В каталоге 183 730 навыков в 14 категориях.
Use when optimizing MCP token usage, understanding Tool Search thresholds, or deciding MCP vs skills for token efficienc...
Use when adding allow/deny rules to Claude Code, granting project permissions, troubleshooting "permission denied" error...
This skill should be used when sending images, files, or notifications back to the user via messaging platforms (Discord...
Verify construction prerequisites using 66-item checklists across requirements, architecture, and coding conventions. Ou...
Review control flow quality using 87-item checklist. Use when code has deep nesting (3+ levels), complex conditionals, l...
Comprehensive Claude Code conversation analysis skill for deep-diving into CC session logs.Use when analyzing exported C...
通用防御性编码规范，适用于跨语言代码修改中的最小改动、真实边界处理、定向验证，以及约束假想风险驱动的过度兜底或抽象；不负责语言细节、正式 review 或结构化 debug。
AI Agent 成本工程 — 基於 Claude Code 的成本追蹤、prompt cache 最佳化、token 預算控制逆向分析。Use when: 優化 token 消耗、設計成本控制機制、分析 cache 效率、選擇模型配置。
Use when C++ module/header boundaries, resource lifetime, exception safety, ABI, build-standard conventions or project-w...
Use when scheduling autonomous in-session flywheel ticks with Claude Code cron routines. Triggers:
Cursor PMでアイデアを検証し、Plans.mdを更新してバトンタッチ。2-Agentワークフロー対応。
Validate brainstorm with Cursor PM, update Plans.md, handoff back. Cursor↔CC 2-agent workflow. Triggers: Cursor PM hando...
Audit and fix data organization: variable declarations, data types, magic numbers, naming conventions, and global data....
Use when diagnosing unexplained engineering failures, build errors, service exceptions, inconsistent data, or cross-laye...
Guide systematic debugging using scientific method: STABILIZE -> HYPOTHESIZE -> EXPERIMENT -> FIX -> TEST -> SEARCH. Two...
Review error handling, input validation, and exception patterns using 24-item checklist. Use when auditing defensive cod...
Designs Claude Code prompts and CC environments. Produces CLAUDE.md drafts, agent topologies, scope-authorization framew...
High-fidelity HTML design and prototype guidance for AI agents with structured design thinking and quality guardrails
Enforce developer discipline under pressure by detecting rationalization patterns and providing counter-arguments. Use w...
This skill should be used when starting any feature or bug fix, exploring unfamiliar code, making commits or PRs, or whe...
Use when project documentation, multilingual READMEs, setup instructions, CLI usage, or public capability descriptions d...
Read Claude Code documentation to learn about features, capabilities, hooks, skills, MCP, subagents, and how to use Clau...
Review documentation quality across README, comments, API docs, changelog, and AI documentation (CLAUDE.md, .cursorrules...
Use when creating editable technical diagrams with draw.io / diagrams.net sources, including architecture diagrams, ERD,...
Use when an Electron application needs work on main/preload/renderer boundaries, contextBridge IPC, sender validation, s...
Generate a Figma component set from a component contract. Use when the user wants to build or update a Figma component f...
Build or update Figma variable collections (Primitives and Semantic) from component-contracts token files. Use when the...
结构化 bug 修复工作流，适用于显式 fix 或 debug 场景；不负责语言规范、正式 review 或运维审批。
前端开发规范，包含 Vue 3 编码规范、UI 风格约束、TypeScript 规范等
Use when Go goroutine leaks, channel ownership, cancellation propagation, synchronization, worker bounds or race conditi...
Go 开发规范，适用于 Go 源码、包结构、错误处理、并发和测试相关任务；不负责 review、debug 或运维流程。
Use when Go module/workspace organization, package ownership, error and context conventions, dependency boundaries or en...
Harness Engineering 設計模式 — 基於 Claude Code 原始碼逆向分析的 12 條可遷移原則。Use when: 設計 agent 系統架構、實作 tool orchestration、設計 context 管理...
Configure Claude Code hooks for PreToolUse, PostToolUse, Stop, Notification. Use when blocking commands, auto-formatting...
This skill should be used when users want to create, configure, or debug Claude Code hooks. Hooks are shell commands tha...
TypeScriptで型安全なClaude Code Hooksを作成するためのガイド。cc-hooks-tsライブラリを使用してフックを実装する際に使用する。(1) Claude Code用の新しいhookを作成する時、(2) 既存のho...
Use PROACTIVELY when searching past Claude Code conversations, analyzing development patterns, or generating activity re...
Audit integration strategy and daily build processes (CHECKER) or select optimal integration approach and configure CI/C...
How Claude Code works internally. Use for ANY question about CC behavior, architecture, or "how does CC do X". Covers se...
Java 开发规范，包含命名约定、异常处理、Spring Boot 最佳实践等
Use when Java package/module structure, build-tool conventions, application boundaries, exceptions, persistence ownershi...
Use when Java thread pools, JVM memory/GC, JFR or thread-dump evidence, blocking contention or runtime latency need diag...
Interact with Linear task management via cc alias — spawns a one-shot Claude Code session with Linear MCP connected.
Iterative quality loop for any content deliverable. Runs fixer → polish → N parallel critiques → score → loop until pass...
