Investigate and fix CI failures on a pull request. Use when CI checks fail on a PR branch — covers finding the PR, identifying failed checks, downloading logs and artifacts, extracting the failure cause, and iterating on a fix. Requires the `gh` CLI.
92%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required workflow reads GitHub Actions job logs and PR metadata (`gh run view --log-failed`, `gh api .../jobs/<JOB_ID>/logs`, and artifact downloads) that contain output from test code, which an outsider can influence by submitting a PR or contributing to a PR branch, and the agent reads this without choosing a specific outsider-authored item.
microsoft/vscode
278203b
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.