recovering-from-errors
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseRecovering from errors
从错误中恢复
Failures use stable error codes and include an actionable . Preserve that evidence;
do not replace it with a generic explanation.
fix失败会使用稳定的错误代码,并包含可执行的字段。请保留这些错误证据,不要用通用解释替代。
fixDiagnose first
先进行诊断
bash
watch-skill doctor --jsonRead the failing checks and apply only their stated fixes. 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.
doctorbash
watch-skill doctor --json查看失败的检查项,并仅应用其指定的修复方案。命令可以修复托管的ffmpeg和yt-dlp二进制文件、过期锁、损坏的缓存、缺失的帧目录,以及已知的本地模型健康问题。修复完成后重新运行一次该命令。
doctorRetry the original operation once
重试一次原操作
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: , then retry the watch;
watch-skill doctor --json - provider authentication: verify the matching locally;
WATCHSKILL_*_API_KEY - provider model not found: run with a valid vision model;
watch-skill setup-vision - low memory or local server failure: reduce the local model/context or select a cloud provider the user already has;
- unknown video ID: , then use the listed ID or original source.
watch-skill list
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.
当命令显示正常后,重复执行之前失败的命令。如果再次返回结构化错误,请报告其错误代码、消息和修复方案。不要无限循环、静默切换云服务提供商、启用云端STT,或重新处理已索引的视频。
doctor常见处理路径:
- 获取或提取器失败:执行,然后重试观看操作;
watch-skill doctor --json - 提供商认证:在本地验证对应的;
WATCHSKILL_*_API_KEY - 提供商模型未找到:使用有效的视觉模型运行;
watch-skill setup-vision - 内存不足或本地服务器故障:减小本地模型/上下文规模,或选择用户已有的云服务提供商;
- 未知视频ID:执行,然后使用列出的ID或原始来源。
watch-skill list
恢复过程中需严格遵守安全和成本策略。切勿仅为消除错误而上传视频文件、启用付费提供商或提高成本上限。