Communitygithub.com

do-a-rough-cut

Create a transcript-led rough cut from repeated video takes: extract the spoken script, map unique variations to source time ranges, use a supplied script as authoritative when provided, confirm only unresolved editorial choices, assemble an ordered gapless draft, and render a verified preview. USE WHEN cleaning recorded footage, removing repeated takes, building a script variation map, choosing takes for a reel, assembling a rough cut, or rendering a first edit. NOT FOR final polish, captions, graphics, music, or color styling unless explicitly requested.

¿Qué es do-a-rough-cut?

do-a-rough-cut is a Claude Code agent skill that create a transcript-led rough cut from repeated video takes: extract the spoken script, map unique variations to source time ranges, use a supplied script as authoritative when provided, confirm only unresolved editorial choices, assemble an ordered gapless draft, and render a verified preview. USE WHEN cleaning recorded footage, removing repeated takes, building a script variation map, choosing takes for a reel, assembling a rough cut, or rendering a first edit. NOT FOR final polish, captions, graphics, music, or color styling unless explicitly requested.

Compatible con~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/hash-anmol/skills/tree/HEAD/skills/video-editing/do-a-rough-cut

Preguntar en tu IA favorita

Abre un nuevo chat con esta habilidad de agente ya precargada.

Documentación

Do a Rough Cut

Build an editable first cut from several recordings of the same spoken piece. The skill is deliberately transcript-first: it keeps the words and their source ranges visible before making irreversible editorial choices. When the user supplies the script, that wording and order become the editorial source of truth; the transcript and variation map are then used to locate and validate the matching takes rather than to ask for script approval again.

Workflow routing

RequestWorkflow
Create, revise, or render a transcript-led rough cutWorkflows/RoughCut.md

Non-negotiable invariants

  • Preserve source originals; work from copies or source references.
  • Produce a unique-script document and a variation map before cutting.
  • Match ASR to the speech: for code-mixed takes (e.g. Hinglish), use a code-mix transcriber (e.g. Sarvam saaras:v3, mode codemix; keep the API key in your environment) with utterance splits at measured pauses. A single English-only Whisper pass produces confident, badly wrong text on code-mixed audio.
  • If the user supplies a script, treat its wording and order as confirmed; do not ask the user to confirm the script again. Confirm only decisions the supplied script cannot answer.
  • Pause at the decision checkpoint when competing takes materially change the words, meaning, or ending. “Proceed” is a valid best-effort override.
  • Treat the ordered edit manifest as the only source of timeline order. Never build an FFmpeg concat list from a filesystem glob.
  • Keep selected audio and video ranges identical, cut immediately between segments, and leave handles around words when the user asks for a relaxed rough cut.
  • Inspect source color metadata. Apply at most one deliberate HLG/BT.2020 → BT.709 SDR conversion, then verify the result visually.
  • On GPU-less hosts, libplacebo needs an explicit software Vulkan device: -init_hw_device vulkan=vk -filter_hw_device vk; the bare filter fails device init with Found no suitable device. Keep it SW-in/SW-out: a hwupload/hwdownload wrapper can run yet silently zero the chroma planes (monochrome-green output), so verify colors via channel means, not luma stats.
  • Verify the rendered MP4 itself, not only the HTML/composition preview: probe metadata, decode all video and audio, check first/last frames, and report the real output path and duration.

Supporting material

Example

User: “Use these three recordings to make a rough Instagram reel. Remove repeats, show me the script variations first, then cut and render it.”
→ Transcribes each source and writes the unique script plus variation map.
→ Asks only the unresolved take/order/ending decisions.
→ After confirmation, writes an ordered manifest, creates relaxed gapless cuts, renders, and verifies the MP4.

User: “Here is the final script: [script]. Use it to make the rough cut.”
→ Saves the supplied script verbatim, marks its wording/order as confirmed, and maps each line to the best matching source range.
→ Does not ask for script approval; it asks only about a genuine non-script ambiguity or proceeds automatically when none remains.
→ Writes the ordered manifest, creates relaxed gapless cuts, renders, and verifies the MP4.

Skills relacionados