About learning-from-mistakes
learning-from-mistakes is a Watch Skill skill for recording corrections to incorrect video answers. It classifies mistakes, stores local lessons for similar future questions, and can re-ask the original question to check whether a lesson helps.
Key features
- 01Classifies errors and records guidance
- 02Stores lessons locally
- 03Applies lessons to similar questions
- 04Re-asks questions to check corrections
- 05Lists lessons and token statistics
Use cases
- 01Record a user's correction to a video answer
- 02Review lessons learned from prior errors
- 03Check whether corrected guidance fixes an answer
- 04Inspect token savings from text-first answers and semantic cache
Install
Copy the command and run it in a terminal.
npx skills add https:/After installing, type/learning-from-mistakesin Claude Code to confirm it loaded.
Details
From the project READMELearning from mistakes
When a video answer turns out wrong, the correction is worth more than an apology. Report it and Watch Skill learns locally — the mistake is classified, stored as a lesson, injected into future similar questions, and where possible the original question is immediately re-asked to confirm the lesson actually fixes it.
Report a correction
The moment the user corrects a video answer, run:
watch-skill lessons add <video_id> "<question>" "<the wrong answer>" "<the correction>"
The output includes the lesson (error_class, guidance) and, when the
question was re-asked, whether the corrected answer now comes back —
tell the user which it was. Nothing is uploaded; lessons live in
~/.watch-skill/.
See what has been learned
watch-skill lessons list
The savings meter
watch-skill stats
Lifetime token economics: what text-first answering and the semantic cache have saved versus stuffing raw frames into context. Quote real numbers from it when the user asks whether any of this is worth it.