Agent skills
Skills you can use with AI coding agents, indexed from public GitHub repositories.
-
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
majiayu000/claude-skill-registry 163
-
variant-analysis
Find similar vulnerabilities across a codebase after discovering one instance. Uses pattern matching, AST search, Semgrep/CodeQL queries, and manual tracing to propagate findings. Adapted from Trail of Bits. Use after finding a bug to check if the same pattern exists elsewhere.
majiayu000/claude-skill-registry 163
-
shadcn-component-review
Review custom components and layouts against shadcn design patterns, theme styles (Maia, Vega, Lyra, Nova, Mira), component structure, composability, and Radix UI best practices. Use when planning new components, reviewing existing components, auditing spacing, checking component structure, or verifying shadcn best practices alignment.
majiayu000/claude-skill-registry 163
-
client-components
Enforces project client component conventions for interactive React components with hooks, event handlers, Radix UI integration, and server action consumption. Extends react-coding-conventions with client-specific patterns.
majiayu000/claude-skill-registry 163
-
create-pr
This skill should be used when user asks to "create a PR", "make a pull request", "open PR for this branch", "submit changes as PR", "push and create PR", or explicitly invokes "create-pr".
majiayu000/claude-skill-registry 163
-
tdd
Use when implementing any feature or fix outside code-forge workflow — enforces Red-Green-Refactor cycle with mandatory test-first discipline. For ad-hoc development, quick fixes, or any code change that is not tracked by code-forge:impl.
majiayu000/claude-skill-registry 163
-
ln-773-cors-configurator
Configures CORS policy for development and production environments. Use when setting up cross-origin access for APIs.
majiayu000/claude-skill-registry 163
-
anthropic-api
Anthropic Claude API for AI models with tool use and extended context.
majiayu000/claude-skill-registry 163
-
cirq
Google quantum computing framework. Use when targeting Google Quantum AI hardware, designing noise-aware circuits, or running quantum characterization experiments. Best for Google hardware, noise modeling, and low-level circuit design. For IBM hardware use qiskit; for quantum ML with autodiff use pennylane; for physics simulations use qutip.
majiayu000/claude-skill-registry 163
-
vite
Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.
majiayu000/claude-skill-registry 163
-
ux-sequence-diagram
[UI/UX] Visualizes interaction sequences and system communications as ASCII diagrams. Represents user-system interactions, API call sequences, and event flows. Use when requesting 'sequence diagram', 'interaction flow', or 'API sequence'.
majiayu000/claude-skill-registry 163
-
claw
Install the claw CLI tool — run NanoClaw agent containers from the command line without opening a chat app.
majiayu000/claude-skill-registry 163
-
l-thread
Long-duration autonomous task with checkpoints and verification. Use when:
- User says "overnight", "long running", "autonomous task"
- User mentions "l-thread", "extended task"
- Task will consume significant context window
- Multi-phase implementation requiring persistence across interruptions
majiayu000/claude-skill-registry 163
-
secrets-management
Implement secure secrets management for CI/CD pipelines using Vault, AWS Secrets Manager, or native platform solutions. Use when handling sensitive credentials, rotating secrets, or securing CI/CD environments.
majiayu000/claude-skill-registry 163
-
shadcn
Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".
majiayu000/claude-skill-registry 163
-
code-review-excellence
Master effective code review practices to provide constructive feedback, catch bugs early, and foster knowledge sharing while maintaining team morale. Use when reviewing pull requests, establishing review standards, or mentoring developers.
majiayu000/claude-skill-registry 163
-
neon-vercel-postgres
Set up serverless Postgres with Neon or Vercel Postgres for Cloudflare Workers/Edge. Includes connection pooling, git-like branching, and Drizzle ORM integration.
Use when: setting up edge Postgres, troubleshooting "TCP not supported", connection pool exhausted, SSL config errors, or Node v20 transaction issues.
majiayu000/claude-skill-registry 163
-
libpolicy
libpolicy - Policy engine for access control. PolicyIndex stores and evaluates authorization policies. createPolicyIndex factory loads policies from storage. Planned OPA-WASM integration for complex policy evaluation. Use for access control, authorization decisions, and resource permissions.
majiayu000/claude-skill-registry 163
-
unit-test-exception-handler
Provides patterns for unit testing @ExceptionHandler and @ControllerAdvice for global exception handling. Use when validating error response formatting and HTTP status codes.
majiayu000/claude-skill-registry 163
-
frontend-design
Create polished frontend interfaces from designs/screenshots/videos. Use for web components, 3D experiences, replicating UI designs, quick prototypes, immersive interfaces, avoiding AI slop.
majiayu000/claude-skill-registry 163
-
survey
Survey State of the Art (SOTA) literature for an Artificial Intelligence / Machine Learning (AI/ML) topic, method, or architecture. Finds relevant papers, builds a comparison table, and recommends the best implementation strategy for the current codebase. Delegates deep analysis to the ai-researcher agent.
majiayu000/claude-skill-registry 163
-
request-discord-approval
Request human approval for a critical operation via Discord MCP server. Posts a message with reaction buttons and uses await_reaction to wait for response. Use for destructive or irreversible operations. Keywords: approval, Discord, human-in-the-loop, confirmation, dangerous operation, reactions.
majiayu000/claude-skill-registry 163
-
youtube
Query YouTube — search videos, get channel stats, list playlists, and manage comments via the Data API v3.
majiayu000/claude-skill-registry 163
-
root-cause-analysis
Find the true source, not symptoms — systematic debugging from observation to permanent fix
majiayu000/claude-skill-registry 163