Skill Creator
技能 已验证 活跃Guide for creating effective skills
To guide developers in creating effective, well-structured, and maintainable Claude skills by providing best practices, examples, and a clear creation workflow.
功能
- Comprehensive guide to skill creation
- Demonstrates progressive disclosure pattern
- Provides examples of well-structured skills
- Includes utility scripts for packaging and validation
- Emphasizes imperative voice and structured content
使用场景
- When creating a new Claude skill from scratch
- When updating or refactoring existing skills
- When learning best practices for skill development
- When planning skill components like scripts and references
非目标
- Creating skills for non-Claude platforms
- Providing a direct execution environment for skills
- Automating the entire skill creation process without user input
工作流
- Understand skill with concrete examples
- Plan reusable components (scripts/references/assets)
- Initialize with init_skill.py
- Edit SKILL.md and resources
- Package and validate using package_skill.py
- Iterate based on usage and feedback
实践
- Skill development
- Documentation best practices
- Progressive disclosure
- Instructional design
先决条件
- Claude Code environment
- Basic understanding of LLM agent concepts
安装
npx skills add bobmatnyc/claude-mpm-skills通过 npx 运行 Vercel skills CLI(skills.sh)— 需要本地安装 Node.js,以及至少一个兼容 skills 的智能体(Claude Code、Cursor、Codex 等)。前提是仓库遵循 agentskills.io 格式。
质量评分
已验证类似扩展
Skill Template
99Template for creating new Agent Skills for context engineering. Use this template when adding new skills to the collection.
Claude Code Skill Builder
98Interactive skill creator for Claude Code and Agent Skills ecosystem. Build SKILL.md files with proper frontmatter, triggers, and structure. Triggers on creating skills, building skills, skill templates, skill frontmatter, allowed-tools, npx add-skill, agent skills.
Lean Ctx
100AI 代理的上下文运行时 — 包含 59 个 MCP 工具、10 种读取模式、95+ 种 shell 模式、支持 18 种语言的 tree-sitter AST。将 LLM 上下文压缩高达 99%。用于读取文件、运行 shell 命令、搜索代码或探索目录。如果不存在，则自动安装。
Manus
100Delegate complex, long-running tasks to Manus AI agent for autonomous execution. Use when user says 'use manus', 'delegate to manus', 'send to manus', 'have manus do', 'ask manus', 'check manus sessions', or when tasks require deep web research, market analysis, product comparisons, stock analysis, competitive research, document generation, data analysis, or multi-step workflows that benefit from autonomous agent execution with parallel processing.
风险管理
100交易代理的风险管理领域知识 — 情感状态监控、仓位调整、回撤管理、交易心态检测和行为控制。在交易前检查风险、管理回撤、检测行为漂移或强制执行纪律时使用。触发词包括“风险”、“回撤”、“心态”、“仓位大小”、“手数”、“信心”、“报复性交易”、“过度交易”、“纪律”。
Setup Gbrain
100Set up gbrain for this coding agent: install the CLI, initialize a local PGLite or Supabase brain, register MCP, capture per-remote trust policy. One command from zero to "gbrain is running, and this agent can call it." Use when: "setup gbrain", "connect gbrain", "start gbrain", "install gbrain", "configure gbrain for this machine". (gstack)