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

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:

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:

1. 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.
2. 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).
3. 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.
4. Captions after render — burn on the finished MP4; pick style for readability (karaoke vs simple phrase). See captions.md.
5. 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:

1. assembly-concat.md — concat, normalize, mux
2. transitions.md — xfade / acrossfade
3. captions.md — whisperx → phrase-bar + word-accent (default) or simple phrase / line-block → burn-in
4. overlays.md — drawtext, logo watermark
5. comparison-sliders.md — side-by-side / before-after
6. background-music.md — bed under VO
7. motion-composition-craft.md — example visual tokens, open act patterns, instructional beats, motion habits
8. narrated-showcase.md — flow presets, reel timing, hero vs grid
9. combination-hyperframes.md — HTML combo videos (optional)
10. social-usecase-reel.md — portrait workflow demo structure; example visuals are suggestions
11. 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:

Or install the full suite once: npx skills add PrunaAI/pruna-skills@pruna -y