Investigate and fix failing GitHub Actions checks for this repo or its PRs. Use when the user asks to debug CI failures, broken workflows, failed release jobs, or failing GitHub checks.
67
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
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 workflow reads GitHub Actions metadata and workflow files, which may include outsider-authored contributions depending on the repository context, but specifically GitHub issue/PR reading or public feeds are not universally mandated as open outsider text feeds in this prompt definition.
03aad8c
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.