Essential command-line tools and system utilities.
Build production-ready FastAPI applications with async patterns, Pydantic validation, dependency injection, middleware, and database integration. Use for FastAPI endpoints, async workflows, or API design.
AI agent supporting REST/GraphQL/gRPC API design, OpenAPI specification generation, and API best practices Trigger terms: API design, REST API, GraphQL, OpenAPI, API specification, endpoint design, API contract, API documentation, gRPC, API versioning Use when: User requests involve api designer tasks.
Generate OpenCode configuration components and skills. Use this skill when you need to create or update OpenCode agents, commands, MCP servers, plugins, tools, or full agent skills following the official opencode.json schema. Supports generating supagents, commands, mcp configs, frontmatter, plugins, and tool mappings.
Create new Claude Agent Skills following best practices. Use when user wants to create, scaffold, or update a skill package with proper progressive disclosure structure.
Consult multiple LLM providers via src.agents.scripts.consult to get approach suggestions before implementing changes. Use when you need design options, risk checks, or alternative solutions for a task in this repo, especially before complex work.
Use PROACTIVELY when you need to create, update, configure, or validate Claude hooks for various events and integrations
Use when designing agent tools, creating tool descriptions, implementing MCP tools, or asking about "tool design", "agent tools", "tool descriptions", "MCP", "function calling", "tool consolidation"
AI collaboration protocols for multi-agent problem solving. Use when bouncing ideas between different AI perspectives, reviewing documents for updates, or simulating expert consultations. Enables structured thinking and comprehensive analysis.
Guide for creating Claude Code hooks - user-defined shell commands that execute at lifecycle points. Use when the user wants to create, add, or configure a hook for Claude Code, including PreToolUse, PostToolUse, Notification, UserPromptSubmit, Stop, SubagentStop, PreCompact, SessionStart, or SessionEnd hooks.
Unified router for agent delegation and skill routing. Absorbs agents-router + skills-router. Triggers on complex tasks, multi-step operations, research, exploration, or specialized skill needs.
Mandatory workflow for creating LLM-facing content. Follow the 4-step process (objective → draft → verify → adjust) before writing any prompt, skill, tool description, or system instruction. Triggers on requests to create or revise skills, prompts, agent workflows, or any content that will be sent to an LLM repeatedly.
Browser automation CLI for AI agents. Use for web scraping, testing, screenshots, form filling, and headless browser interactions.
Build production-ready FastAPI applications with async patterns, Pydantic validation, dependency injection, middleware, and database integration. Use for FastAPI endpoints, async workflows, or API design.
Expert guide for building and managing Gemini CLI Extensions. Covers extension anatomy, GEMINI.md context, commands, MCP integration, and publishing. Use when creating Gemini extensions, linking local extensions, packaging MCP servers, or installing extensions from GitHub. Delegates to gemini-cli-docs.
Performs automatic web search using Gemini CLI with Google Search grounding. Triggers on "Gemini search:", "suche mit Gemini", "use Gemini to find". Claude writes a request file, the Watcher executes the search, Claude reads the result. FREE Gemini 2.5 Pro with 1000 requests/day.
Automatically search indexed code when user asks questions about the codebase. Detects code-related queries and uses semantic memory to find relevant files. Activates for questions like "how does X work", "where is Y", "show me Z implementation".
This skill orchestrates complete feature development using specialized agents. Use when the user says "build feature", "implement feature", "develop feature end-to-end", "full feature lifecycle", "orchestrate development", or needs coordinated multi-agent feature work with discovery, design, implementation, and review phases.
Expert knowledge of Microsoft Agent Framework for building production AI agents and workflows. Use when building agents with Microsoft's framework, multi-agent orchestration, or tool integration.
Expert guidance for clue workspace coordination. Use when working in a directory with .clue/, when multiple Claude sessions need coordination, or when managing repositories in a shared workspace.
Launch four Explore agents in parallel to simultaneously investigate multiple areas of a codebase. Use this skill when multiple independent exploration tasks need to be performed concurrently, such as searching for different patterns, examining various file types, or investigating multiple architectural components at once.
