Skills for Real Engineers. Straight from my .agents directory.

Skills I use with Claude for shaping

Automation foundation model for tiny devices: 2-bit, 8-29 MB, tool calls, ASR, structured extraction and embeddings on phones, wearables, smart homes, robots, cars and microcontrollers.

Browser Harness | Self-healing harness that enables LLMs to complete any task.

Deterministic browser automation. Works out of the box with Claude/Codex/OpenCode

📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG

Stock options, RSUs, taxes — read the latest edition: www.holloway.com/ec

The SDK to extract data and interact with any site on the web. Get started with Claude Code, Codex, Eve, Mastra, and more.

An MCP server that uses AppleScript to send iMessages and manage contacts.

superglue (YC W25) builds integrations and tools from natural language. Get production-grade tools for long tail and enterprise systems.

Collaborative forensic timeline analysis

BookWith – A New Reading Experience with AI. A next-generation conversational reading platform that goes beyond traditional e-book readers

(Crystal is now Nimbalyst) Run multiple Codex and Claude Code AI sessions in parallel git worktrees. Test, compare approaches & manage AI-assisted development workflows in one desktop app.

Implementing DeepSeek R1's GRPO algorithm from scratch

🤗 smolagents: a barebones library for agents that think in code.

The best ChatGPT that $100 can buy.

Store your data from all your accounts and devices in a single cohesive timeline on your own computer

AI computer use powered by open source LLMs and E2B Desktop Sandbox

Control Ableton Live with any LLM: create tracks, arrange clips & compose music via MCP

AI-powered tools to enhance Anki flashcards with explanations, mnemonics, illustrations, and adaptive learning for medical school and beyond

MCP server and CLI tool for searching and downloading documents from Anna's Archive

MiMo: Unlocking the Reasoning Potential of Language Model – From Pretraining to Posttraining

The open source research environment for AI researchers to seamlessly train, evaluate, and scale models from local hardware to GPU clusters.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Open-source, self-hosted customer support desk in a single binary. A lightweight alternative to Intercom, Zendesk, Chatwoot.

Command and Conquer: Red Alert

An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.

Tips and tricks for working with Large Language Models like OpenAI's GPT-4.