| name | repurpose |
| description | Use when the user wants to turn one source piece (blog post, transcript, doc, notes, or URL) into multiple channel-ready formats — posts, a thread, an email, and a video script. Triggers on "repurpose", "atomize", "turn this into", "make social content from", or "one piece into many". |
Repurpose
Turn one source piece into posts, a thread, an email, and a video script that all carry the same core message and match the source voice.
Workflow
- Locate the source. Accept pasted text, a file path, or a URL. If given a URL, fetch the page with the built-in web tool and use the main article text only. If the source is missing, ask for it before continuing.
- Read the source in full. Extract the single core message in one sentence, then list 3-5 supporting points and any quotable lines or concrete data.
- Identify the voice: tone, sentence length, and recurring phrasing. Mirror it in every output. Do not invent facts not in the source.
- Confirm targets and constraints with the user only if unstated: which channels, how many posts, and any length or audience limits. Otherwise default to the full set below.
- Generate standalone social posts: one for LinkedIn (hook + value + soft CTA) and one for X/Twitter (single punchy post under 280 characters). Each must stand on its own.
- Generate a thread: 5-8 numbered parts. Part 1 is a scroll-stopping hook, the middle parts deliver the supporting points one idea each, and the final part closes with a CTA.
- Generate a short email: subject line, one-line preheader, 120-180 word body, and a single clear CTA. Keep it scannable.
- Generate a short-form video script (30-60 seconds): a hook in the first 3 seconds, 3-4 spoken beats with on-screen-text cues, and a closing CTA. Mark spoken lines and visual cues separately.
- Review against the core message: every asset must reinforce it, contain no placeholder text, and stay true to the source facts.
- Deliver all assets grouped by format with clear headers. Note any claim that could not be verified from the source so the user can check it.
Rules
- Imperative voice. No emoji in any output or header.
- No purple in any color reference, token, or preview.
- Never fabricate stats, names, or quotes. Pull only from the source.
- Keep each asset publish-ready. No "insert X here" gaps.
References
For per-channel format details and length limits, see references/formats.md.
