langsmith-fetch
Debug LangChain and LangGraph agents by fetching execution traces from LangSmith Studio. Use when debugging agent behavior, investigating errors, analyzing tool calls, checking memory operations, or examining agent performance. Automatically fetches recent traces and analyzes execution patterns. Requires langsmith-fetch CLI installed.
error-fixer
Fix JavaScript and HTTP errors flagged for AI in the admin dashboard. Queries the database for errors with ai_status='flagged_for_ai', analyzes them, and attempts to fix them. Use when: - User says "fix errors" or "fix flagged errors" - User says "check error queue" - User mentions AI error queue or AI-flagged errors - After flagging errors in admin dashboard Triggers: "fix errors", "error queue", "ai errors", "flagged errors", "fix ai errors", "/fix-errors"
a2a-mcp-integration
Integration patterns for combining Agent-to-Agent (A2A) Protocol with Model Context Protocol (MCP) for hybrid agent communication. Use when building systems that need both agent-to-agent communication and agent-to-tool integration, implementing composite architectures, or when user mentions A2A+MCP integration, hybrid protocols, or multi-agent tool access.
generate-workshop-slide-image
Генерація обкладинки/ілюстрації для слайду воркшопу через OpenAI Images API та вставка в Slidev.
unsloth-core
Core fundamentals of Unsloth for fast LLM fine-tuning, covering FastLanguageModel setup, optimized gradient checkpointing, and native inference acceleration (triggers: unsloth, FastLanguageModel, from_pretrained, get_peft_model, for_inference, gradient checkpointing).
manage-conversation-db
This skill should be used when implementing stateless conversation persistence, creating/loading conversations by ID, saving user/assistant messages, fetching history for agent input, and handling async database queries.
gemini-cli-model
Instructions for selecting and configuring Gemini 3 Pro Preview model in Gemini CLI. Use when the user asks about switching models in Gemini CLI, enabling Gemini 3, or configuring Gemini CLI model settings.
ai-sdk-v6
Guide for building AI-powered applications using the Vercel AI SDK v6. Use when developing with generateText, streamText, useChat, tool calling, agents, structured output generation, MCP integration, or any LLM-powered features in TypeScript/JavaScript applications. Covers React, Next.js, Vue, Svelte, and Node.js implementations.
voice-state-machine
Voice assistant state machine pattern with XState, Whisper, and VAD. Trigger: When implementing voice commands, wake word detection, or speech flows.
session-manager
Activates when the user asks to "create session summary", "summarize this session", "end the session", "start a session", "load context", "what did we work on", "session notes", "document this session", or wants to track, document, and manage work sessions.
ai-model-reference
AI 모델 API 호출명 및 가격 참조 가이드. API 키로 AI 모델을 호출할 때 정확한 모델명(model string)과 최신 가격 정보를 제공합니다. 사용 시점: (1) OpenAI, Anthropic, Google, DeepSeek 등의 API 호출 시 모델명이 필요할 때, (2) 토큰 비용/가격 비교가 필요할 때, (3) 최신 추론 모델/FAST 모델/가성비 모델 선택이 필요할 때, (4) 프롬프트 캐싱/배치 처리 비용 최적화가 필요할 때
tool-design-pattern
Automatically applies when creating AI tool functions. Ensures proper schema design, input validation, error handling, context access, and comprehensive testing.
streaming-patterns
Configure ADK bidi-streaming for real-time multimodal interactions. Use when building live voice/video agents, implementing real-time streaming, configuring LiveRequestQueue, setting up audio/video processing, or when user mentions bidi-streaming, real-time agents, streaming tools, multimodal streaming, or Gemini Live API.
langgraph-persistence
Persistence and human-in-the-loop patterns for LangGraph. Use when implementing checkpointing, saving/restoring graph state, adding human approval workflows, managing conversation memory across sessions, enabling time-travel debugging, or building fault-tolerant agents that resume from failures.
repo-grounding
Ground answers in the repository by reading relevant files, configs, and code paths. Use when the user asks to modify/debug code, configuration, CI/CD, or wants repo-specific reasoning.
payload-generator
Generate optimized indirect prompt injection, H-CoT, and multi-layer attack payloads for AI security testing and CTF competitions with automated family selection and success rate optimization
working-with-ms-agent-framework
Use when building AI agents with Microsoft Agent Framework (Semantic Kernel + AutoGen unified); when implementing memory or context providers; when threads won't deserialize; when workflow checkpointing fails; when migrating from Semantic Kernel or AutoGen; when seeing ChatAgent or AgentThread errors
context-management
Use for any TiDB-related projects, tasks, or code. Context engineering and context management for AI agents: keep prompt prefixes stable for KV-cache, use append-only context, prefer tool masking over tool removal, offload large observations into filesystem memory, recite goals/todos to control attention, preserve errors for recovery, and avoid few-shot pattern lock-in. Use when building or debugging agent loops, prompt/context schemas, memory strategies, or tool-availability policies.
claude-md-expert
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。
ai-ctf-generic
Execute AI security CTF challenges across any competition platform with adaptable workflows for indirect prompt injection, jailbreaks, agent exploitation, and evidence collection with research-grounded techniques
mcp-server-dev
Patterns for building Model Context Protocol (MCP) servers including tools, resources, prompts, and transport handling. Use when creating MCP servers to extend AI assistant capabilities.
