appariciojunior/video-editor-skills/vlog-pacing

Claude Code and agent skill by appariciojunior/video-editor-skills

Trust tier 3
  • community
Source check pending

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-pacing

SKILL.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)

  1. Silence map per clip: below -43 dB for at least 0.25 s.
  2. 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).
  3. Shorten only pauses longer than max_pause, down to pause_keep. Split the leftover air 40% before / 60% after.
  4. 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.
  5. 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.
  6. Snap to frames (start floors, end ceils, end exclusive), remove overlaps, merge touching pieces.
  7. Write a review file: the transcript with cut words struck through + a timeline list with times.

Settings that worked

Contentmax_pausepause_keepFeel
Class / tutorial0.5 s0.3 stight, loved
Vlog1.0 s0.6 sbreathing 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

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
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/appariciojunior/video-editor-skills/vlog-pacing/badge)](https://verified-skill.com/skills/appariciojunior/video-editor-skills/vlog-pacing)

Something wrong with this skill or its page? Tell us.