DigestAI news desk

Cut through the AI noise.

Agents & Tools4 min read

User shares Claude Code skill for chess game analysis

A developer has released a set of Claude Code skills that automate the post-mortem analysis of chess games. The tool takes a game link and an optional audio recording of the player's thought process as input. It uses whisper.cpp to transcribe the audio locally and matches the commentary to specific moves using PGN clock times.

1 source primary source HN 47

Key points

  • Claude Code skill analyzes chess games using Stockfish and user audio notes.
  • Generates plain-language explanations, annotated PGN, and a narrated video of the game.
  • Full analysis run takes approximately one hour of processing time.

The system drives the Stockfish engine to answer human-style questions about the game, such as why a specific move was played or what alternatives existed. It generates a plain-language explanation of mistakes, an annotated PGN, and a narrated video of the game. The author notes that this process takes about one hour to run and is best suited for slow or rapid games where the player took time to think, rather than blitz games.

The project is open-source under the MIT license, with dependencies including Python, Stockfish, and ffmpeg. The author recommends providing audio or written notes to get a review of reasoning rather than just engine evaluation. Users can install the skills by cloning the repository and copying them into their Claude Code skills directory.

Full story from github.com · via Hacker News primary sourceOpen source ↗

Show HN: A Claude Code skill to analyze your chess games

github.com · 26 September 2026

Loading the full article…

This text was published by github.com. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Coverage and discussion

1source

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Agents & Tools

All →

Related stories