AgentNexus-LangChain-FastAPI

FastMCP documentation navigator and implementation guide. Use when Agent needs to answer FastMCP questions, build or debug FastMCP servers or clients, configure authentication or authorization, choose transports or deployment patterns, integrate FastMCP with FastAPI, OpenAPI, ChatGPT, Claude, Cursor, Gemini, or inspect package-level FastMCP API reference details from the bundled docs.

Structural code search, linting, and rewriting using AST-level pattern matching. Use when users need to search code by syntax structure (not text), write custom lint rules, perform codemods across a codebase, replace regex grep for precise AST-aware queries, or create reusable lint rule sets. Covers CLI usage, pattern syntax, rule system (atomic/relational/composite/utility), lint rule authoring, rewrite/transform, project setup, and testing.

Use when exploring codebase architecture, structure, components, finding code, understanding relationships between modules, or answering "how does X work" questions. Graphify queries a pre-built knowledge graph for scoped results. Use before reading files or grepping.

Use when working with LangChain or LangGraph in this repo, especially for agent construction, middleware, state graphs, persistence, memory, retrieval, runtime context, or durable execution patterns.

Help users start or troubleshoot a Cognee project by choosing the right installation path, creating a clean Python environment, configuring LLM and embedding providers, installing optional extras, running the first remember/recall smoke test, and resolving dependency setup errors.

Use when a subsystem feels hard to change because callers know too much about internals, configuration is duplicated, helper sprawl is growing, or you need to hide complexity behind a small stable interface in a large codebase.

Use when working with LangChain or LangGraph in this repo, especially for agent construction, middleware, state graphs, persistence, memory, retrieval, runtime context, or durable execution patterns.

Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"

Use when working on pg_textsearch in this repository, especially for extension installation, BM25 index creation, ranked text queries, score-based filtering, configuration tuning, or hybrid search with vectors. Trigger this skill for SQL changes, docs, examples, or guidance involving bm25 indexes, BM25 scoring operators, `to_bm25query()`, filtering tradeoffs, or pg_textsearch deployment constraints.

Use when working on pgvector or pgvectorscale in this repository, especially for extension setup, embedding-table design, similarity queries, vector distance/operator choices, or ANN index selection and tuning. Trigger this skill for SQL changes, docs, examples, or guidance involving vector columns, cosine/L2/inner-product search, StreamingDiskANN, HNSW, or ivfflat.

Creates, structures, and reviews technical documentation following the Diátaxis framework (tutorials, how-to guides, reference, and explanation pages). Use when a user needs to write or reorganize docs, structure a tutorial vs. a how-to guide, build reference docs or API documentation, create explanation pages, choose between Diátaxis documentation types, or improve existing documentation structure. Trigger terms include: documentation structure, Diátaxis, tutorials vs how-to guides, organize docs, user guide, reference docs, technical writing.

Complete toolkit for web crawling and data extraction using Crawl4AI. This skill should be used when users need to scrape websites, extract structured data, handle JavaScript-heavy pages, crawl multiple URLs, or build automated web data pipelines. Includes optimized extraction patterns with schema generation for efficient, LLM-free extraction.