appariciojunior/video-editor-skills/vlog-pacing
Claude Code and agent skill by appariciojunior/video-editor-skills
- community
Checking that the SKILL.md file is still in the repository.
The numbers and rules that make a transcript-based cut feel natural instead of "popping" - silence detection, word pads, pause shortening, room at scene edges, jump-cut zoom alternation and punch-ins. Use when building the cut planner, tuning pauses, or when the creator says the edit is too choppy or too slow.
Install
npx vskill@latest install appariciojunior/video-editor-skills/vlog-pacingSKILL.md
Pacing: how much air to leave
A transcript cut is precise; the danger is that it is too precise. Every cut becomes a jump cut and the video "pops". These values came from real feedback.
Cut from the transcript, never from volume
A volume-only silence cut (ffmpeg silencedetect on the whole file) gave ~800 choppy pieces on a 34-minute class. Cutting from the word timestamps gave 120 pieces the creator loved. Use the waveform only to refine edges.
Planner algorithm (in words)
- Silence map per clip: below -43 dB for at least 0.25 s.
- Pause candidates inside kept speech: gap between two words ≥ 0.25 s and ≥ 85% of it is silence on the waveform (an untranscribed sound is not a pause).
- Shorten only pauses longer than
max_pause, down topause_keep. Split the leftover air 40% before / 60% after. - Word edges: start = word start − 0.08 s, end = word end + 0.12 s, refined to the nearest silence edge within 0.25 / 0.3 s so soft consonants aren't clipped; never reach into a word that was cut.
- Scene edges: the first range of a clip gets 0.5 s before the first word, the last range 0.6 s after the last word (only spoken words limit this; a lighter click or ambience may stay). Override per range in the keep-list (
lead_in,tail). Look at frames first: stop before the creator reaches for the camera. - Snap to frames (start floors, end ceils, end exclusive), remove overlaps, merge touching pieces.
- Write a review file: the transcript with cut words struck through + a timeline list with times.
Settings that worked
| Content | max_pause | pause_keep | Feel | |
|---|---|---|---|---|
| Class / tutorial | 0.5 s | 0.3 s | tight, loved | |
| Vlog | 1.0 s | 0.6 s | breathing room; 0.5/0.3 felt "popping" |
Rough check with a pause report ("what if max_pause = …: N cuts, saves X s") before choosing. On a dramatic slow opening, 0.5 s gave 7 jump cuts in 20 seconds; 1.0 s gave 3 in 53 seconds.
Framing (zoom)
- Every jump cut inside one scene alternates 100% / 107.5%, so it reads as a camera change.
- A new scene (new clip, or after B-roll) always opens at 100%. Toggling zoom on scene changes adds pops.
- Punch-in 115% only for the punchline itself: split the piece at the line's first word and again right after its last word. Without the second split one punch-in held 83 seconds.
- B-roll is always 100%.
When they say "it's choppy"
Measure first (how many cuts come from pause shortening vs. scene edges vs. zoom), then fix the actual cause: usually loosen pauses, add scene room, and stop zooming on scene changes. Don't guess.
Security
- Security scanPassed, 90 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingskills/vlog-pacing/SKILL.md
Popularity
- Repository stars
- 65
- Repository forks
- 11
- 7-day trend score
- 0
Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.
Works with
Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.
- Claude Code
- Cursor
- GitHub Copilot
- Windsurf
- Codex
- Gemini CLI
- Cline
- Amp
- Roo Code
- Goose
- Continue
- Kilo Code
- Junie
- Trae
- OpenHands
- Qwen Code
- AI Agent
- Tabnine Chat
- Sourcegraph Cody
- Amazon Q
- Firebase Genkit
- Sweep
- Devin
- Phind
- Mentat
- Claude Desktop
- Aider
- GPT Pilot
- Plandex
- bolt.new
- v0
- Replit Agent
- Anse
- TypingMind
- BetterChatGPT
- LibreChat
- Warp AI
- Pieces
- Fig AI
Embed badge
[](https://verified-skill.com/skills/appariciojunior/video-editor-skills/vlog-pacing)