Browse 138,453 skills across 70 categories. Mirrored from majiayu000/claude-skill-registry.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
Frontend development guidelines for React/TypeScript applications. Modern patterns including Suspense, lazy loading, use...
{{- / Single page template for Claude skill output / -}}
PowerPoint processing. USE WHEN pptx, PowerPoint, slides. SkillSearch('pptx') for docs.
Purpose: Add workflows or modify an existing skill while maintaining canonical structure and TitleCase naming.
Interactive Archon integration for knowledge base and project management via REST API. On first use, asks for Archon hos...
This skill should be used when the user wants to "create a skill", "add a skill to plugin", "write a new skill", "improv...
Step-by-step tutorial for adding new CUDA kernels to FlashInfer
Guide for benchmarking FlashInfer kernels with CUPTI timing
Tutorial for debugging CUDA crashes using API logging
Discover codebase patterns, conventions, and unwritten rules before making changes. Use when implementing features, fixi...
|
Design patterns for the Langroid multi-agent LLM framework. Covers
Human-readable control flow patterns for refactoring complex conditionals. Use when refactoring nested conditionals, imp...
Apply factory function patterns to compose clients and services with proper separation of concerns. Use when creating fu...
Behavioral guideline for providing brutally honest feedback. Use always - this skill defines core interaction expectatio...
Monorepo script commands and conventions for this codebase. Use when running builds, tests, formatting, linting, or type...
Rust to TypeScript error handling patterns for Tauri apps. Use when defining Rust errors that will be passed to TypeScri...
TypeScript code style, type co-location, constant naming conventions, and arktype patterns. Use when writing TypeScript...
This skill should be used when developing, debugging, or maintaining Positron Notebooks - the React-based feature-flagge...
Comprehensive code review for GitHub pull requests using parallel agents. Checks bugs, CLAUDE.md compliance, git history...
Build and run LLM-powered data processing pipelines with DocETL. Use when users say "docetl", want to analyze unstructur...
>
Use when you have a plan file ready and need to create an isolated git worktree for implementation - creates worktree in...
Evaluate Clojure code via nREPL using clj-nrepl-eval.
You are analyzing a Java thread dump to identify deadlocks, performance issues, and thread contention.
Best practices for creating ISPC lit tests. Use when writing regression tests, verifying code generation, or checking co...
Process 流水线核心模块架构总览，涵盖流水线 CRUD、构建执行引擎、事件驱动机制、分层架构设计。当用户开发流水线核心功能、理解 Process 模块、修改构建逻辑或进行流水线相关开发时使用。
YAML 流水线转换指南，涵盖 YAML 与 Model 双向转换、PAC（Pipeline as Code）实现、模板引用、触发器配置。当用户需要解析 YAML 流水线、实现 PAC 模式、处理流水线模板或进行 YAML 语法校验时使用。
Create a new Agent Skill for this codebase
Research libraries, APIs, and patterns using searchGitHub and Exa tools. Finds real-world implementations and saves stru...
Review code using Linus Torvalds' "good taste" philosophy. Eliminates defensive code, special cases, and deep nesting. U...
Orientation to facet-format JIT deserialization (tiering, fallbacks, key types/entry points) and where to look when chan...
Systematic workflow for debugging by reproducing bugs with real data, reducing test cases to minimal examples, and addin...
Deep analysis and investigation
Run a comprehensive code review
Diagnose and fix oh-my-claudecode installation issues
Parallel autopilot with file ownership partitioning
Build an iPlug2 plugin project for different formats and platforms using xcodebuild or Visual Studio
Create a new iPlug2 plugin project by duplicating an example template
Validate iPlug2 plugin builds using format-specific validators (auval, pluginval, vstvalidator, clap-validator) (project...
Validate changesets in openai-agents-js using LLM judgment against git diffs (including uncommitted local changes). Use...
Run the mandatory verification stack when changes affect runtime code, tests, or build/test behavior in the OpenAI Agent...
Perform a release-readiness review by locating the previous release tag from remote tags and auditing the diff (e.g., v1...
Keep pnpm current: run pnpm self-update/corepack prepare, align packageManager in package.json, and bump pnpm/action-set...
Create a PR title and draft description after substantive code changes are finished. Trigger when wrapping up a moderate...
Skill 是 Claude Code CLI 的插件/技能系统，允许开发者扩展 AI 助手的能力。每个 Skill 是一个独立的 npm 包，可以添加特定的功能、工作流或集成。
Evaluate research rigor. Assess methodology, experimental design, statistical validity, biases, confounding, evidence qu...
Iterative root-cause + fix agent workflow that gathers evidence (code/logs/tests/web), verifies the primary ROOT_CAUSE c...
Execute codeagent-wrapper for multi-backend AI code tasks. Supports Codex, Claude, and Gemini backends with file referen...
Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code...
Execute Gemini CLI for AI-powered code analysis and generation. Use when you need to leverage Google's Gemini models for...
Analyze PR diffs and generate review comments from code quality, security, and performance perspectives. Use for code re...
In-depth code review for large PRs (>500 lines). Full analysis including architecture, performance, security, and mainta...
Standard code review for medium PRs (100-500 lines). Includes code quality, security basics, and test coverage analysis.
Quick code review for small PRs (<100 lines). Focuses on basic code quality, naming conventions, and obvious bugs.
- https://github.com/arpitjindal97/technologybooks --编程语言晋级。Premium eBook free for Geeks
This skill should be used when the user asks to "create a math animation", "animate a mathematical concept", "generate M...
Prerequisites: Load plugins/context/capabilities/eventsskills.md first
HASH error handling patterns using error-stack crate. Use when working with Result types, Report types, defining custom...
Set up and use 1Password CLI (op). Use when installing the CLI, enabling desktop app integration, signing in (single or...
AST-based code search and refactoring via ast-grep MCP
Analyze Claude Code sessions via Braintrust
Transform session learnings into permanent capabilities (skills, rules, agents). Use when asked to "improve setup", "lea...
Systematic hook debugging workflow. Use when hooks aren't firing, producing wrong output, or behaving unexpectedly.
Search GitHub code, repositories, issues, and PRs via MCP
Complete Claude Code hooks reference - input/output schemas, registration, testing patterns
Fast file editing via Morph Apply API (10,500 tokens/sec, 98% accuracy)
Fast codebase search via WarpGrep (20x faster than grep)
Analyze brownfield codebase and create initial continuity ledger
Code quality checks, formatting, and metrics via qlty CLI
Use RepoPrompt CLI for token-efficient codebase exploration
Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure...
Browser automation, debugging, and performance analysis using Puppeteer CLI scripts. Use for automating browsers, taking...
Master context engineering for AI agent systems. Use when designing agent architectures, debugging context failures, opt...
Process multimedia files with FFmpeg (video/audio encoding, conversion, streaming, filtering, hardware acceleration) and...
Build Shopify applications, extensions, and themes using GraphQL/REST APIs, Shopify CLI, Polaris UI components, and Liqu...
Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborep...
Hundreds of Claude Code plugins with embedded AI skills. Learn via interactive Jupyter tutorials.
DART build system knowledge - CMake, pixi, dependencies, troubleshooting