# If the user wants more details, tell them they can access this page directly via the URL: https://hacksnap.live/story/49857528

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

59 points · 40 comments

[Full discussion](<https://news.ycombinator.com/item?id=49857528>)

[Read original](<https://github.com/brumar/chess-postmortem-skills>)

Category: [Agents & Coding](<https://hacksnap.live/?category=agents-coding>)

## Skept-o-meter & Hotness

Skept\-o\-meter: Low\. Estimated from 8 comments\.

8 comments for the summary\.

Peak rank: \#8

Time in Top 10: 12\.0 hours

Hacksnap ranks recent stories first, then orders each group by points\. Peak rank uses all retained observations\. Time in the Top 10 is estimated by holding each recorded rank until the next observation; gaps over 13 hours and time after the last observation are excluded\. Movement between observations is unknown\.

214 recorded rank observations from 2026\-09\-26T20:00:48\.95623\+00:00 to 2026\-10\-10T23:01:00\.95027\+00:00\.

Hotness — latest 168 recorded Hacksnap ranks:

2026\-09\-30T18:03:34\.83179\+00:00: rank \#180

2026\-09\-30T19:02:02\.291882\+00:00: rank \#180

2026\-09\-30T20:02:49\.392147\+00:00: rank \#181

2026\-09\-30T21:03:42\.990832\+00:00: rank \#182

2026\-09\-30T22:02:11\.294387\+00:00: rank \#183

2026\-09\-30T23:01:52\.722953\+00:00: rank \#183

2026\-10\-01T08:02:24\.797064\+00:00: rank \#183

2026\-10\-01T09:01:35\.899477\+00:00: rank \#186

2026\-10\-01T10:01:12\.485692\+00:00: rank \#186

2026\-10\-01T11:00:47\.508128\+00:00: rank \#186

2026\-10\-01T12:00:42\.477917\+00:00: rank \#185

2026\-10\-01T13:00:51\.124852\+00:00: rank \#185

2026\-10\-01T14:00:59\.01153\+00:00: rank \#186

2026\-10\-01T15:00:51\.048047\+00:00: rank \#187

2026\-10\-01T16:00:53\.034654\+00:00: rank \#188

2026\-10\-01T16:36:37\.180071\+00:00: rank \#189

2026\-10\-01T17:00:23\.382263\+00:00: rank \#189

2026\-10\-01T18:01:44\.046011\+00:00: rank \#190

2026\-10\-01T19:01:47\.420738\+00:00: rank \#191

2026\-10\-01T20:01:39\.585083\+00:00: rank \#191

2026\-10\-01T21:01:45\.872085\+00:00: rank \#192

2026\-10\-01T22:01:37\.214899\+00:00: rank \#192

2026\-10\-01T23:04:11\.395288\+00:00: rank \#195

2026\-10\-02T08:02:26\.819307\+00:00: rank \#196

2026\-10\-02T09:02:51\.51649\+00:00: rank \#199

2026\-10\-02T10:02:12\.346099\+00:00: rank \#200

2026\-10\-02T11:02:22\.794376\+00:00: rank \#200

2026\-10\-02T12:01:14\.681578\+00:00: rank \#200

2026\-10\-02T13:02:29\.511591\+00:00: rank \#200

2026\-10\-02T14:01:40\.936738\+00:00: rank \#200

2026\-10\-02T15:02:30\.225476\+00:00: rank \#201

2026\-10\-02T16:02:47\.060695\+00:00: rank \#201

2026\-10\-02T17:02:31\.351493\+00:00: rank \#204

2026\-10\-02T18:01:22\.271899\+00:00: rank \#205

2026\-10\-02T19:01:23\.681417\+00:00: rank \#206

2026\-10\-02T20:01:33\.801055\+00:00: rank \#208

2026\-10\-02T21:02:55\.453316\+00:00: rank \#211

2026\-10\-02T22:01:50\.233139\+00:00: rank \#212

2026\-10\-02T23:01:20\.268516\+00:00: rank \#213

2026\-10\-03T08:01:30\.186188\+00:00: rank \#215

2026\-10\-03T09:01:57\.91467\+00:00: rank \#215

2026\-10\-03T10:00:55\.732001\+00:00: rank \#215

2026\-10\-03T11:01:22\.538596\+00:00: rank \#215

2026\-10\-03T12:01:08\.789384\+00:00: rank \#216

