A Watch Skill command failed, video download broke, ffmpeg or yt-dlp is missing, a provider returned an error, local vision stopped, or the user asks "why can't it watch this" or "repair my setup". Use this to diagnose and apply the engine's structured fix before retrying the original operation.
npx skills add https://github.com/oxbshw/watch-skill --skill recovering-from-errors
Failures use stable error codes and include an actionable fix. Preserve that evidence;
do not replace it with a generic explanation.
watch-skill doctor --json
Read the failing checks and apply only their stated fixes. doctor can repair managed
ffmpeg and yt-dlp binaries, stale locks, corrupt caches, missing frame directories, and
known local-model health failures. Re-run it once after remediation.
After doctor is green, repeat the command that failed. If it returns another structured
error, report its code, message, and fix. Do not loop indefinitely, silently switch cloud
providers, enable cloud STT, or reprocess an already indexed video.
Common routes:
watch-skill doctor --json, then retry the watch;WATCHSKILL_*_API_KEY locally;watch-skill setup-vision with a valid vision model;provider the user already has;
watch-skill list, then use the listed ID or original source.Security and cost policy are invariants during recovery. Never upload the video file,
enable a paid provider, or raise the cost ceiling merely to make an error disappear.
Take oxbshw/recovering-from-errors 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.