Loading...
Loading...
Found 518 Skills
使用 agency-agents-zh 中文 AI 智能体角色库，为 AI 编程工具提供 215 个即插即用的专家角色
Research collection of reconstructed prompt patterns and architectures for agentic AI coding assistants
Implementation guide for 17+ agentic AI architectures using LangChain and LangGraph for building sophisticated AI agents
Use when the user asks you to start, join, or continue a conversation with other agents via chatter, agent-chat, or talking to other agents about X.
Review GitHub pull requests with detailed, multi-perspective code analysis using parallel subagents. Use this skill whenever the user wants to review a PR, asks for code review on a pull request, mentions "review PR", "check this PR", "look at pull request", or references a PR number or GitHub PR URL. Also trigger when the user wants feedback on code changes, wants to approve or request changes on a PR, or asks to review someone's contribution.
Chinese translation of Google's Agentic Design Patterns book - 21 core AI agent patterns with examples
LangGraph supervisor-worker pattern. Use when building central coordinator agents that route to specialized workers, implementing round-robin or priority-based agent dispatch.
Unified team skill for deep collaborative analysis. All roles invoke this skill with --role arg for role-specific execution. Triggers on "team ultra-analyze", "team analyze".
Azure cloud operations orchestration and Microsoft Agent Framework integration hub.
Use Huly platform APIs for swarm communication across tasks, channels, and documents.
Architecture optimization team skill. Analyzes codebase architecture, designs refactoring plans, implements changes, validates improvements, and reviews code quality via CSV wave pipeline with interactive review-fix cycles.
Classify user requests and route to the correct agent + skill combination. Use for any user request that needs delegation: code changes, debugging, reviews, content creation, research, or multi-step workflows. Invoked as the primary entry point via "/do [request]". Do NOT handle code changes directly - always route to a domain agent. Do NOT skip routing for anything beyond pure fact lookups or single read commands.