使用方法
- 复制安装命令，在自己的智能体环境安装前先检查源码包。
- 从原始文档核对所需工具、凭据和支持的宿主。
- 说明输入材料与期望交付物，并对照来源检查输出。
npx skills add https://github.com/oxbshw/watch-skill --skill recovering-from-errors开始前需了解
- 安装不包含模型订阅、API 额度或访问文件的权限。
- 仓库星数和安装量反映活跃情况，不等于独立质量或安全测试。
按源仓库内容呈现，保留标题、案例、代码、表格、链接以及原文引用的演示图片。
Recovering from errors
Failures use stable error codes and include an actionable fix. Preserve that evidence; do not replace it with a generic explanation.
Diagnose first
watch-skill doctor --jsonRead 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.
Retry the original operation once
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:
- acquisition or extractor failure:
watch-skill doctor --json, then retry the watch; - provider authentication: verify the matching
WATCHSKILL_*_API_KEYlocally; - provider model not found: run
watch-skill setup-visionwith a valid vision model; - low memory or local server failure: reduce the local model/context or select a cloud
provider the user already has;
- unknown video ID:
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.
