Practices, protocols, and skills for AI-driven software development. Skills and safety hooks for Claude Code, Codex, OpenCode, Cursor, Antigravity, and any agent supporting the Agent Skills standard.

GoClaw - GoClaw is OpenClaw rebuilt in Go — with multi-tenant isolation, 5-layer security, and native concurrency. Deploy AI agent teams at scale without compromising on safety.

Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

Reverse-engineering Claude Code's 512K LOC TypeScript source: agent loop, tool system, permission model, Grove training pipeline, anti-distillation defense

🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, uses embeddings/LLMs, and provides accurate context via a tool call.

A universal, industry-neutral taxonomy of cognitive core skills (perception, memory, reasoning, planning, action, verification, learning, governance) for LLMs, SLMs, AI agents, and world models — with schemas, 159 skill cards, benchmarks, and CI.

Free, open-source MCP server giving AI assistants 17 weather tools — a one-call weather summary plus forecasts, alerts, air quality, marine, radar, lightning, rivers, wildfires, and historical data back to 1940. Ask by city name or coordinates. Built on free public APIs (NOAA, Open-Meteo). No API keys, no signup.