Agent Skills Hub

semantic-compression

Aggressively prune grammatical scaffolding and filler text from inputs to optimize LLM token usage while retaining core semantic content.

agent-architecture

Implement production-grade AI agents with LangGraph, tool-calling guardrails, SSE streaming, and episodic memory. Includes anti-patterns, fix pairs, and stateful architecture patterns.

karpathy-guidelines

Behavioral guidelines for LLMs to reduce coding mistakes, follow best practices, and improve output quality by enforcing simplicity, surgical changes, and goal-driven verification.

scraper

Automated CLI tool to scrape and convert Notion, DocSend, PDFs, and general web documents into local PDF files with session persistence and daemon support.

claude-rag-skills

A suite of professional tools for auditing, evaluating, chunking, and scaffolding production-ready RAG pipelines within Claude Code.

anthropic-api

Expert guidance for building production-ready applications with Anthropic's Claude API. Covers SDKs, prompt caching, batch processing, streaming, tool use, and cost optimization strategies.

simplemem-skill

Persistent, semantic long-term memory for AI agents. Save, query, and retrieve cross-session dialogues, decisions, and multimodal context using semantic compression.

openai-agents-sdk

Build AI agents with the OpenAI Agents SDK for Python. Supports multi-agent handoffs, function tools, stateful sessions, streaming, and Azure OpenAI integration via LiteLLM.

multi-llm-advisor

Fetches expert perspectives from OpenAI Codex and Google Gemini for architecture, code reviews, and debugging, with transparent LLM synthesis.

brave-search

Headless web search and content extraction using Brave Search API. Perform documentation lookups, factual research, and web data retrieval without a browser.

trulens-evaluation-workflow

A systematic workflow to instrument, evaluate, and monitor LLM applications using TruLens, supporting frameworks like LangChain, LangGraph, and LlamaIndex.

markitdown

Convert diverse file formats like PDFs, Office docs, images, audio, and web content into clean Markdown, specifically optimized for LLM ingestion, RAG pipelines, and automated text analysis workflows.