Learning From Mistakes Agent Skill
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.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/oxbshw/watch-skill --skill learning-from-mistakesWhat it tells the agent to use
found in the instruction textThe instruction itself
4 sections, as written by the authorLearning 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.
How to use it
Take oxbshw/learning-from-mistakes from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.