Use when generating synthetic training data for multi-turn conversation fine-tuning. Triggers - have design artifacts ready, need to generate conversations, ready to assess quality. Requires finetune-design first.
Build production-ready multi-agent systems using OpenAI AgentKit and Agents SDK with best practices for agent orchestration, handoffs, and routines
This skill should be used when the user asks about "creating a new ADK project", "initializing ADK", "setting up Google ADK", "adk create command", "ADK project structure", "YAML agent configuration", "creating an agent", "LlmAgent", "BaseAgent", "custom agent", "agent with different model", "Claude with ADK", "OpenAI with ADK", "LiteLLM", "multi-model agent", or needs guidance on bootstrapping an ADK development environment, authentication setup, choosing between Python code and YAML-based agent definitions, agent configuration, model selection, system instructions, or extending the base agent class for non-LLM logic.
Analyze arguments, detect biases, evaluate claims, and improve reasoning. Use when asked to fact-check, identify logical fallacies, evaluate arguments, analyze predictions, find root causes, or think adversarially about plans. Triggers include "evaluate this argument", "logical fallacies", "fact check", "analyze the claims", "identify biases", "devil's advocate", "red team this", "root cause".
Spawner selection, cost optimization, and HeadlessSpawner patterns for coordinating multiple AI models (Codex, Gemini, Copilot, Claude).
Comprehensive guide for building, testing, and distributing Claude Code plugins including slash commands, Agent Skills, subagents, MCP servers, and hooks. Use this when the user asks about creating plugins, writing slash commands, implementing skills, building MCP tools, configuring hooks, plugin architecture, marketplace distribution, or debugging plugin components. Covers 2025 schema with tool permissions, version tracking, and activation triggers.
Enhanced context7 integration with AI-powered features
[Utility] ⛔ MANDATORY skill for ANY Brain canvas operations. AI MUST invoke this skill BEFORE creating/modifying ANY files in Docs/Brain/. Failure to follow = broken canvas.
Build AI agents with OpenAI Agents SDK + Model Context Protocol (MCP) for tool orchestration. Supports multi-provider backends (OpenAI, Gemini, Groq, OpenRouter) with MCPServerStdio. Use this skill for conversational AI features with external tool access via MCP protocol.
Use to maintain context across sessions - integrates episodic-memory for conversation recall and mcp__memory knowledge graph for persistent facts
Quantum-resistant, self-learning version control for AI agents with ReasoningBank intelligence and multi-agent coordination
Enterprise Programming Languages Foundation with AI-powered language selection, Context7 integration, and intelligent multi-language orchestration for optimal technology choices
Evidence citation and domain scope standards for Neo4j subagents. Prevents hallucination and ensures audit trail.
Analyzes recent conversation history using chat tools to identify recurring workflow patterns and generate Custom Skills recommendations with statistical rigor. Use when users request workflow analysis, pattern identification, skill generation suggestions, or automation opportunities based on their AI usage patterns without requiring conversation exports.
Helps write autonomous and teleop code using Pedro Pathing library. Use when creating paths, building autonomous routines, setting up path following, working with Follower, PathChain, BezierLine, or heading interpolation.
Claude Code Agents system, task delegation patterns, and multi-agent coordination. Use when creating custom agents, managing agent workflows, or implementing task delegation.
Classifies inbound Telegram messages for telclaude as ALLOW/WARN/BLOCK with brief rationale.
Guide model fine-tuning processes for customized AI performance
WinJin AIGC 项目开发规范和最佳实践。在开发 WinJin AIGC 项目时使用，包含 Sora2 API 集成、React Flow 节点开发、文档更新流程。每次功能开发或 Bug 修复后必须更新文档。
