Takes a draft PR that its author approved to a human review. Add the CI label, mark it ready, fix what CI and Greptile find, then request the named reviewer.
85%
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 PR review threads and CI/Greptile feedback via handle-pr-comments and check-pr, and outsiders can post comments on a PR, so this is GitHub PR reading, which the medium rule covers.
storybookjs/storybook
7c89155
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.