trove-video-edit
Edit a pre-cut talking-head video: captions, overlays, zooms, and a music bed. Use when the cut is already made and the edit is what remains. Not for raw multi-take footage and not for finding b-roll in a clip.
- License 许可
- MIT
- 所属仓库
- bravew/trove
- 最近更新
- 2026-11-12
- Stars
- ★ 10
- Forks
- 1
01 前言 Front Matter
- name
- trove-video-edit
- license
- MIT
- metadata
- { "inspired-by": "BuildLoop video skills", "trove-category": "designs-media", "trove-category-label": "Designs & media" }
- description
- Edit a pre-cut talking-head video: captions, overlays, zooms, and a music bed. Use when the cut is already made and the edit is what remains. Not for raw multi-take footage and not for finding b-roll in a clip.
- when_to_use
- edit this pre-cut video; add captions and overlays to this cut; one-shot edit this intro; add music and zooms to this talking head
- user-invocable
- true
02 资源文件 10
- 资产文件assets/remotion/bun.lock68.5 KB
- 资产文件assets/remotion/package.json365 B
- 资产文件assets/remotion/src/Edit.tsx2.9 KB
- 脚本assets/remotion/src/index.ts93 B
- 脚本assets/remotion/src/plan.ts427 B
- 资产文件assets/remotion/src/Root.tsx734 B
- 资产文件assets/remotion/tsconfig.json297 B
- 参考文档references/edit-plan.schema.json1.5 KB
- 参考文档references/overlays.md1.9 KB
- 脚本scripts/lint_plan.py4.2 KB
03 SKILL.md 正文
<!-- AUTO-GENERATED from SKILL.md.tmpl — do not edit directly --> <!-- Regenerate: bun run build:skills -->
Video edit
A pre-cut talking-head clip gets captions, overlays, punch-in zooms, and a
music bed. The cut already exists. Choosing takes belongs to trove-take-cut,
finding b-roll in raw footage belongs to trove-broll-ingest, and checking the
finished piece belongs to trove-video-review.
Everything on screen comes from one file, edit_plan.json. If it is not in the
plan it does not get rendered. That is what keeps the edit reviewable: the plan
is the edit, and the render is a projection of it.
Modes
Probe with trove-ffmpeg's probe.py and pick from the geometry.
| Shorts | Intro | Longform | |
|---|---|---|---|
| Shape | Portrait, 9:16 | Landscape, up to 30 seconds | Landscape, longer |
| Density | A few beats, hand placed | A few beats | One every half minute or so, per section |
Read references/runtime-spec.md in trove-ffmpeg before the first command.
Never write a raw ffmpeg command.
The plan
-
Transcribe to word level and write
words.jsonin the shapetrove-take-cutdefines. The transcript is the timing source for every beat. -
Correct it yourself. Read the transcript against the script when the user supplied one, and against what you can hear otherwise. Fix names and terms the recognizer got wrong and write each correction down. There is no second model and no API call for this. You are the pass.
-
Author the beats. One per moment that earns it. Each names the words it lands on (
anchor, copied from the transcript) and what the viewer understands from it that the words alone do not carry (reason). A reason of "this adds energy" is not a reason. Drop that beat. The kinds and when to use each are in overlays.md. The file matches edit-plan.schema.json. -
Lint before anything renders. Run
scripts/lint_plan.pywith the probed duration, and with--fpswhen the composition renders at a rate other than its default of 30. The plan carries no frame rate. A failing plan does not render. Fix the plan.
Music, sound effects, and images come from directories the user supplies. This skill ships none, fetches none, and generates none. A moment with no asset gets no image beat.
Preview, then final
Render a preview first: a short, low-resolution pass that is cheap to throw away. Show the user the file and stop. The final render happens only after they approve the preview in this session. Re-renders after feedback stay at preview until they approve again.
State once, before the first render, that Remotion is free for individuals and
small teams, that companies may need a paid license, and link the
Remotion license.
Render SDR finals with --color-space bt709. Remotion then converts the pixels
to limited range and tags the matrix, primaries, and transfer as BT.709.
The composition lives in assets/remotion/ and reads the plan. It renders the
speaker and the overlays as separate layers, so a zoom on the speaker never
crops an overlay. Copy the clip into that directory's public/ folder and name
it in plan.source as a bare filename. The composition resolves it with
staticFile, which is the only path form Remotion's renderer can fetch.
Audio
Score the approved render, not the preview. Duck the music under the voice and
normalize loudness with trove-ffmpeg's audio.py and loudness.py. When the
user supplied no music, the cut ships silent rather than with a bed they did
not choose. Then hand the result to trove-video-review.
What this skill does not decide
Colors, type, and pacing beyond the rules in overlays.md come from the
user's project. There is no default brand, no default music, and no default
call to action. Ask when a choice would change the result, and leave the moment
unadorned when there is nothing to ask.
04 同仓库更多 Skills
using-trove
Skill discipline anchor for the Trove marketplace. Loaded once per session; routes the agent to the right trove-* skill before code, planning, review, or git actions.
trove-write-skill
Skill authoring workflow. Use when creating or updating a Codex or Trove skill, including rubrics, tasks, metadata, and validation.
trove-worktree
Git worktree workflow for spikes, risky experiments, and broad refactors that should not disturb the user's current branch.
trove-why
Reconstruct design rationale and decision history from evidence — source control, issue tracker (Linear), docs (Notion), chat (Slack), error tracking (Sentry) — with calibrated confidence. Use for "why does X work this way", "why did we pick Y", regressions, and postmortems. Use trove-explain for how it works now.
trove-verify
Completion verification workflow. Use before claiming done, fixed, complete, ready, or shipped.
trove-unslop
Cut AI tells from writing — PR descriptions, release notes, specs, commit bodies, and replies. Use before finalizing prose, or when the user asks to clean up, de-slop, or make text sound human.