cut-as-code

Add word-timed captions to an Open Recut program. Use this skill to map the canonical transcript through timeline.json, review a maintained style on source-backed pixels, render a local transparent HyperFrames PNG sequence, and register it as an overlay contribution for the shared delivery render.

Use when an understood video project needs selective transcript-timed titles, lower-thirds, statistics, lists, quotes, chapter cards, or calls to action authored as HyperFrames HTML graphics.

End-to-end turn an unedited long-form talking-head / vlog / podcast video into a compact "first cut" (rough cut). Use when asked to edit/剪辑 a raw YouTube (or local) video into a tighter version: download, word-level transcribe, diagnose bad-edit spots (slow intro, fillers, dead air, tangents, rambling), decide cuts in a JSON edit plan (each kept/dropped span with in/out + a one-line reason), render with ffmpeg, then self-check the result (re-transcribe + frame/black/ silence checks). Triggers: "剪成第一版", "rough cut", "first cut", "压缩时长", "把这条原片剪短", "cut down this video".

Use when a completed cut-as-code delivery needs a strict side-by-side review against its original source, including cuts, varispeed, color grade, and graphics.

Select complete short-form moments from a verified Open Recut main delivery, extract approved horizontal derivatives, and optionally render reviewed 9:16 versions. Uses the shared program transcript/timeline, hash-bound human or delegated-agent decisions, and Project Protocol V1 output locations.

Use when a video project needs reusable media metadata, word-level transcription, objective speech analysis, or evidence-backed semantic understanding before optional editing skills run.

Use when footage needs color correction, white-balance or exposure repair, Log-to-Rec.709 conversion, named creative looks, skin-tone review, or a portable .cube LUT for a cut-as-code delivery.