Screen-recording demo script for an app: what to click, what to say, when
A prompt that writes a demo script where every spoken line is paired with one on-screen action, so the recording is done in one pass and the narration recorded over it afterwards.
Write a screen-recording demo script for {app} that shows {the one job it does} in {60-90} seconds. The recording is the picture; the narration is recorded separately over it. Output a table: Time | Action on screen (what I click, type or scroll) | Narration (what is said during this action) | Hold (seconds the result stays on screen). Rules: - Start on the result, not the login screen: the first 5 s show the finished thing, then cut to the start. - One action per row. 'Open settings and change the language' is two rows. - Narration describes what the viewer sees and why it matters, never 'now I click'. Max 18 words per row. - Every row where a result appears gets a Hold of at least 2 s. No row shorter than 2 s. - No feature that is not needed for {the one job}. Mention the others in one closing line at most. - End on the result again, with the URL spoken once. Context about the app: {paste README or feature list}
In Claude Code, paste the prompt as a message.
Steps
- Prepare the app state before recording: sample data that looks real, notifications off, a clean desktop, the window at the final export size.
- Record the actions following the table without talking. Then read the narration over the recording and stretch holds in the edit where the voice runs long.
- Cursor: slow, straight lines, a pause before each click. A fast cursor is the one thing viewers notice and remember.
Tips
- Record at the output size or an integer multiple of it; non-integer scaling blurs UI text.
- For an iOS app, record on the Simulator or mirror the device; for web, a clean browser profile with no extensions.
| works with | Claude Code: Runs as a skill or a prompt in the terminal; can read your files and write the result. · Claude: Paste into claude.ai or the Claude app. · ChatGPT: Paste into ChatGPT; works with any GPT model. · Any LLM: Model-agnostic: Gemini, Mistral, a local model. |
| cost | Free. No API, no key. |
| status | Unverified: written from the technique, not yet run end to end by us. |
| license | CC BY 4.0 for the text here; skills are MIT. |
| updated | 2026-11-01 |
| for agents | screen-recording-demo-script-app.md |
Related
Screen-recording b-roll for app demos: what to record, size, cursor
Rules for screen captures used as cutaways in a product video: real-looking data, output-size or 2x resolution, a slow cursor, one action per clip, and what makes a recording unusable.
The 30-45 second promo script: hook, problem, demo, CTA with timings
A fill-in script template for a vertical product promo: four blocks with second counts and a 75-100 word narration budget, so the video ends before the viewer scrolls.
Turn a blog post into three short scripts: one claim per video
A prompt that reads a post and returns three 30-45 second scripts, each built on a different claim from the text, with the hook, the proof, the ask and the source sentence for each.
Forced reasoning before scripting: goal, hook type, demo moments, emotion arc
Four questions an agent must answer in writing before it writes a line of script. Skips the generic promo every model produces when asked for one directly.
Cut any script to 55 words: the 20-second rewrite prompt
A rewrite prompt that compresses a script to 55 words (about 20 seconds at 165 wpm) without losing the number, the name or the ask, and reports what it removed so you can argue.
Shot list generator: a table with shot, duration, visual, audio and overlay
An agent prompt that turns any script into a numbered shot table a camera operator or a video model can follow: one visual, one audio line and one text overlay per row, durations that add up.