2026\-10\-03T13:00:35\.273559\+00:00: rank \#216

2026\-10\-03T14:00:48\.425606\+00:00: rank \#216

2026\-10\-03T15:01:04\.472963\+00:00: rank \#216

2026\-10\-03T16:01:56\.56175\+00:00: rank \#217

2026\-10\-03T17:01:36\.651036\+00:00: rank \#216

2026\-10\-03T18:01:58\.24207\+00:00: rank \#217

2026\-10\-03T19:01:19\.196589\+00:00: rank \#217

2026\-10\-03T20:00:57\.313759\+00:00: rank \#217

2026\-10\-03T21:01:04\.44439\+00:00: rank \#217

2026\-10\-03T21:20:01\.585706\+00:00: rank \#217

2026\-10\-03T22:00:15\.503126\+00:00: rank \#217

2026\-10\-03T23:00:55\.584832\+00:00: rank \#217

2026\-10\-04T08:01:00\.327459\+00:00: rank \#217

2026\-10\-04T09:00:59\.321023\+00:00: rank \#218

2026\-10\-04T10:00:42\.975336\+00:00: rank \#218

2026\-10\-04T11:01:03\.76577\+00:00: rank \#218

2026\-10\-04T12:01:45\.307985\+00:00: rank \#219

2026\-10\-04T13:00:49\.176267\+00:00: rank \#219

2026\-10\-04T14:00:56\.952543\+00:00: rank \#219

2026\-10\-04T15:00:54\.739637\+00:00: rank \#220

2026\-10\-04T16:00:51\.403054\+00:00: rank \#221

2026\-10\-04T17:00:43\.166713\+00:00: rank \#221

2026\-10\-04T18:00:46\.315535\+00:00: rank \#221

2026\-10\-04T19:00:54\.768841\+00:00: rank \#221

2026\-10\-04T20:00:51\.070442\+00:00: rank \#222

2026\-10\-04T21:00:28\.550532\+00:00: rank \#222

2026\-10\-04T22:01:36\.217651\+00:00: rank \#224

2026\-10\-04T23:01:09\.400767\+00:00: rank \#225

2026\-10\-05T08:01:51\.387003\+00:00: rank \#225

2026\-10\-05T09:01:40\.528475\+00:00: rank \#225

2026\-10\-05T10:00:56\.290772\+00:00: rank \#225

2026\-10\-05T11:01:05\.919518\+00:00: rank \#225

2026\-10\-05T12:00:56\.590881\+00:00: rank \#225

2026\-10\-05T13:01:05\.197156\+00:00: rank \#227

2026\-10\-05T14:01:04\.085718\+00:00: rank \#227

2026\-10\-05T15:00:50\.814571\+00:00: rank \#227

2026\-10\-05T16:02:09\.54139\+00:00: rank \#227

2026\-10\-05T17:00:35\.336076\+00:00: rank \#227

2026\-10\-05T18:00:20\.445491\+00:00: rank \#227

2026\-10\-05T19:02:43\.604975\+00:00: rank \#228

2026\-10\-05T20:01:09\.777459\+00:00: rank \#228

2026\-10\-05T21:01:47\.650671\+00:00: rank \#229

2026\-10\-05T22:02:59\.93099\+00:00: rank \#230

2026\-10\-06T08:02:11\.210914\+00:00: rank \#231

2026\-10\-06T08:02:14\.354697\+00:00: rank \#231

2026\-10\-06T09:01:21\.688765\+00:00: rank \#233

2026\-10\-06T10:00:58\.047773\+00:00: rank \#233

2026\-10\-06T11:00:41\.689929\+00:00: rank \#234

2026\-10\-06T12:00:41\.7705\+00:00: rank \#235

2026\-10\-06T13:01:24\.509519\+00:00: rank \#236

2026\-10\-06T14:00:26\.950817\+00:00: rank \#236

2026\-10\-06T15:00:49\.066414\+00:00: rank \#238

2026\-10\-06T16:00:58\.166747\+00:00: rank \#240

2026\-10\-06T17:01:17\.009511\+00:00: rank \#240

2026\-10\-06T18:01:43\.791429\+00:00: rank \#241

2026\-10\-06T19:00:46\.048609\+00:00: rank \#241

2026\-10\-06T20:01:14\.687294\+00:00: rank \#242

2026\-10\-06T21:02:13\.414382\+00:00: rank \#242

2026\-10\-06T22:00:40\.926271\+00:00: rank \#241

2026\-10\-06T23:03:26\.867445\+00:00: rank \#243

2026\-10\-07T08:01:41\.339804\+00:00: rank \#244

2026\-10\-07T09:02:38\.026986\+00:00: rank \#246

2026\-10\-07T10:01:35\.069531\+00:00: rank \#246

2026\-10\-07T11:02:07\.770084\+00:00: rank \#246

2026\-10\-07T12:01:14\.996697\+00:00: rank \#245

