Communitygithub.com

Narration Script

Write the spoken voiceover for a tutorial or demo - the actual words, phrased for the ear and synced one-instruction-per-action to what is on screen, with a pacing budget and a confident, jargon-checked tone. Use when someone says

Narration Script 是什麼?

Narration Script is a Cursor agent skill that write the spoken voiceover for a tutorial or demo - the actual words, phrased for the ear and synced one-instruction-per-action to what is on screen, with a pacing budget and a confident, jargon-checked tone. Use when someone says.

相容平台~Claude Code~Codex CLICursor
npx skills add https://github.com/SkillMedev/tutorial-video-studio/tree/main/skills/narration-script

在你喜歡的 AI 中提問

開啟一個已預先載入此 Agent Skill 的新對話。

說明文件

Narration Script 是做什麼的?

A tutorial lives or dies on its narration. The viewer is trying to do the thing while listening, so every word competes with their attention on the screen. Write less, say it plainer, and pin each line to a visible action.

Write for the ear, not the page

Spoken language is not written language. Read every line aloud before keeping it.

  • Short sentences. One idea each. If you run out of breath, it is too long.
  • Active voice, present tense, second person: "Click Save" - not "The Save button would then be clicked by the user."
  • Cut every "basically", "simply", and "just." "Just click Settings" quietly tells a stuck viewer they are stupid. Drop it.
  • Contractions are good ("you'll", "it's"); they sound human.

Sync narration to action

The cardinal rule: one instruction per on-screen action, and the words land with the action, never describing what already happened.

  • State the action a beat before or exactly as it happens on screen, so the viewer's hand and the cursor move together.
  • Never narrate a click that has already finished - "and now we've saved it" after the save animation is dead air.
  • When the screen does something complex, stop talking and let it breathe. Silence over a clear visual beats narration fighting it.

Pace it

  • Target ~140-160 words per minute for instruction. Faster loses people who are following along.
  • Budget the script against the storyboard's per-scene durations. If a beat is 8 seconds, that is ~20 words, not 50.
  • Build in deliberate pauses at transitions and at any moment the viewer needs to look rather than listen.

Structure each step

A reliable three-part shape per step keeps viewers oriented:

  1. Goal - what we're about to do and why ("To share this, we'll create a public link.").
  2. Action - the single concrete instruction ("Open the Share menu and choose Anyone with the link.").
  3. Confirmation - what success looks like ("You'll see the link turn green when it's ready.").

Signpost between steps with light transitions - "Next", "Now that the link exists, let's…" - so the spine of the tutorial is always audible.

Tone

Confident and warm, like a competent colleague sitting beside them. Never condescending, never hype. Define a term the first time it appears, then use it consistently. Match on-screen UI labels exactly - if the button says "New project", say "New project", not "create a project."

Output format

Deliver a two-column script the editor and VO talent can both follow:

On-screen actionSpoken line
Cursor opens Share menu"Open the Share menu in the top right."
Link toggles to public"Switch it to Anyone with the link."

Mark [pause] where the visual should carry the moment, and bold the words to stress. Note approximate timing per line if the storyboard durations are known.

Don't

  • Don't write music, SFX, or mix cues here - pacing the audio, ducking, and beat-matching is sound-and-music-sync.
  • Don't plan the scene order or shot list - that is video-storyboard, which this script should follow.
  • Don't describe filler the viewer can already see ("here is the screen, as you can see there are some buttons").
  • Don't let a line outrun its scene's duration budget; trim words, not pauses.

Individual skills in this repo

This repo contains 11 individual skills — each has its own dedicated page.

Captions From Transcript

Produce an accurate, properly timed caption track (SRT or WebVTT) from a video

Kinetic Typography

Put text in motion the right way - title cards, animated captions, lower-thirds, callouts, and word-by-word reveals - with a reading-time-per-word budget so copy holds long enough to read, plus enter/exit timing, weight and size transitions, and type hierarchy in motion. Use when someone asks to

Motion Design Principles

The craft layer for motion: pick the right easing (ease-in / ease-out / ease-in-out / spring), get timing and spacing right, build the anticipation→action→follow-through arc, and apply Disney

Product Demo Director

Direct the craft of putting a real software UI on screen - cursor choreography, zoom/pan/callout language, screen-recording vs recreated-UI, and making state changes legible with highlights, focus pulls, and slow-downs. Use when filming or recreating an app for a product demo, feature walkthrough, onboarding clip, or release reel and asking

Remotion Compose

Turns a natural-language video brief into a complete, ready-to-preview Remotion composition - extracts duration, scenes, brand colors, aspect ratio, and real copy; plans the frame budget; and writes data-driven React/TypeScript using useCurrentFrame, interpolate, spring, AbsoluteFill, and Sequence, registered in Root.tsx. Use when someone says

Remotion Render

Renders a Remotion composition to MP4 and runs the edit-and-re-render loop - CLI render commands, 1080p/4K/9:16 presets, concurrency tuning, codec selection, batch variants from a JSON data file, and Lambda for cloud rendering. Use when someone says

Remotion Setup

Scaffolds a new Remotion video project wired for Claude Code Agent Skills - Node check, create-video scaffold, skills install, folder conventions, Google Fonts, and a smoke-test render. Use whenever someone wants to start making videos with Remotion and Claude, even just

Screencast Capture

Capture clean raw screen and camera footage for a tutorial or product demo - choosing the recorder (macOS Screenshot toolbar, QuickTime, OBS, Windows Game Bar), setting resolution / frame-rate / cursor / microphone, prepping a distraction-free stage, and recording in retakeable segments. Use when someone says

Social Video Formatter

Reframe and export a finished video for social platforms - 9:16 ↔ 16:9 cropping, burned-in captions, a platform-native first frame, loop design, and per-platform specs (aspect, length, safe areas) for TikTok, Reels, Shorts, X, and LinkedIn. Use when someone says

Sound and Music Sync

Score a video like an editor: beat-match cuts to the music, land SFX on transitions, pace the voiceover so it breathes, source royalty-free tracks safely, and duck the music so the VO sits clearly on top. Use when adding music, sound effects, or voiceover to a video, when asked to

Video Storyboard

Plan a product demo, feature announcement, or launch video as a beat sheet and shot list BEFORE animating - hook in the first 3s, problem, reveal, proof, CTA - with target duration and pacing per scene type, output as a JSON scene plan that remotion-compose consumes directly. Use when someone says

相關技能