Copy-paste prompt
Turn [URL / doc / transcript] into: 3 short posts, 1 thread, 1 LinkedIn post, 1 newsletter section and 3 quote cards of under 20 words each. Use only ideas and numbers from the source, keep quotes word for word, and add a source map that links each draft to where it came from. Write in the voice of [samples]. Don't post anything.
Fill in everything in [square brackets]. Put your approval rules (see the free operator's charter) above it.
What you need
- The source piece (URL, doc or transcript)
- Voice samples
How the agent does it
- Pull out the 5-8 strongest ideas, stats and quotes, with timestamps or paragraph references.
- Write platform-native drafts: 3 short posts, 1 thread, 1 LinkedIn post, 1 newsletter section.
- Suggest 3 quote-card texts under 20 words.
- Keep a source map so every claim traces back to the original.
What you get
A doc with all drafts plus the source map.
| Schedule | On demand, or when a new piece lands in [folder]. |
|---|---|
| Needs your approval | Publishing needs approval. |
| How to check it worked | No new claims that aren't in the source; quotes are verbatim. |
Common mistakes
- Drifting from the original meaning. Keep the source map.
Setting it up in each agent
In Grok Bot
Ask the Bot to run the prompt once and review the result. Then say "Save the process we just used as a skill called 'Repurpose one long piece into ten'" and "Create a routine that runs the Repurpose one long piece into ten skill on demand, or when a new piece lands in [folder]". Grok Bot's docs say a Bot can own up to 50 routines, schedules must be at least five minutes apart, and you should use Test run before you enable one.
In Meta Muse
Paste the prompt into Muse and ask it to remember the job and run it on the schedule. Muse asks for approval before outbound actions and purchases, so keep the 'don't send' line in the prompt. Before you rely on it, check that Muse can reach the apps this recipe needs.
In ChatGPT Dots
Give your dot the prompt as an ongoing goal and set the schedule. Dots can work between chats and ask for approval before sensitive actions. OpenAI says background work counts toward your plan's allowance, so match the frequency to what you actually need.
Run it by hand once with harmless inputs before you schedule it. A test run does real work.