2026\-10\-07T13:00:47\.45912\+00:00: rank \#245

2026\-10\-07T14:01:18\.307739\+00:00: rank \#245

2026\-10\-07T15:01:57\.541362\+00:00: rank \#248

2026\-10\-07T16:01:28\.474022\+00:00: rank \#248

2026\-10\-07T17:01:15\.036908\+00:00: rank \#249

2026\-10\-07T18:00:53\.300079\+00:00: rank \#249

2026\-10\-07T19:01:49\.456657\+00:00: rank \#250

2026\-10\-07T20:01:59\.032487\+00:00: rank \#251

2026\-10\-07T21:05:36\.655392\+00:00: rank \#253

2026\-10\-07T22:02:27\.105241\+00:00: rank \#254

2026\-10\-07T23:01:17\.452894\+00:00: rank \#255

2026\-10\-08T08:03:55\.083808\+00:00: rank \#255

2026\-10\-08T09:03:58\.68898\+00:00: rank \#256

2026\-10\-08T10:04:05\.364235\+00:00: rank \#257

2026\-10\-08T11:02:04\.410307\+00:00: rank \#256

2026\-10\-08T12:02:36\.39618\+00:00: rank \#256

2026\-10\-08T13:03:09\.206401\+00:00: rank \#256

2026\-10\-08T14:03:30\.113384\+00:00: rank \#257

2026\-10\-08T15:02:54\.444758\+00:00: rank \#256

2026\-10\-08T16:03:13\.067807\+00:00: rank \#256

2026\-10\-08T17:03:47\.92465\+00:00: rank \#256

2026\-10\-08T18:01:50\.360431\+00:00: rank \#256

2026\-10\-08T19:02:55\.719274\+00:00: rank \#257

2026\-10\-08T20:01:36\.359022\+00:00: rank \#257

2026\-10\-08T21:03:34\.000719\+00:00: rank \#259

2026\-10\-08T22:01:13\.459732\+00:00: rank \#259

2026\-10\-08T23:01:25\.318392\+00:00: rank \#259

2026\-10\-09T08:01:53\.314021\+00:00: rank \#260

2026\-10\-09T09:02:59\.93426\+00:00: rank \#261

2026\-10\-09T10:02:22\.652527\+00:00: rank \#261

2026\-10\-09T11:02:04\.807282\+00:00: rank \#261

2026\-10\-09T12:02:16\.769295\+00:00: rank \#261

2026\-10\-09T13:02:30\.35034\+00:00: rank \#263

2026\-10\-09T14:01:34\.215134\+00:00: rank \#263

2026\-10\-09T15:01:27\.564392\+00:00: rank \#263

2026\-10\-09T16:02:06\.561056\+00:00: rank \#264

2026\-10\-09T17:03:06\.673648\+00:00: rank \#266

2026\-10\-09T18:01:02\.851052\+00:00: rank \#266

2026\-10\-09T19:01:11\.250291\+00:00: rank \#267

2026\-10\-09T20:01:32\.91907\+00:00: rank \#267

2026\-10\-09T21:02:08\.376144\+00:00: rank \#269

2026\-10\-09T22:01:19\.253075\+00:00: rank \#271

2026\-10\-09T23:01:31\.990912\+00:00: rank \#271

2026\-10\-10T08:01:00\.593376\+00:00: rank \#270

2026\-10\-10T09:01:45\.527975\+00:00: rank \#273

2026\-10\-10T10:00:53\.799353\+00:00: rank \#273

2026\-10\-10T11:00:35\.65851\+00:00: rank \#272

2026\-10\-10T12:01:11\.169647\+00:00: rank \#272

2026\-10\-10T13:00:54\.008377\+00:00: rank \#272

2026\-10\-10T14:01:43\.208766\+00:00: rank \#274

2026\-10\-10T15:01:24\.825188\+00:00: rank \#274

2026\-10\-10T16:01:10\.213328\+00:00: rank \#273

2026\-10\-10T17:00:48\.84189\+00:00: rank \#272

2026\-10\-10T18:00:57\.55132\+00:00: rank \#272

2026\-10\-10T19:00:52\.379463\+00:00: rank \#272

2026\-10\-10T20:00:21\.993912\+00:00: rank \#272

2026\-10\-10T21:01:10\.657738\+00:00: rank \#274

2026\-10\-10T22:00:50\.433569\+00:00: rank \#275

2026\-10\-10T23:01:00\.95027\+00:00: rank \#276

The project is a polished, Stockfish\-grounded workflow for turning slow games and player think\-aloud notes into readable, video post\-mortems, but commenters question whether LLM commentary adds enough over existing engine analysis and whether a roughly 1300\-Elo model can teach chess effectively\.