Use when running a Claude-native control-plane tick loop with worker and separate-validator subagents. Triggers:
Use when working with Claude Code plugin marketplaces - adding, updating, creating, or understanding how marketplace ver...
GitHub repository skill for mcfearsome/cc-mcp-executor-skill
Use when C/C++ leaks, use-after-free, double release, bounds errors, allocator mismatch, FFI ownership or teardown races...
结构化新功能交付工作流，适用于显式 new feature、从需求到实现的一站式功能开发或恢复未完成任务场景；通过项目内 .codex/tasks/ 持久化状态。
Write a newsletter issue built around one core idea, with a subject line, tight structure, and a single CTA.
Shell、服务、容器、数据库、部署或环境敏感操作的安全规范，适用于风险说明、回滚思路和影响面控制；不负责语言细节。
Comprehensive overview of Claude Code features, architecture, and capabilities. Learn about hooks, skills, commands, per...
Enforce measure-first discipline for code optimization using a 7-step gated decision tree and 40-item checklist. Use whe...
Comprehensive Claude Code plugin development expert providing guidance for creation, maintenance, installation, configur...
This skill should be used when the user asks to "install a plugin", "extend a plugin", "create a .local.md file", "add p...
Comprehensive toolkit for detecting and eliminating "AI slop" - generic, low-quality AI-generated patterns in natural la...
Automatically discover API design skills when working with REST APIs, GraphQL schemas, API authentication, OAuth, JWT, r...
Automatically discover build system skills when working with build systems. Activates for build-systems development task...
Automatically discover caching and performance skills when working with caching. Activates for caching development tasks...
Automatically discover CI/CD and automation skills when working with CI/CD. Activates for cicd development tasks.
Automatically discover cloud computing and serverless skills when working with cloud. Activates for cloud development ta...
Automatically discover collaboration and teamwork skills when working with collaboration. Activates for collaboration de...
Automatically discover container and Docker skills when working with Docker. Activates for containers development tasks.
Automatically discover cryptography skills when working with encryption, TLS, certificates, PKI, and security
Automatically discover data pipeline and ETL skills when working with ETL. Activates for data development tasks.
Automatically discover database skills when working with SQL, PostgreSQL, MongoDB, Redis, database schema design, query...
Automatically discover debugging and profiling skills when working with debugging. Activates for debugging development t...
Automatically discover deployment and release skills when working with deployment. Activates for deployment development...
Automatically discover diagram and visualization skills when working with flowcharts, sequence diagrams, architecture di...
Automatically discover distributed systems skills when working with consensus, CRDTs, replication, partitioning, and dis...
Automatically discover eBPF and kernel skills when working with eBPF. Activates for ebpf development tasks.
Automatically discover software engineering practice skills when working with engineering practices. Activates for engin...
Automatically discover formal methods and verification skills when working with formal methods. Activates for formal dev...
Automatically discover frontend development skills when working with React, Next.js, UI components, state management, da...
Automatically discover infrastructure and DevOps skills when working with infrastructure. Activates for infrastructure d...
Automatically discover intermediate representation and compiler skills when working with intermediate representation. Ac...
Automatically discover mathematics and algorithm skills when working with mathematics. Activates for math development ta...
Automatically discover machine learning and AI skills when working with machine learning. Activates for ml development t...
Automatically discover mobile development skills when working with iOS. Activates for mobile development tasks.
Automatically discover Modal platform skills when working with Modal. Activates for modal development tasks.
Automatically discover networking and connectivity skills when working with networking. Activates for networking develop...
Automatically discover observability and monitoring skills when working with monitoring. Activates for observability dev...
Automatically discover programming language theory skills when working with compilers. Activates for plt development tas...
Automatically discover product management skills when working with product management. Activates for product development...
Automatically discover protocol skills when working with HTTP, TCP, UDP, QUIC, and network protocols
Automatically discover proxy skills when working with forward/reverse proxies, nginx, traefik, envoy, caching, or NATS m...
Automatically discover realtime communication skills when working with realtime. Activates for realtime development task...
Gateway skill for research methodology - automatically loads relevant research skills based on task context
Automatically discover security skills when working with authentication, authorization, input validation, security heade...
Automatically discover testing skills when working with testing. Activates for testing development tasks.
Automatically discover terminal UI skills when working with terminal user interfaces. Activates for tui development task...
Automatically discover WebAssembly skills when working with WebAssembly. Activates for wasm development tasks.
Automatically discover workflow and task management skills when working with Beads. Activates for workflow development t...
Automatically discover Zig programming skills when working with Zig. Activates for zig development tasks.
Create world-class, accessible, responsive interfaces with sophisticated interactive elements including chat, terminals,...
Refactor codebases using Design by Typed Holes methodology - iterative, test-driven refactoring with formal hole resolut...
System Prompt 工程 — 基於 Claude Code 914 行系統提示詞的逆向分析。Use when: 撰寫 system prompt、設計 prompt 動態組裝、最佳化 prompt cache 效率、撰寫安全指令。
Guide routine design using the Pseudocode Programming Process (PPP). Produce pseudocode design, header comments, and imp...
Use when Python event-loop blocking, task cancellation, async resource cleanup, bounded concurrency or thread offloading...
Python 开发规范，适用于类型注解、验证模型、pytest 和 uv 工具链；不负责 review、debug 或运维流程。