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.

🦀 Prevents outdated Rust code suggestions from AI assistants.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.

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.