learning-from-mistakes

当用户指出某条视频答案错误时，该技能通过本地命令行把错误归类并保存为经验课程，供日后相似问题参考，并在条件允许时重新提问以验证纠正效果；还可列出已保存的经验课程并查看节省统计。经验仅保存在本地目录，不上传。

oxbshw

热度 0.00

最近更新 2026-10-19 04:17:50

分类：知识依赖：代码执行 / 读写文件应用场景：笔记整理 / 研究 / 测验

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add oxbshw/watch-skill/learning-from-mistakes

Metadata

name: learning-from-mistakes
version: 1.4.3
description: The user corrected an answer about a video — "no, it actually says X", "that's the wrong timestamp", "you misread the error code" — or asks why a video answer was wrong. Use this to record the correction as a lesson so future answers on similar questions improve, and to show what the system has learned and saved.
license: MIT
user-invocable: true
allowed-tools: Bash, Read

Learning 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.