AI & ML

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LLM applications. Use when: building RAG, vector search, embeddings, semantic search, document retrieval.

OpenClaw personal AI assistant configuration for life organization and income generation. Use when setting up, configuring, or instructing an OpenClaw agent named Henry to manage daily life, finances, tasks, calendar, and money-making activities. Activates on: 'Henry', 'OpenClaw Henry', 'my AI assistant', 'organize my life', 'make money with AI', 'set up Henry', 'Henry config'.

Caching strategies for LLM prompts including Anthropic prompt caching, response caching, and CAG (Cache Augmented Generation) Use when: prompt caching, cache prompt, response cache, cag, cache augmented.

Curated collection of high-quality prompts for various use cases. Includes role-based prompts, task-specific templates, and prompt refinement techniques. Use when user needs prompt templates, role-play prompts, or ready-to-use prompt examples for coding, writing, analysis, or creative tasks.

Multi-agent orchestration patterns. Use when multiple independent tasks can run with different domain expertise or when comprehensive analysis requires multiple perspectives.

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

Search local documents, files, notes, and knowledge bases. Index directories, search with BM25/vector/hybrid, get AI answers with citations. Use when user wants to search files, find documents, query notes, look up information in local folders, index a directory, set up document search, build a knowledge base, needs RAG/semantic search, or wants to start a local web UI for their docs.

Local search/indexing CLI (BM25 + vectors + rerank) with MCP mode.

Access ATXP's paid API tools for web search, AI image generation, music creation, video generation, and X/Twitter search via CLI or programmatic client.

Send messages to WeCom (企业微信) via webhooks using MCP protocol. Works with Claude Code, Claude Desktop, and other MCP clients.

Expert in CrewAI - the leading role-based multi-agent framework used by 60% of Fortune 500 companies. Covers agent design with roles and goals, task definition, crew orchestration, process types (sequential, hierarchical, parallel), memory systems, and flows for complex workflows. Essential for building collaborative AI agent teams. Use when: crewai, multi-agent team, agent roles, crew of agents, role-based agents.

Autonomous financial research agent for stock analysis, financial statements, metrics, prices, SEC filings, and crypto data.

Use the @steipete/oracle CLI to bundle a prompt plus the right files and get a second-model review (API or browser) for debugging, refactors, design checks, or cross-validation.

AI-optimized web search using Tavily Search API. Use when you need comprehensive web research, current events lookup, domain-specific search, or AI-generated answer summaries. Tavily is optimized for LLM consumption with clean structured results, answer generation, and raw content extraction. Best for research tasks, news queries, fact-checking, and gathering authoritative sources.

Search YouTube videos, get channel info, fetch video details and transcripts using YouTube Data API v3 via MCP server or yt-dlp fallback.

Use the ClawdHub CLI to search, install, update, and publish agent skills from clawdhub.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 clawdhub CLI.

Context7 MCP - Intelligent documentation search and context for any library

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. Use when: langfuse, llm observability, llm tracing, prompt management, llm evaluation.

Use the mcporter CLI to list, configure, auth, and call MCP servers/tools directly (HTTP or stdio), including ad-hoc servers, config edits, and CLI/type generation.

Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.

`task-agent`/`review-agent`: use when CPU, memory, I/O, database, network, rendering, or cost needs measured bottleneck evidence; skip without a profiling need.

`analysis-agent`/`task-agent`/`review-agent`: use when code needs correctness, security, performance, maintainability, or hallucinated-API review; skip when no review is needed.

`analysis-agent`/`task-agent`/`review-agent`: use when logic, rules, invariants, branches, edges, or failure paths need isolated tests; skip without a unit-test decision.

`analysis-agent`/`task-agent`/`review-agent`: use for render sinks, browser state, server fetch, upload, redirect, cross-origin, or embedding changes; skip without web exposure.

Use `analysis-agent` to create a Task DAG from an accepted source-backed Brief when 2+ tasks have dependencies, parallel value, integration, or release order. Skip single edits, accepted DAGs, and unanalysed requests.

Use `analysis-agent` to map acceptance to validation, `task-agent` to add or run bounded tests, and `review-agent` to assess proof coverage. Skip work with no material change or already-fresh complete validation.

For analysis/task/review agents using a Professional Skill on models, RAG, agents, evaluation, or safety; not for work without AI decision impact.

`task-agent`: use when document, key-value, wide-column, or graph storage changes access, partitioning, consistency, or evolution; skip vendor-only mentions and unchanged storage.

Use `task-agent` for bounded logging changes or `review-agent` to independently assess placement, schema, severity, redaction, correlation, and signal tradeoffs. Skip work with no logging impact and self-review requests.

`task-agent`/`review-agent`: use when image layers, build context, runtime user, secrets, health checks, shutdown, or provenance change; skip when container behavior is unaffected.

`analysis-agent`/`task-agent`/`review-agent`: use for provider-consumer compatibility of APIs, events, schemas, or behavior; skip without independent consumer/version risk.

`analysis-agent`/`task-agent`: use for persisted identity, relationship, ownership, lifecycle, cardinality, or invariants; skip repository, migration, and mapping-only work.

`task-agent`: use when DTO fields, validation, nullability, defaults, serialization, or compatibility change; skip persistence/domain-only work without an external schema.

`analysis-agent`: use when actors, goals, preconditions, triggers, paths, guarantees, postconditions, or acceptance traces need modeling; skip when no use-case decision exists.

Use `analysis-agent` for release decisions, `task-agent` for delivery artifacts, or `review-agent` for readiness on deployment, migration, rollback, or production risk. Skip local work with no release decision.