A set of Claude Code skills turns a recorded chess game into a readable post-mortem: it transcribes think-aloud audio, aligns sentences to PGN moves, runs a Stockfish sweep and iterative investigator queries, and produces a layered annotated PGN, a standalone HTML analysis board, and a narrated video with subtitles. Example output includes a 6:49 narrated MP4 built from a storyboard that shows move-by-move commentary matched to the player's own recorded thoughts; engine claims and all intermediate artifacts are saved as stage files (sweep JSON, investigator fragments, assembled annotations).
Claude drives Stockfish by asking human-style questions until mistakes are explained in plain language, and a verifier pass checks claims against the engine to reduce hallucinations. Three skills are provided: chess-analysis (engine sweep, investigator agents, think-aloud handling), chess-video (video/storyboard/TTS/subtitles, HTML viewer), and chess-play (PGN play with visual rendering). Installation copies skill folders into .claude/skills; dependencies include python-chess, Stockfish, ffmpeg, piper-tts and optional whisper.cpp. A full run (sweep, investigations, annotations, video) takes about an hour and is aimed at rapid or correspondence games where the player records notes or audio. MIT-licensed.
Summary generated by AI from the linked article. hn.today is not affiliated with Hacker News or Y Combinator.
OpenAI and Synopsys have announced GPT-Synopsys, a frontier intelligence platform designed to revolutionize chip design. The collaboration aims to enhance AI-driven automation and optimization in semiconductor development. (news.synopsys.com)
The US government's new AI chatbot has refrained from debunking claims made by Trump. The chatbot is currently experiencing connection issues that prevent full functionality. (techxplore.com)
OpenAI reduced the usage allowance for the $200 plan from 20x to 10x the ChatGPT Plus limit starting October 30, 2026. A new Pro 500 tier offers 25x the usage of Plus for users needing more capacity. (news.ycombinator.com)
Vectorless, reasoning-based retrieval-augmented generation (RAG) is introduced by VectifyAI to improve AI reasoning without relying on vector embeddings. The approach enhances reasoning capabilities in AI models, as detailed in their GitHub repository. (github.com)
The video features interviews with AI CEOs in 2026 discussing the future of artificial intelligence and its impact on industries. It highlights advancements in AI leadership and technological integration. (youtube.com)
A GitHub project involving 'torturing' large language models has sparked a heated debate about AI consciousness and model welfare. Experts agree that LLMs are not sentient, but some AI safety advocates worry about their 'mental health' as models become more advanced. (404media.co)
Today's best Hacker News stories, summarized and screenshotted, one email a day.