Gets a blind review of a diff or a PR from a model of another provider (Claude, GPT, Gemini), then checks and compares its findings. Use when the user asks for a second opinion, an adversarial review, or a review by another model.
88%
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 has the reviewer read a PR by URL or number and includes the PR body as the spec in the brief (SKILL.md:14, 21-22), so outsider-authored PR text reaches the agent without it selecting a specific comment.
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.