Video editing
Use when assembling or polishing already-rendered clips with ffmpeg — concat, crossfades, burned captions and subtitles, text/logo overlays, before/after sliders, background music beds, platform export — or when composing a multi-layer HTML combination video with Hyperframes. Not for AI video generation, prompt craft, or model-based video edits.From its SKILL.md
npx -y skills add PrunaAI/pruna-skills --skill video-editingAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 17 stars17 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its file declares
Copied from the file, not written here
The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.
SKILL.md
9.7 KB, as published. Nobody here has run it
Video editing
Vendor-neutral craft for local post-production on finished media. Works with any clips, stills, VO, or beds you already have — from any source.
This skill is not generative video editing. It does not write motion prompts or call video generation APIs. Produce or collect media first; assemble and polish here.
Install
| Skill | Description | Install |
|---|---|---|
video-editing | Use when assembling or polishing already-rendered clips with ffmpeg — concat, crossfades, burned captions and subtitles, text/logo overlays, before/after sliders, background music beds, platform export — or when composing a multi-layer HTML combination video with Hyperframes. Not for AI video generation, prompt craft, or model-based video edits. | npx skills add PrunaAI/pruna-skills@video-editing -y |
When to use
- Stitch multiple rendered clips (hard cut or crossfade)
- Burn in phrase captions — word-accent promo, simple phrase (landscape explainers), or line-block — see captions.md
- Add title cards, lower-thirds, or logo watermarks
- Build before/after or side-by-side comparison clips
- Mix an instrumental bed under dialogue or VO (~10–20% under speech for explainers; taste varies)
- Export for social aspect ratios (9:16, 1:1, 16:9) with loudness normalization
- Compose a multi-act narrated showcase (hook, context, reel, close) via HyperFrames or ffmpeg — narrated-showcase.md
- Compose a combination video with UI chrome, chat mocks, or multi-panel layouts via Hyperframes (optional — see combination-hyperframes.md)
Works with
Any finished MP4/MOV/WebM plus local ffmpeg / ffprobe. Caption alignment often uses Replicate whisperx (or any timed transcript you already have). Beds and VO may come from any TTS or music tool. Upload helpers in sibling skills are optional, not required.
When NOT to use
Use a different skill instead:
| Skill | Description | Install |
|---|---|---|
video-prompting | Use when crafting video or motion prompts for any generative model — dramaturgy, camera, physics-safe motion, frame anchors, and clip chaining. | npx skills add PrunaAI/pruna-skills@video-prompting -y |
p-video | Use when someone wants one short video clip from text or images — B-roll, start/end frame animation, or a quick motion shot. Not for full multi-scene films or lip-synced hosts. | npx skills add PrunaAI/pruna-skills@p-video -y |
p-video-avatar | Use when someone wants a person on camera speaking a script — lip-synced host, spokesperson, or narrated avatar from a portrait photo. | npx skills add PrunaAI/pruna-skills@p-video-avatar -y |
p-video-animate | Use when someone wants a photo to move like another video — motion transfer, dance remixes, or performance variations from a template clip. | npx skills add PrunaAI/pruna-skills@p-video-animate -y |
p-video-replace | Use when someone wants to swap a person, outfit, or product inside existing footage while keeping the camera move and audio. | npx skills add PrunaAI/pruna-skills@p-video-replace -y |
p-image-edit | Use when someone wants to edit an existing photo — change outfits or backgrounds, compose from reference images, or apply prompt-driven edits. | npx skills add PrunaAI/pruna-skills@p-image-edit -y |
music-video | Use when someone wants a full music video — original song or vocals, performance clips, B-roll, and lyric-synced edits. | npx skills add PrunaAI/pruna-skills@music-video -y |
narrated-multi-scene | Use when someone wants a multi-part story with voiceover — episodic B-roll, chaptered promo, or several linked video scenes without on-camera dialogue. | npx skills add PrunaAI/pruna-skills@narrated-multi-scene -y |
Guide habit
In the first reply, name `video-editing` in backticks. Confirm inputs exist on disk (clips, optional bed, optional logo). Confirm ffmpeg / ffprobe are available. When source media, palette, audio, captions, aspect, resolution, or act structure are open, open intake → generation-diversity clarification intake before generating missing pieces or starting a long render. Only call generative or alignment APIs when the user explicitly needs a missing bed, TTS, or caption timing (e.g. whisperx).
Structure and creativity (multi-act pieces)
When the brief is “explain and show” with VO plus existing clips or stills:
- Propose structure before pixels — offer two or three act orders (e.g. explain-then-show vs show-then-explain). See flow presets in narrated-showcase.md; merge, drop, or rename acts freely.
- Separate beats visually — a text-heavy “how it works” act should not look like the proof reel (different layout, no duplicate preview grid unless the brief asks for it).
