A modern and intuitive terminal-based text editor

Fast, light, simple Docker containers & Linux machines

👩‍🚒 Good content deserves good paper.

🥷 Engineering habits you already know, turned into skills Claude can run.

Desktop app to manage markdown knowledge bases

Markdown Preview Enhanced for macOS QuickLook

My personal directory of skills, straight from my .claude directory.

skill for explaining architecture

Generate beautiful dark-themed system architecture diagrams as standalone HTML/SVG files. Works as a Claude AI skill.

Orchestrate sandboxed coding agents in TypeScript with sandcastle.run()

A spatial research tool that explores using AI to augment thinking, not replace it.

An Android app to visualize still images on a Pixoo Max

Control a Divoom Pixoo Max 32x32 LED display via Bluetooth from macOS

MCP server for Divoom Pixoo Max

A reverse engineering experiment of the Divoom Pixoo Max Bluetooth protocol in nodejs

Uses the pixoo-client to display interactive data (custom clock, cpu load, ram, git status, ....) on a Pixoo-Max.

Local knowledge graph for Claude Code. Builds a persistent map of your codebase so Claude reads only what matters — 6.8× fewer tokens on reviews and up to 49× on daily coding tasks.

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

PDF Parser for AI-ready data. Automate PDF accessibility. Open-source.

Mobile and Web client for Codex and Claude Code, with realtime voice, encryption and fully featured

mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local

Production-grade engineering skills for AI coding agents.

Auto generated skeleton loading framework

Autonomous experiment loop extension for pi

A spiritual successor to the standardjs javascript style guide

Open-source orchestration for zero-human companies

Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.

BullshitBench measures whether AI models challenge nonsensical prompts instead of confidently answering them, created by Peter Gostev.

stupid simple persistent memory and skill improvement