A suite of MCP tools for AIs to analyze and modify C# solutions with high signal, Roslyn powered context.

Claude Code / Codex skill: generate a lean, high-signal CLAUDE.md from scratch via repo scan + focused user interview.

Claude Design DESIGN.md prompts by aesthetic family, remix recipes, skills, video teardowns, X signal, honest community takes.

Open-World Self-Evolution for LLM Agents — agents that build both their skills and their own verification signals from scratch, with no target-task supervision. (Code coming soon.)

Open-source AI phone API for voice agents. Give Claude, Cursor, OpenClaw, or any LLM a real phone number — outbound/inbound calls, SMS, transcripts, MCP, DTMF/IVR. FastAPI + SignalWire + Deepgram. Self-hostable alternative to Twilio, Vapi, and Retell.

MCP server for predictive maintenance and machinery fault diagnosis. Gives AI assistants evidence-based vibration analysis - FFT, envelope, bearing fault detection, ISO 20816-3 severity - with a measured, blind CWRU benchmark. Local-first: raw signals never leave your machine. Includes a Claude Code plugin.

Don't trust an autoresearch paper at face value. Reviewer-side integrity forensics (self-consistency + fabrication), deterministic verdict. 61 signals: 46 integrity hack-patterns (families A–H, verdict-bearing) + 13 zero-weight AI writing-style impressions (AIS) + 2 advisory. Not an opaque AI-text classifier. The dual of ARIS.

Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns

IncuBrain Foundry is a Nuxt 4 template optimised for creating AI-native businesses

Agent Skill for generating AGENTS.md files following the agents.md convention | Claude Code compatible

Chrome extension to extract styles from any website and generate DESIGN.md files and design skills for AI based on TypeUI

ffprobe for documents — probe PDF, Microsoft Office, and Apple iWork files without opening them. Rust CLI + browser WASM SDK returning structured JSON with confidence, evidence, and measured I/O cost.