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
/plugin marketplace add trailofbits/skills-curated
/plugin install openai-gh-fix-ci@skills-curatedWhat 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.pywith--jsonand 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-curatedThis 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-code3Manually: put the files in place
~/.claude/skills/openai-gh-fix-ci/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/openai-gh-fix-ci/
1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-gh-fix-ci -a codex2Manually: put the files in place
.agents/skills/openai-gh-fix-ci/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-gh-fix-ci -a cursor2Manually: put the files in place
.cursor/skills/openai-gh-fix-ci/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install trailofbits/skills-curated plugins/openai-gh-fix-ci/skills/openai-gh-fix-ci2Manually: put the files in place
.github/skills/openai-gh-fix-ci/SKILL.md1Skills CLI (Vercel)
npx skills add trailofbits/skills-curated --skill openai-gh-fix-ci -a gemini-cli2Platform CLI
gemini skills install https://github.com/trailofbits/skills-curated --path plugins/openai-gh-fix-ci/skills/openai-gh-fix-ciManually: put the files in place
.devin/skills/openai-gh-fix-ci/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
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