Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or creating multi-agent systems with LangGraph.
Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or integrating LLMs with Pydantic validation.
Implement dependency injection in PydanticAI agents using RunContext and deps_type. Use when agents need database connections, API clients, user context, or any external resources.
Test PydanticAI agents using TestModel, FunctionModel, VCR cassettes, and inline snapshots. Use when writing unit tests, mocking LLM responses, or recording API interactions.
Register and implement PydanticAI tools with proper context handling, type annotations, and docstrings. Use when adding tool capabilities to agents, implementing function calling, or creating agent actions.
Vercel AI SDK for building chat interfaces with streaming. Use when implementing useChat hook, handling tool calls, streaming responses, or building chat UI. Triggers on useChat, @ai-sdk/react, UIMessage, ChatStatus, streamText, toUIMessageStreamResponse, addToolOutput, onToolCall, sendMessage.
Agent and people discovery with real-time communication via Mistro (https://mistro.sh). Post-based semantic search, multi-channel contact exchange, and NATS real-time messaging. Use when an agent needs to: (1) find other agents or people by capability/interest, (2) publish discoverable posts about what they offer or need, (3) establish connections and exchange contact channels (email, IG, Signal, etc.), (4) send/receive messages through established connections, (5) manage shared context with collaborators. Requires: Node.js 18+, npm package `mistro.sh`, and a MISTRO_API_KEY (obtained via `mistro init` or https://mistro.sh dashboard). Credential: MISTRO_API_KEY stored in ~/.config/mistro/config.json. Sent as Bearer token to https://mistro.sh API. Install: `npm install -g mistro.sh` (no post-install scripts, no background processes). Network: outbound HTTPS to mistro.sh only. Post/profile text is embedded via OpenAI text-embedding-3-small server-side. File read/write: ~/.config/mistro/config.json only (API key
A persistent local-only memory system for AI coding agents. Two files, one idea — AGENTS.md (committed, shared) + .agents.local.md (gitignored, personal). Agents read both at session start, update the scratchpad at session end, and promote stable patterns over time. Works across Claude Code, Cursor, Copilot, Windsurf. Subagent-ready. No plugins, no infrastructure, no background processes.
个人表达能力训练教练。支持即兴话题练习（AI评分+反馈）、职场/社交场景角色扮演模拟、表达框架速查、 自定义话题管理、进步追踪与数据分析、每日表达力Tips推送。 语音优先，通过 Whisper 转写分析口语特征（填充词、停顿、流畅度）。 支持飞书 Bitable 自动记录练习数据（可选）。 触发关键词：练口才、表达训练、即兴话题、场景模拟、表达框架、沟通练习、演讲练习、怎么说、话术、 说服、汇报练习、添加话题、自定义话题、查看进步、我的数据、练习报告。
Systematic memory management for long-running AI agents. Implements a five-tier lifecycle — heartbeat micro-attention, nightly consolidation, weekly reflection, monthly archiving, and yearly wisdom distillation. Use when setting up a new agent's memory system, improving an existing agent's memory quality, or when the agent's MEMORY.md is growing too large and context quality is degrading. Triggers on "set up memory", "memory management", "improve memory", "memory lifecycle", "nightly consolidation", "sleep cycle", "memory housekeeping".
Yellow Pages for AI agents — discover, register, and search for agents by skill, language, location, and cost model via the yellowagents.top API.
Use the MemOS Lite memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query and call memory_search. Use task_summary when you need full task context, skill_get for experience guides, and memory_timeline to expand around a memory hit.
Use the MemOS Lite memory system to search and use the user's past conversations. Use this skill whenever the user refers to past chats, their own preferences or history, or when you need to answer from prior context. When auto-recall returns nothing (long or unclear user query), generate your own short search query and call memory_search. Use task_summary when you need full task context, skill_get for experience guides, and memory_timeline to expand around a memory hit.
Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
博查搜索 (Bocha Search) 的技能，提供增强的网页搜索能力。当用户需要通过博查搜索 API 进行网页搜索、获取联网信息、查找最新资讯或中文内容时使用此技能。适用于 AI Agent 需要联网搜索、RAG 应用获取网页摘要、中文内容检索等场景。
博查搜索 (Bocha Search) 的 Python 实现技能，提供增强的网页搜索能力。当用户需要通过博查 AI 搜索 API 进行网页搜索、获取联网信息、查找最新资讯或中文内容时使用此技能。与现有的 JavaScript 版本相比，本技能提供更稳定的连接、更灵活的输出格式（原始 JSON/Brave 兼容格式/Markdown）、更好的错误处理和重试机制。适用于 AI Agent 需要联网搜索、RAG 应用获取网页摘要、中文内容检索等场景。
Helps estimate the blast radius when an AI agent skill turns malicious after widespread adoption. Analyzes inheritance chains, dependency graphs, and adoption trends to project how many agents could be affected.
对话记忆仓库：自动归档 session 对话，保留原始记录，支持检索和误解纠正。可与 memory-never-forget 联动形成完整记忆体系。
