Polish
You choose the variant, the AI polishes it, and you approve before it is published. Reject it and the workflow returns to Draft Variants.
reject → back to Draft Variants
The Social Post template makes your AI turn a brief into a ready-to-publish post: capture platform, audience, core message, proof and call to action, write three variants with different hook angles, then polish the one you pick. It stops once, before publishing. Reject it and the AI drafts new variants.
4 steps · 1 approval · 1 loop back
example · the steps are this template's real steps
For founders and marketers posting on LinkedIn, X or other platforms who want options, not one take.
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 the approval until a person says yes.
4 steps, in this order. Below each one is the instruction your AI receives at that step, exactly as the template stores it.
Establish the brief for this post. Do not draft yet.
Capture, in plain prose:
If the core message is fuzzy, ask the operator before advancing: a vague message produces a forgettable post.
Save the full brief as a task note with task_notes_add. The next step (Draft Variants) reads this note.
Read the task notes with task_notes_list: the note from the Brief step contains platform, audience, message, proof, and CTA. Work from it.
Write three distinct variants of the post. What good looks like:
Label them Variant A, B, C so the operator can pick.
Save all three variants as a task note with task_notes_add. The Polish step reads this note and the operator's choice.
Read the task notes with task_notes_list: the note from the Draft Variants step contains Variant A, B, and C. Work from it.
Ask the operator which variant to run with. Polish the chosen one: tighten the hook, fix any awkward phrasing, confirm the link and CTA, check it reads well on the target platform.
Save the final polished post as a task note with task_notes_add. Then ask the operator to approve it 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 Draft Variants.
rejected → back to Draft Variants
The post is approved and ready to publish. Confirm the final post is saved as a task note, then close out the task.
One step waits for a person. You answer in the chat; the engine records the verdict and the audit row records who gave it.
You choose the variant, the AI polishes it, and you approve before it is published. Reject it and the workflow returns to Draft Variants.
reject → back to Draft Variants
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 Social Post 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
Each opens with a different hook angle (question, bold claim, story or stat), not three rewrites of one line. Each fits the platform and carries the core message, the proof point and the call to action.
Any. The Brief step records the platform (LinkedIn, X or another) because format and length differ, and the variants are written to fit it.
Yes, as the brief. For several channels at once, the Content Repurpose template turns one source into a 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.