dev-swarm-create-update-agent-skill
Create or update agent skills following the agent skill specification. Use when user asks to create a new skill or update an existing skill.
发现 documentation llm ai 相关 Skills,比较来源仓库和用途,查看适合你工作流的技能说明。
Create or update agent skills following the agent skill specification. Use when user asks to create a new skill or update an existing skill.
Review and refine MCP skill descriptions to follow the agent skill specification, and record approved overrides in dev-swarm/mcp_descriptions.yaml. Use when the user asks to update one MCP skill description, al...
Add and manage Model Context Protocol (MCP) servers for AI agents, including transports, scopes, and config files. Use when extending agent capabilities with new tools or data sources.
Install AI code agent CLI tools including claude-code, gemini-cli, codex, and github copilot-cli. Use when setting up AI coding assistants or when the user asks to install an AI code agent.
Create custom slash commands for popular AI agents (Claude Code, Codex, Gemini CLI). Use when user asks to create slash commands, custom commands, or reusable prompts for AI agent CLIs.
Create and maintain AgentV YAML evaluation files for testing AI agent performance. Use this skill when creating new eval files, adding eval cases, or configuring custom evaluators (code validators or LLM judges...
Call LLM via CLI for transcription, vision, speech/image generation, piping prompts, sub-agents, ...
Text manipulation and documentation engine. PRIMARY TOOL FOR TEXT EDITING. Use this skill for ALL text replacement, documentation updates, and file rewriting tasks. SUPERIOR to 'grep' or 'sed' because it unders...
Project Cortex - Structural Knowledge Injection for LLM
The Hippocampus Interface - Vector-based Memory for LLM (LanceDB + FastEmbed)
Employee agent lifecycle management system. Use when working with agents/ directory employee agents - starting, stopping, monitoring, or assigning tasks to Dev/QA agents running in tmux sessions. Completely ind...
Gera agents experts especializados em areas especificas da codebase. Use quando precisar criar um novo agent expert com knowledge base, sub-comandos e integracao com a codebase.
Gera skills e comandos personalizados para Claude Code. Use quando precisar criar novas capacidades, templates de comandos, ou estrutura de skills. Inclui templates para skills simples, multi-arquivo, e com res...
AFK (Away From Keyboard) mode - enable tiered modes, check status, review sessions. Use /afk [operation] where operation is full|plan|research|monitor|off|status|review
技能创建指南。当用户需要创建新技能(Skill)或更新现有技能时使用此技能。帮助扩展 Claude 在特定领域的专业能力。
MCP(Model Context Protocol)服务器开发指南。当用户需要开发 MCP 服务器、创建 LLM 工具集成、或构建 AI 代理与外部服务交互的接口时使用。
Generate or refactor AGENTS.md files following progressive disclosure principles for optimal context efficiency.
LLM working files and session context management. Use at the start of sessions to restore context, and during work to maintain state across conversations.
Deep Agents library for building complex, multi-step AI agents with planning, context management, and subagent delegation.
Git commands optimized for AI agent workflows with porcelain output and deterministic execution patterns.
Convert text to Google Chat compatible formatting (Markdown to Google Chat syntax). Use when formatting messages for Google Chat, converting Markdown documents for Google Chat, or when the user mentions Google...
GitHub Actions security and authentication for Claude Code including API keys, OIDC, AWS Bedrock, Google Vertex AI, secrets management, and permission scoping. Use when setting up authentication or discussing s...
Claude Code workflow design and automation patterns for PR reviews, issue triage, and CI/CD integration. Use when creating or modifying GitHub Actions workflows that integrate Claude Code.
Coordinate multi-agent workflows: sequential, parallel, and iterative patterns. Defines agent handoffs, dependencies, communication protocols, and integration. Use when designing multi-agent workflows, coordina...
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。