GoKawiilDeveloper builds Claude Code skill that narrates chess post-mortems using Stockfish
A developer created a set of Claude Code skills that convert a single chess game into a readable post-mortem, combining Stockfish engine analysis with the player's own recorded thoughts during the match. In a demonstration, Claude transcribed a French audio recording of the player's in-game reasoning via whisper.cpp, aligned it with move timestamps from the PGN, and produced a narrated video explaining specific decisions, such as bishop placement choices, verified against engine lines. All underlying files—transcript, engine analysis, annotated PGN, and storyboard—are shared in the project's example folder.
GoKawiil's interpretation of the reporting above, not reported fact.
By pairing a player's actual reasoning with engine verification, this approach could make chess analysis more instructive than raw evaluation numbers, since it addresses why a move was wrong rather than just how bad it was, according to the developer. It also demonstrates a broader pattern of using AI models to orchestrate other tools (like Stockfish and speech-to-text) and turn technical outputs into narrative explanations, which could extend to other domains where numeric analysis is hard to interpret.
- The tool combines Stockfish engine analysis with a player's recorded in-game thoughts to explain mistakes in plain language.
- Claude Code drives Stockfish interactively, asking follow-up questions to build human-readable explanations rather than raw evaluations.
- The full example, including transcript, PGN, and narrated video, is publicly available for review.
Source: github.com, 2026-09-26
Published there as: “Show HN: A Claude Code skill to analyze your chess games”
Read the original report → The summary and analysis above are GoKawiil's own, written from reporting by the source above. Facts and quotes belong to the original publisher.