codex +1 ★ 540repo stars

Project sponsors

Companies that keep this analytics open