Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
178 skills
Jakub Krehel· Community
An autonomous workflow that improves a project by identifying, building, and reporting on user-focused enhancements while you are away.
Jakub Krehel· Community
Review interface changes for accessibility, layout, and UI regressions within a specific git scope.
Jakub Krehel· Community
A comprehensive guide for applying precise visual polish to UI surfaces, icons, and motion.
Jakub Krehel· Community
A comprehensive guide for setting, reviewing, and standardizing typography in digital interfaces.
Julien Thibeaut (ibelick)· Community
Audit product interfaces against design evidence and generate implementation plans for UI improvements.
Julien Thibeaut (ibelick)· Community
A systematic guide for auditing and correcting HTML metadata, SEO tags, and structured data.
Trail of BitsOfficial
An autonomous loop that iteratively reviews and fixes code until quality standards are met.
Trail of BitsOfficial
Generates an interactive HTML walkthrough for code reviews by grouping changes into logical steps with explanations and findings.
Trail of BitsOfficial
Automated triage for GitHub repositories, including PR merging, issue resolution tracking, and local-only backlog grooming.
Trail of BitsOfficial
Automated compliance checking between technical documentation and source code implementation.
Trail of BitsOfficial
Automated iterative review-and-fix loop for pull requests.
Trail of BitsOfficial
Provides a rapid structural overview of a codebase by identifying languages, entry points, and dependencies.
Trail of BitsOfficial
Provides independent code reviews for uncommitted changes, branch diffs, and commits using Codex or Antigravity.
Trail of BitsOfficial
A workflow for delegating focused code analysis tasks to subagents using graph-informed source slices.
OpenAIOfficial
A rigorous framework for processing code review feedback with technical verification and objective communication.
OpenAIOfficial
Evaluate a local Codex plugin in engineer-friendly language. Use when the user says "evaluate this plugin", "audit this plugin", "why did this score that way", "what should I fix first", "help me benchmark this plugin", or asks for a plugin-wide report before comparing versions.
OpenAIOfficial
Run a pre-submission compliance check against your Shopify app's codebase. Reviews App Store requirements and surfaces likely issues before you submit for official review.
OpenAIOfficial
React best-practices reviewer for TSX files. Triggers after editing multiple TSX components to run a condensed quality checklist covering component structure, hooks usage, accessibility, performance, and TypeScript patterns.
OpenAIOfficial
Assess an immutable patch artifact's program impact, regression risk, and auto-merge eligibility. Use for generated patch files, provider pull-request diffs, or commit ranges when reviewers need evidence about affected runtime paths, contracts, tests, and recoverability. This skill is read-only and does not generate, edit, apply, push, or merge the patch.
OpenAIOfficial
Reviews and authors Cloudflare Workers code against production best practices. Load when writing new Workers, reviewing Worker code, configuring wrangler.jsonc, or checking for common Workers anti-patterns (streaming, floating promises, global state, secrets, bindings, observability). Biases towards retrieval from Cloudflare docs over pre-trained knowledge.
OpenAIOfficial
Inspect macOS signing, entitlements, and Gatekeeper issues. Use when diagnosing code signing, sandbox, hardened runtime, or trust failures.
OpenAIOfficial
Reviews code changes using CodeRabbit AI. Use when user asks for code review, PR feedback, code quality checks, security issues, or requests fix-review cycles.
Meng To· Community
Audit digital experiences against source references to identify originality risks and plagiarism.
Meng To· Community
A systematic approach to auditing work, verifying claims with evidence, and explaining findings in simple, accessible language.