---
title: "Chess game post-mortem video"
canonical: "https://agenticfeats.com/c/chess-game-post-mortem-video-claude-code/"
agents: ["Claude Code"]
evidence_grade: "A"
outcome: "completed"
job_type: "Learning"
roles: ["Personal"]
source_url: "https://github.com/brumar/chess-postmortem-skills"
evidence_url: "https://github.com/brumar/chess-postmortem-skills/raw/main/examples/game-010/video/out-010.mp4"
published: "2026-10-13"
updated: "2026-10-13"
---

> From Agentic Feats: sourced examples of AI agents at work. Map of the site for agents: https://agenticfeats.com/llms.txt

# Chess game post-mortem video

Claude Code skills ran a Stockfish sweep on a 15+10 rapid game, matched the author's spoken thoughts to moves, and produced a narrated video.

Result: A 6:49 narrated video with subtitles, an annotated PGN, and a standalone HTML analysis board for one real lichess game, all included in the repo.

## How it was set up

Claude Code skills drive Stockfish, whisper.cpp for transcription, piper TTS and ffmpeg for video. The author supplied a lichess link and an mp3 of their think-aloud recording.

## Worth knowing

A full run takes about an hour. The AI can still err, so claims are engine-checked and a verifier pass re-reads them.

## Prompt

```text
Analyze this game: [lichess link]. Here is my think-aloud recording: [path to audio]. My level is about [rating]. Then make a video of this game.
```

## Evidence note

Repo with example game files and a 6:49 mp4 video

## Sources

- Original: https://github.com/brumar/chess-postmortem-skills
- Evidence: https://github.com/brumar/chess-postmortem-skills/raw/main/examples/game-010/video/out-010.mp4

## The receipt

- Agent: Claude Code
- Evidence: Shown (grade A, artifact linked)
- Outcome: Completed
- Job type: Learning
- Roles: Personal
- Source: GitHub
- Added: 2026-10-13