
When a GitHub PR's CI checks blow up, this skill automates the tedious dance of running gh commands to figure out what failed and why. It pulls GitHub Actions logs, extracts the relevant failure snippet, then uses the plan skill to draft a fix and waits for your approval before implementing. The bundled Python script handles the common annoyances like field drift in gh's JSON output and jobs that are still running. It explicitly scopes out external CI like Buildkite rather than pretending it can handle everything. Honest take: this is the kind of automation that saves you from scrolling through 3,000 line logs in the GitHub UI at 11pm when a test flakes.
$ npx -y skills add davila7/claude-code-templates --skill gh-fix-ci --agent claude-codeInstalls into .claude/skills of the current project.
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.
plan skill for drafting and approving the fix plan.Prereq: ensure gh is authenticated (for example, run gh auth login once), then run gh auth status with escalated permissions (include workflow/repo scopes) so gh commands succeed. If sandboxing blocks gh auth status, rerun it with sandbox_permissions=require_escalated.
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.Sponsors