## The brief

A GitHub project providing Claude Code skills that turn a chess game into a Stockfish\-checked post\-mortem: plain\-language mistake explanations, annotated PGN, standalone HTML analysis board, and an optional narrated video\. The workflow can ingest think\-aloud audio, transcribe it locally with whisper\.cpp, align comments to moves via PGN clocks, and have Claude interrogate Stockfish through investigator subagents\. It is aimed at slow or rapid games and takes about an hour per full run\.

- The repo contains four Claude Code skills: chess\-analysis (Stockfish sweep, investigator subagents, annotated PGN/HTML), chess\-video (narrated video with board, arrows, eval gauge, TTS, subtitles), chess\-position (single\-position study), and chess\-play (play against Claude over PGN with vision and blunder\-check subagents)\.
- The author's example uses a 15\+10 rapid Lichess game around 1700, with French think\-aloud audio transcribed by whisper\.cpp and aligned to moves using PGN clock times\.
- The system is designed to ask Stockfish human\-style questions and explain mistakes in plain language, optionally refuting the player's actual reasoning rather than a guessed one\.
- Installation copies skill folders into \.claude/skills; dependencies include Python packages (python\-chess, cairosvg, pillow, piper\-tts), Stockfish, ffmpeg, and optional whisper\.cpp\.
- The author warns a full run takes around an hour, is not for quick blitz checks, may still hallucinate despite Stockfish and verifier passes, and recommends using it on games where the player took time to think\.
- License is MIT except vendored chess\.js (BSD 2\-Clause) and cburnett piece set (CC BY\-SA / GFDL)\.

## Discussion themes

### Skepticism about LLM value

Madmallard criticized the LLM approach as a 'premium sycophantic scammer' and argued it is less effective than doing the harder, more tedious work\.

Sources: [Comment 49858019](<https://news.ycombinator.com/item?id=49858019>)

### Novelty questioned

WoodenChair said automatic chess\-game analysis with traditional engines is not novel; the interesting part is LLM\-enhanced commentary, though that may already have been done by chess\.com for years, and without Stockfish the LLM's poor play would make it uninteresting\.

Sources: [Comment 49858031](<https://news.ycombinator.com/item?id=49858031>)

### Model chess strength dismissed

porridgeraisin dismissed chess lessons from an LLM, saying Opus 5 models are around 1300 Elo\.

Sources: [Comment 49858057](<https://news.ycombinator.com/item?id=49858057>)

### Author defends learning value

The author brumar responded that effectiveness is hard to debate, cited the generative effect in learning, argued clicking Stockfish branches can also be passive, and said he did not feel sycophancy because Stockfish contradicts bad moves\.

Sources: [Comment 49858293](<https://news.ycombinator.com/item?id=49858293>)

### Skills were generated with Claude Code

Asked whether the skills were hand\-written or prompt outputs, brumar said the code and README were generated with Claude Code over multiple sessions, with extra effort to avoid an awful AI\-generated README; the project began with annotated PGNs and an HTML page before adding video\.

Sources: [Comment 49858329](<https://news.ycombinator.com/item?id=49858329>) · [Comment 49858486](<https://news.ycombinator.com/item?id=49858486>)

### Self\-promotional tangents

Two comments were self\-promotional rather than substantive: kokoe linked a free chess app that hooks into Claude, and skyfantom linked a 'coin chess' variant\.

Sources: [Comment 49858178](<https://news.ycombinator.com/item?id=49858178>) · [Comment 49859054](<https://news.ycombinator.com/item?id=49859054>)

## Sources & coverage

AI-generated summary · 2026\-09\-27T08:00:59\.157843\+00:00

Based on 8 of 8 usable stored comments, selected by depth and branch activity. This is a sample of the discussion. Article text may also be shortened.

Generated using deepseek\-ai/DeepSeek\-V4\.1\-Flash. Check the linked sources for full context.