$ loading_
Debug failing GitHub Actions PR checks, analyze logs, propose fixes, then implement with approval.
This skill is essentially an open-source prompt/workflow guide with relatively strong source credibility and an overall low risk profile. The main consideration is that its workflow relies on local GitHub CLI authentication and accesses GitHub repository and Actions log data, but the materials do not show exfiltration to unknown third parties or unusual privilege requests.
Although the metadata says no environment variables or keys are required, the README explicitly requires GitHub CLI authentication via `gh auth login`, typically with repo and workflow scopes. This means it uses local GitHub credentials and carries normal token-scope and misuse exposure, but there is no sign of extra third-party secrets being requested or obvious credential theft behavior.
The workflow uses `gh`/`gh api` to access GitHub repositories, PRs, checks, and Actions logs, which is normal network communication directly tied to the stated purpose. The documentation also explicitly treats Buildkite and other external providers as out of scope and only reports the details URL, with no red flags indicating exfiltration to unknown or unrelated endpoints.
The objective checks indicate this is prompt-only. The materials include instructions to run `gh` and a Python script, but the skill itself appears to be a review/fix workflow guide rather than a bundled opaque binary or hidden execution mechanism. Based on the available materials, there are no red flags of local code execution beyond its stated purpose.
Per the documented workflow, it reads the current repository, PR information, check results, and GitHub Actions logs, and may implement fixes after approval. This access scope is consistent with diagnosing CI failures, with no indication of broad system-level file permissions or unrelated data sources, though logs and repository content may still contain sensitive information.
The source is the open-source `openai/skills` repository on GitHub with strong community adoption (about 22k stars), both of which are meaningful risk-reducing signals. The missing license declaration and unknown maintenance status are worth noting, but absent signs of closed-source exfiltration, suspicious install scripts, or provenance issues, the supply-chain profile remains low risk overall.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "gh-fix-ci" skill from askskill: 1. Download https://raw.githubusercontent.com/openai/skills/main/skills/.curated/gh-fix-ci/SKILL.md 2. Save it as ~/.claude/skills/gh-fix-ci/SKILL.md 3. Reload skills and tell me it's ready
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.
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).
repo: path inside the repo (default .)pr: PR number or URL (optional; defaults to current branch PR)gh authentication for the repo hostpython "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"--json if you want machine-friendly output for summarization.gh auth status in the repo.gh auth login (ensuring repo + workflow scopes) before proceeding.gh pr view --json number,url.python "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --pr "<number-or-url>"--json for machine-friendly output.gh pr checks <pr> --json name,state,bucket,link,startedAt,completedAt,workflow
gh.detailsUrl and run:
gh run view <run_id> --json name,workflowName,conclusion,status,url,event,headBranch,headShagh run view <run_id> --loggh api "/repos/<owner>/<repo>/actions/jobs/<job_id>/logs" > "<path>"detailsUrl is not a GitHub Actions run, label it as external and only report the URL.create-plan skill to draft a concise plan and request approval.gh pr checks to confirm.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" --jsonpython "<path-to-skill>/scripts/inspect_pr_checks.py" --repo "." --max-lines 200 --context 40Capture full-screen, window, or region screenshots at the operating system level.
Analyze a codebase for threats, abuse paths, and mitigations in Markdown.
Interact with persistent browsers and Electron apps for fast iterative UI debugging.
Migrate instruction files, skills, agents, and MCP configs into Codex files.
Build, scaffold, refactor, and troubleshoot ChatGPT Apps SDK applications.
Build, review, refactor, and architect modern ASP.NET Core web applications.
Investigate failed PR checks and iteratively fix CI issues faster.
Address review and issue comments on the current branch's GitHub PR with gh CLI.
Check for and install GitHub CLI to prepare a development environment.
Review GitHub pull requests in ChatGPT with comments, approvals, and change requests.
Manage issues, PRs, logs, releases, and repos with GitHub CLI.
Check CI readiness before pushing by catching common formatting and policy issues.