基于直觉（Instinct）的学习系统，通过钩子（Hooks）观测会话，创建带有置信度评分（Confidence Scoring）的原子直觉，并将其演进为技能（Skills）、命令（Commands）或智能体（Agents）。

Intelligent skill router and creator. Analyzes ANY input to recommend existing skills, improve them, or create new ones. Uses deep iterative analysis with 11 thinking models, regression...

结构化AI提示词写作工具，内置395+提示词模板。支持详细模式和简单模式。用于创建专业的AI角色提示词、系统提示词或任务提示词。当用户需要：(1) 创建新的AI提示词/Prompt (2) 设计AI角色/Persona (3) 编写系统提示词 (4) 优化现有提示词结构时使用此技能。

Generates git patch files from codebase modifications for local application. Use when user mentions patch, diff, export changes, bring changes back, apply locally, or after editing uploaded codebases.

Reduces token usage from paid providers by offloading work to local LM Studio models. Use when: (1) Cutting costs—use local models for summarization, extraction, classification, rewriting,...

Plan and coordinate multi-agent bead execution. Use when starting a new epic, assigning tracks to agents, or monitoring parallel work progress.

|

Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task...

21 production-ready scripts for iOS app testing, building, and automation. Provides semantic UI navigation, build automation, accessibility testing, and simulator lifecycle management. Optimized...

GitHub repository access in containerized environments using REST API and credential detection. Use when git clone fails, or when accessing private repos/writing files via API.

Detect and fix AI-generated writing patterns (slop). Comprehensive detection with 35+ patterns, tiered severity scoring, and editor mode.

Transform markdown/HTML into styled 3:4 ratio images for Xiaohongshu

Manage Linear issues, projects, and teams

Claude Code 프로젝트의 에이전트와 스킬 관계를 D3.js 노드 그래프로 시각화합니다. 에이전트-스킬 의존성을 파악하고 구조를 탐색할 때 사용하세요.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge,...

Analyzes your Claude Code conversation history to identify patterns, common mistakes, and opportunities for workflow improvement. Use when user wants to understand usage patterns, optimize...

Parallelizes codebase exploration and research by launching multiple subagents simultaneously. Use when exploring codebases, researching questions, investigating bugs, gathering context from...

Build static websites using Metalsmith's component-based architecture. Triggers on phrases like "build me a website", "create a landing page", "help me make a site", or when working with...

Use when user needs capabilities Claude lacks (image generation, real-time X/Twitter data) or explicitly requests external models ("blockrun", "use grok", "use gpt", "dall-e", "deepseek"). For...

建议在逻辑间隔进行手动上下文压缩（Context Compaction），以便在任务阶段中保留上下文，而不是依赖随机的自动压缩。