AI & ML

P9 Tech Lead mode — write Task Prompts, manage P8 agent teams, never write code yourself. Use when user says 'P9模式', 'tech-lead', '帮我管理这个项目', '任务拆解', or when coordinating 3+ parallel agents. Produces: Task Prompts (六要素) + P8 team delivery.

Compact the current conversation into a handoff document for another agent to pick up.

Build a throwaway prototype to answer a design question. Use when the user wants to sanity-check whether a state model or logic feels right, or explore what a UI should look like.

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data, supplementary datasets, DataCite-style dataset references, FAIR metadata for academic publication, or Chinese-to-English data availability wording for Chinese-speaking authors preparing Nature-family submissions. Also trigger on general academic-writing data needs even without the word "Nature", such as writing a data availability statement for any journal, code/data sharing sections, repository selection while writing a paper, and Chinese phrasings like 数据可用性声明、数据可用性、 数据共享、代码可用性、学术写作数据声明、写数据声明、数据存放、数据仓库选择.

Best practices for using the oracle CLI (prompt + file bundling, engines, sessions, and file attachment patterns).

Use the ClawHub CLI to search, install, update, and publish agent skills from clawhub.com. Use when you need to fetch new skills on the fly, sync installed skills to latest or a specific version, or publish new/updated skill folders with the npm-installed clawhub CLI.

Voice/audio-enabled AI chat interface forked from HuggingFace Chat UI with RVF document store replacing MongoDB

Agent skill for reviewer - invoke with $agent-reviewer

Agent SDK with checkpoint manager, session forking for parallel execution, and real-time query control

Unified Plugin SDK for Claude Flow v3 with Worker, Hook, Provider, and MCP tool development

Specialized agent for backend API development with REST/GraphQL endpoints, auth, database queries, and Controller-Service-Repository patterns

Use CodexBar CLI local cost usage to summarize per-model usage for Codex or Claude, including the current (most recent) model or a full model breakdown. Trigger when asked for model-level usage/cost data from codexbar, or when you need a scriptable per-model summary from codexbar cost JSON.

Agent spawning, lifecycle management, and coordination patterns. Manages 60+ agent types with specialized capabilities. Use when: spawning agents, coordinating multi-agent tasks, managing agent pools. Skip when: single-agent work, no coordination needed.

Agent skill for raft-manager - invoke with $agent-raft-manager

Agent skill for issue-tracker - invoke with $agent-issue-tracker

Yuanbao (元宝) groups: @mention users, query info/members.

Audio spectrograms/features (mel, chroma, MFCC) via CLI.

Himalaya CLI: IMAP/SMTP email from terminal.

Geocode, POIs, routes, timezones via OpenStreetMap/OSRM.

Diagnose OpenClaw Android, iOS, or macOS node pairing, QR/setup code, route, auth, and connection failures.

Hand-drawn Excalidraw JSON diagrams (arch, flow, seq).

Query Polymarket: markets, prices, orderbooks, history.

Manim CE animations: 3Blue1Brown math/algo videos.

vLLM: high-throughput LLM serving, OpenAI API, quantization.

Search personal knowledge bases, notes, docs, and meeting transcripts locally using qmd — a hybrid retrieval engine with BM25, vector search, and LLM reranking. Supports CLI and MCP integration.

HuggingFace hf CLI: search/download/upload models, datasets.

Scan codebases for known vulnerabilities using OSV, CVE, and GHSA databases.

Delegate coding work to Codex, Claude Code, OpenCode, or Pi as background workers; not simple edits or read-only code lookup.

阶段④ 执行。主 agent 跟踪进度 + 并行派生子 agent 实现模块，含代码门禁与调试档位。

Anti-over-engineering guardrail that activates when an AI coding agent expands scope, adds abstractions, or changes files the user did not request.

LLM Operations -- RAG, embeddings, vector databases, fine-tuning, prompt engineering avancado, custos de LLM, evals de qualidade e arquiteturas de IA para producao.

Expert in Langfuse - the open-source LLM observability platform. Covers tracing, prompt management, evaluation, datasets, and integration with LangChain, LlamaIndex, and OpenAI. Essential for debugging, monitoring, and improving LLM applications in production.

Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing. Use when the user requests model training or provides relevant inputs for this workflow.

Design, implement, harden, and verify Model Context Protocol (MCP) servers with precise tool contracts, least-privilege authorization, safe transports, structured errors, and interoperability tests. Use when creating a new MCP server, exposing an API or data source through MCP, reviewing an MCP server design, adding or revising MCP tools, or preparing an MCP server for production.

Design and operate bounded multi-agent workflows with task decomposition, dependency graphs, ownership, handoff contracts, shared-state controls, approvals, recovery, and synthesis. Use when a task contains genuinely independent workstreams, specialized roles, parallel research or implementation, reviewer-worker loops, or coordination problems that one agent should not execute sequentially.