The Content Repurpose template makes your AI turn one piece of content into several: capture the source and its key points, propose a different angle per channel, produce each version, then review the set for faithfulness. You approve the angles before anything is written and the set before publishing.
5 steps · 2 approvals · 1 loop back
example · the steps are this template's real steps
For content teams who turn blog posts, webinars and case studies into social posts, threads and newsletter blurbs.
It is a stored workflow, not a prompt. Your AI client receives one step at a time from ConvOps over MCP, does the work, and advances. The engine holds the run at each of its two approvals until a person says yes.
5 steps, in this order. Below each one is the instruction your AI receives at that step, exactly as the template stores it.
Capture the source you are repurposing. Do not start producing yet.
Record:
If the source is missing or you cannot identify its core points, ask the operator before advancing.
Save the source, its core points, and the target channels as a task note with task_notes_add. The next step (Angles) reads this note.
Read the task notes with task_notes_list: the note from the Source Intake step contains the source, core points, and target channels. Work from it.
Propose one angle per target format. What good looks like:
Save the per-format angle list as a task note with task_notes_add. Then ask the operator to approve the angles before producing any version. This is a checkpoint: the AI cannot advance until you approve.
no rejection path · the run moves on only when approved
Read the task notes with task_notes_list: the note from the Angles step contains the approved per-format angles, and the Source Intake note holds the core points to stay faithful to. Work from them.
Produce each version following its approved angle. For every channel:
Save all produced versions as a task note with task_notes_add, labeled by channel. If the set exceeds 10,000 characters, split across notes or store where the operator keeps documents and record the location. The Review step reads this note.
Read the task notes with task_notes_list: the note from the Produce step contains every version, and the Source Intake note holds the original points to check against. Work from them.
Review each version:
Ask the operator to approve the full set for publishing. This is a checkpoint: publishing is the irreversible moment, so the AI cannot advance until you approve. If you reject, the workflow returns to Produce Versions.
rejected → back to Produce Versions
Every version is approved and ready to publish. Confirm the final set is saved as a task note, then close out the task.
Two steps wait for a person. You answer in the chat; the engine records the verdict and the audit row records who gave it.
One angle per channel decides whether the set reads as copy-paste. You approve the angles before any version is produced.
what you review
no rejection path · approve to continue
Every version is checked against its angle and the source's claims. Reject it and the workflow returns to Produce Versions.
what you review
reject → back to Produce Versions
gates the engine checks without you
Read from the template's own steps: the tools they call, the files they write, and whether they touch code.
Connect your AI client first, then install Content Repurpose from the catalog in the ConvOps app. See how to connect a client
An installed template is a workflow in your workspace. Ask your AI to change it in plain words; the edit lands on the one step that needs it.
new chat
more example prompts
No. Produce Versions carries the source's key points accurately with no claims the source did not make, and Review checks every claim is faithful to the source.
Whatever you list at Source Intake: a LinkedIn post, a thread, a newsletter blurb, an email. Each gets its own format, length and tone.
Social Post writes one post with three hook variants. Content Repurpose starts from existing content and produces one version per channel.
Any MCP client connected to ConvOps. Verified clients: Claude Code, Claude (desktop, web, Cowork), OpenAI Codex, ChatGPT, Cursor, OpenCode. It needs no repository, so a plain chat client works.