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.
Read the post below. Find the three strongest claims that each stand alone without the rest of the post: a number, a contrarian take, a step-by-step. Write one 30-45 second vertical script per claim, 75-100 words each.
For each script:
CLAIM: the sentence from the post it is built on, quoted.
HOOK (0-3 s): the claim as a question or a bold line, max 12 words.
PROOF (3-25 s): the evidence or the steps from the post, in spoken sentences of max 14 words. Nothing that is not in the post.
ASK (25-30 s): one next step: read the post, try the thing, answer a question in the comments.
ON SCREEN: three text overlays, max 5 words each, one per block.
B-ROLL: three things to show that are literally in the text (a screen, an object, a place).
Rules: three different hook types across the three scripts; no script reuses a sentence from another; keep the author's words where they are better than yours. If the post holds fewer than three standalone claims, return fewer scripts and say why.
Post:
{paste post} In Claude Code, paste the prompt as a message.
Steps
- Paste the whole post, not a summary; the agent needs the author's sentences to keep.
- Post the three on different days. The claim that gets replies is the next post's topic.
- Keep the CLAIM line in your notes with the video's URL: it is the attribution and the way back to the source.
Tips
- One claim per video. A script that covers the whole post is a summary, and summaries do not get watched to the end.
- The B-ROLL line is the shot list; if the post names nothing visible, the video is a talking head with three overlays, and that is fine.
| 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 | blog-post-to-three-short-scripts.md |
Related
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.
Hook text on screen: a plan for the first three seconds, word by word
A prompt that plans what text appears in the first 3 seconds of a vertical video: the words, the moment each appears, the hold, what the picture does under it. Written so the hook works muted.
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.
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.
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.
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.