按技能名称、说明或 GitHub 作者匹配的结果。
Set up and use MCP (Model Context Protocol) servers to extend Claude Code capabilities including PRISM semantic memory, filesystem access, and database integration. Use when setting up MCP servers, debugging MC...
Write effective prompts for Task tool sub-agents, slash commands, and system prompts. Covers Claude 4.x prompting patterns, context engineering, output format specification, and parallel delegation. Use when sp...
Multi-AI collaboration protocol using shared file editing. Use when major decisions require diverse AI perspectives (Claude, Grok, Gemini, etc.) to debate and reach consensus. AIs write directly to debate files...
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, workflows, or to...
Generate a recap of recent Claude Code sessions with summaries of what was discussed and accomplished
ONLY trigger this skill when the user EXPLICITLY asks for MCP-based testing: **Required triggers (ALL must mention "MCP" explicitly):** - "test connector with mcp" - "test mcp connector" - "test [provider] wit...
Project-specific architectural patterns and tribal knowledge. Copy this skill to your project's .claude/skills/ and customize with your team's conventions, decision trees, and critical pitfalls.
Manage Kai's task queue - capture topics to work on when Claude usage is available. Commands: - /kai-todo add - Add a new task to the queue - /kai-todo list - Show all queued tasks - /kai-todo next - Start wo...
Personal knowledge base integration via Obsidian vault. Provides semantic search, note retrieval, and context loading for Claude Code sessions. USE WHEN user says 'load context', 'search my notes', 'find in ob...
Real-time observability dashboard for multi-agent Claude Code sessions. Visualize agent interactions, tool usage, and session flows in real-time through a web dashboard. Track multiple agents running in parall...
Multi-source parallel research using Perplexity, Gemini, and Claude. Three modes - Quick (1 query), Standard (3 queries), Extensive (8 queries). USE WHEN user says 'research', 'investigate', 'find out about', '...
Create, optimize, and debug high-performing prompts for Claude 4 models and GLM 4.7 (Z.ai) with production-ready templates and evidence-based techniques. Use this skill when the user asks to create a prompt, wr...
Search Claude Collective Intelligence knowledge base for solutions to problems. Use when the user asks about common issues, wants to find existing solutions, or mentions "CCI", "collective intelligence", or "kn...
Create or update Claude Code skills. Use when user wants to create a new skill, update an existing skill, or needs guidance on skill design.
Act as a versatile professional, seamlessly switching between Document Custodian (Signer), Software Programmer, and UX/UI Designer based on the user's task. This skill enables Claude to manage and certify offic...
Create slash commands for Claude Code with proper frontmatter, arguments, and bash execution. WHEN: MUST use when creating new slash commands. Invoke with "/claude-command-development" or "create a command", "n...
Best practices for developing Claude Code skills with progressive disclosure and proper organization. WHEN: MUST use when improving existing skills. Invoke with "/claude-skill-development" or "improve skill", "...
Create event-driven hooks for Claude Code plugins (PreToolUse, PostToolUse, Stop, SessionStart, etc.). WHEN: MUST use when creating Claude Code hooks. Invoke with "/claude-hook-development" or "create a hook",...
Create and structure Claude Code skills with proper SKILL.md format, frontmatter, and progressive disclosure. WHEN: MUST use when creating new skills. Invoke with "/claude-skill-creator" or "create a skill", "n...
Create and configure Claude Code agents with proper frontmatter, system prompts, and triggering conditions. WHEN: MUST use when creating new Claude Code agents. Invoke with "/claude-agent-creator" or "create an...
Write hookify rules for pattern-based hook triggers in Claude Code. WHEN: MUST use for creating hookify rules. Invoke with "/claude-hookify-rules" or "create hookify rule", "pattern-based hook". WHEN NOT: Creat...
创建、更新和优化 CLAUDE.md 配置文件。当用户请求初始化 CLAUDE.md、改进项目配置、添加编码规范、或询问"如何让 Claude 记住这个设置"时触发。
Patterns for building Claude Code plugins including commands, agents, hooks, MCP servers, and plugin marketplaces. Use when creating extensions for Claude Code or distributing plugins to teams.
Guides creation of Anthropic-compliant Claude skills. Triggers on: create skill, new skill, skill guidelines, skill best practices, write a skill.
默认按已收录数据中的 GitHub 仓库 Stars 排序。Stars 属于来源仓库，同一仓库的多个技能可能共享相同数值；它反映仓库关注度，不代表单个技能的安装量或质量评分。