@jianshuo

extracts 3-6 stand-alone topical short clips from long-form video + srt transcript by human-judged segmentation, accurate-seek cutting, optional reframing, and srt slicing. hands off raw clips + metadata to /wjs-overlaying-video for covers and captions.

wjs-translating-subtitles converts source-language SRT to target-language or bilingual SRT with mandatory punctuation-bounded re-segmentation. handles simplified chinese and english as first-class targets, with detailed translation principles and output validation rules.

wjs-reframing-video crops and reframes video between horizontal and vertical orientations by tracking the active speaker's mouth motion via MediaPipe face landmarks, outputting a crop plan sidecar and the reframed video.

wjs-editing-multicam combines n synced camera angles into a single mp4 by analyzing per-second audio energy to drive camera cuts, with optional picture-in-picture overlay. requires .sync.json sidecars from wjs-syncing-multicam.

wjs-overlaying-video composes multiple post-production overlays (cover, captions, illustrations, cta) onto video clips via hyperframes and renders them in a single encode. the skill is deeply detailed on overlay patterns but vague on the actual automation that glues clips to outputs.

Use when the user has a video + a target-language SRT and wants the video to actually speak that language — generates a time-aligned TTS voice dub. Routes by...

Thin orchestrator for the end-to-end video localization pipeline. Routes to the four focused sub-skills — /wjs-transcribing-audio, /wjs-translating-subtitles...

Use when the user asks to audit what's wrong with a project, "make it right", "看看项目出了什么问题", "为什么用户的需求还没上线", "为什么没提交App Store", "为什么没新build", or wants a holis...

Use when the user wants to write or publish a 微信公众号 (WeChat Official Account) article — they share rough thoughts, a draft, or notes and ask for help polishi...

Use when the user has 2+ video / audio recordings of the same event captured by different devices (cameras, phones, separate audio recorders) and wants them...

Upload one or many videos to YouTube. Use when the user wants to "上传到 YouTube", "发 YouTube", "批量上传", "upload to YouTube", "post videos to YouTube", or to pub...

Use when the user has audio or video and wants a timestamped transcript (SRT) in the source language. Routes by source language — Chinese defaults to Volcano...

Use when the user has a video + an SRT and wants the subtitles either burned into the pixels (libass, always-visible) or soft-muxed as a togglable track. Als...