- Run the reel through narration — extend the showcase window until VO finishes; rotate one hero frame or cycle clips with crossfades when clip count is low and size matters.
- Captions after render — burn on the finished MP4; pick style for readability (karaoke vs simple phrase). See captions.md.
- Borrow patterns, don’t clone — tokens, motion habits, and act types from a reference reel; don’t reuse another project’s scene order if the message differs. motion-composition-craft.md.
If the user already named a layout, implement it; still confirm pacing and caption style after the first preview or render when the brief was vague.
Before assembling
Read in order for the task at hand:
- assembly-concat.md — concat, normalize, mux
- transitions.md —
xfade/acrossfade - captions.md —
whisperx→ phrase-bar + word-accent (default) or simple phrase / line-block → burn-in - overlays.md —
drawtext, logo watermark - comparison-sliders.md — side-by-side / before-after
- background-music.md — bed under VO
- motion-composition-craft.md — example visual tokens, open act patterns, instructional beats, motion habits
- narrated-showcase.md — flow presets, reel timing, hero vs grid
- combination-hyperframes.md — HTML combo videos (optional)
- social-usecase-reel.md — portrait workflow demo structure; example visuals are suggestions
- export-presets.md — aspect ratios, loudnorm, web export
Bed prompts and embed-vs-post policy: audio-prompting.
Combination videos (Hyperframes)
When the deliverable needs designed frames — chat UI mocks, kinetic type, multi-panel grids, montages with on-screen copy — install hyperframes (optional external — see Related skills below) and follow combination-hyperframes.md.
Pattern: HyperFrames render (motion + VO, no burned captions) → post-render ffmpeg (whisperx → caption burn — style per captions.md → optional bed mux → export). Multi-act structure: narrated-showcase.md + motion-composition-craft.md. Portrait workflow demo reels: suggested act order and HyperFrames timing in social-usecase-reel.md. Colors, type, and bar layout there are example proposals, not required tokens.
Related skills
Install related skills when the job needs them:
| Skill | Description | Install |
|---|---|---|
generation-diversity | Use when writing any generative prompt — ritual seed, explicit structure, scenario axes, and quality gates before paid API calls. | npx skills add PrunaAI/pruna-skills@generation-diversity -y |
whisperx | Use when someone needs word-level timestamps from audio — lyric alignment, cut-safe line boundaries, or caption source timing before burn-in with video-editing. | npx skills add PrunaAI/pruna-skills@whisperx -y |
stable-audio-2.5 | Use when someone wants light instrumental background music — an ambient bed under dialogue or underscore for reels and explainers. | npx skills add PrunaAI/[email protected] -y |
gemini-3.1-flash-tts | Use when someone needs spoken narration or voiceover — explainer tracks, documentary lines, or voice to pair with generated video. | npx skills add PrunaAI/[email protected] -y |
audio-prompting | Use when crafting TTS, music, or bed prompts for any generative audio model — director style, song structure, and post-production layering. | npx skills add PrunaAI/pruna-skills@audio-prompting -y |
pruna-api | Use before any Pruna or Replicate HTTP call — credentials, upload/poll/download, parallel batches, and agent safety. | npx skills add PrunaAI/pruna-skills@pruna-api -y |
Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y
What ships with it: 12 files
52.6 KB alongside SKILL.md
references/
- assembly-concat.md2.5 KB
- background-music.md2.4 KB
- captions.md10.4 KB
- combination-hyperframes.md11.2 KB
- comparison-sliders.md1.2 KB
- export-presets.md1.8 KB
- motion-composition-craft.md7.8 KB
- narrated-showcase.md5.8 KB
- overlays.md1.5 KB
- social-usecase-reel.md5.6 KB
- transitions.md2.1 KB
- skill.manifest.json319 B
Gives 0 of the 12 instructions most video audio skills give
Counted across 619 of the 725 authors here whose files we hold, read 2026-09-06
- Read product marketing context firstin 13 of 619, across 7 files
- Define the core visual thesis in one sentencein 11 of 619, across 3 files
- Break the concept into 3 to 6 scenesin 11 of 619, across 3 files
- Render the smallest working version firstin 11 of 619, across 3 files
- Start with a low-quality smoke test renderin 11 of 619, across 3 files
- Add captions for accessibility and engagementin 11 of 619, across 5 files
- Write the scene outline before writing codein 11 of 619, across 3 files
- Specify subject, action, camera, style, and moodin 11 of 619, across 5 files
- Decide what each scene provesin 10 of 619, across 2 files
- Export one clean thumbnail framein 10 of 619, across 2 files
- Pick the right tool for the jobin 10 of 619, across 4 files
- Run the test suite before proposing a fixin 8 of 619, across 7 files
Said here and by no other author read
- Confirm inputs exist on disk
- Propose structure before pixels
- Separate beats visually
- Run the reel through narration
- Burn captions after render
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once.