Design multi-agent architectures for complex tasks. Use when single-agent context limits are exceeded, when tasks decompose naturally into subtasks, or when specializing agents improves quality.

|

|

>

Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.

Process and analyze CSV, JSON, and text files with data transformation, cleaning, analysis, and visualization capabilities

抖音无水印视频下载和文案提取工具. 从抖音分享链接获取无水印视频下载链接, 下载视频, 提取视频中的语音文案并自动保存到文件. 适用场景包括获取抖音视频信息, 下载无水印视频, 批量提取视频文案. 当用户需要处理抖音视频链接或提取视频内容时触发.

|

|

Guide for creating and improving effective skills. This skill should be used when users want to create, update, or improve skills that extend Claude's capabilities with specialized knowledge,...

Create, validate, and maintain Claude Code Agent Skills. Use when the user wants to add a skill, create a skill, make a skill, build a skill, or mentions skill creation. Also use when improving...

安裝 Agent Skills 到本機。當用戶想要「安裝技能」、「新增 skill」、「從 GitHub 安裝 skill」、或「install skill from repo」時觸發此技能。

安裝 Agent Skills 到本機。當用戶想要「安裝技能」、「新增 skill」、「從 GitHub 安裝 skill」、或「install skill from repo」時觸發此技能。

Generate, evaluate, and iterate on agent skills using HuggingFace's Upskill tool. Transfer domain expertise from frontier models to smaller/local models.

|

Create or augment technical documentation. Use when writing new skills, updating existing skills. Also use when modifying project documentation like AGENTS.md.

Generate MANIFEST.json files for Agent Skills, providing content integrity verification, file inventory, and external reference tracking.

Boilerplate templates for Claude Code extensions. Triggers on: create agent, new skill, command template, hook script, extension scaffold.

|

Generates SKILL.md files for npm packages following Anthropic's Agent Skills specification. Use when adding agent documentation to an npm package, making a package AI-agent friendly, or creating...