Plugin

chess-coach-ai

AI-powered chess coaching system with multi-agent cowork architecture. 4 specialized agents work together to provide comprehensive coaching: • Intel — Opponent scouting via Lichess API, Opening Explorer analysis, player profiling with style classification • GM — Stockfish analysis with time-controlled profiles (quick/normal/deep), error classification by cognitive origin (tactical miss, conceptual weakness, pattern recognition failure, time pressure), DQM scoring, endgame tablebases, personalized training roadmaps • Mind — Complete 3-phase mental performance framework (based on Jared Tendler's methodology): self-awareness (7 tilt types), self-regulation (pre/during/post-game protocols), and opponent psychological conditioning • Biohack — Evidence-based nutrition, supplementation, sleep optimization, and full weekly preparation protocols timed to your game schedule Agents communicate via agent_notes system and the coordinator synthesizes their outputs. Includes scoresheet/board photo scanning, local game vault, and Stockfish WASM fallback (no install required).

• Published source
• Repository

Analysed

11 October 2026

Last observed

11 October 2026

What the code does

• Runs shell commands Code that starts system commands on the machine it runs on.
• Evaluates code at runtime Code that builds and runs code while it executes.
• Runs hooks automatically Hooks that execute without being called explicitly.

Having a capability is not wrongdoing; many tools need these to do their job. It tells you what to check before you install.

This is public metadata, not a safety certification or complete assessment. Static analysis cannot establish what a tool does at runtime.