Use when a developer wants an e2e test covering a change they just made — e.g. "explore this feature", "add a test for my PR", "cover the feature in PR
75
94%
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 skill reads GitHub PR information and diffs using `gh pr view` or git commands, which can include outsider-authored descriptions and commit messages.
657e319
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.