Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Use when reviewing changes for regressions, correctness, security, and missing coverage. Generic — no stack assumptions. Stack context loaded from the project's .instructions.md at runtime.
Examines specified files, functions, or code sections to identify potential problems and opportunities for improvement.
Set up Cedar-enforced human approval gates for agent PR reviews, comments, merges, and CI configuration edits. Provides cryptographically auditable approval trails for these actions.
Coordinates two fresh agents to review the same committed branch diff in parallel. One uses codex review --base and the other follows Google's code review guidance; their findings are merged into an agreement-ranked report without applying fixes.
Reviews project code and performs refactoring guided by a defined set of instructions.
Reviews the current branch for bugs, alignment with intent, and test coverage. Runs or writes tests, commits focused work, and opens or updates a pull request.
Evaluates animation and motion code against a demanding craft standard derived from Emil Kowalski's philosophy. Defaults to flagging issues and requires evidence for approval.
Analyze vendor and customer agreements clause by clause against organizational negotiation positions. Flag deviations, generate redlines, assess business impact, and prioritize negotiation changes and fallback positions.
Reviews local working-tree changes using Git diffs and untracked files. Returns actionable improvement suggestions before committing or pushing.
Review code for logging patterns and suggest evlog adoption. Optionally use @evlog/cli (evlog init to wire evlog, evlog agents to write the conventions into AGENTS.md, evlog map to score entry-point coverage, --baseline to gate regressions in CI) on Nuxt, Nitro, Next.js, TanStack Start, and Hono. Guides setup on those plus SvelteKit, React Router, NestJS, Express, Fastify, Elysia, oRPC, Cl…
Runs a worker-reviewer cycle in which a critic subagent scores work from 1 to 10 and provides actionable feedback. Revises until a quality gate is met, supporting feature implementation, specification writing, and code review.
Analyze and respond to app reviews, including negative feedback. Helps address declining ratings and identify ways to obtain more reviews.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name