> ## Documentation Index > Fetch the complete documentation index at: https://docs.oppin.ai/llms.txt > Use this file to discover all available pages before exploring further. # Content > Plan what to publish next. Prompts to paste into Claude or any assistant connected to Oppin. Paste a prompt into an assistant connected to Oppin ([how to connect](https://docs.oppin.ai/mcp/overview.md)) and replace the parts in \[brackets] with your own. In Oppin, the **MCP** tab of the **Data & MCP** page has the same prompts with your brand and a competitor already filled in. ## Quick questions One question, one answer. Paste it as it is. ### Which of our own pages does AI actually use? *Quick question* Your pages ranked by use, with new and dropping ones flagged. ```text wrap theme={null} Using Oppin, which of our own pages does AI actually use? ``` ## Workflows A few steps and one useful result. ### Content brief from a gap *Workflow · Deliverable (a one-page brief)* Turn one question you lose into a brief a writer can start today. ```text wrap theme={null} Using Oppin, find the question in our [topic] topic where competitors beat us by the widest margin. Look at who AI recommends there, which pages it reads, and the related fan-out queries. Then write a content brief: the question, the reader's intent, the angle, the questions to answer, the facts and names to include, the sources worth referencing, an outline, a title and a meta description. Mark anything that is your interpretation rather than Oppin data. ``` * **You get:** A one-page brief where every section points back to what AI reads today. * **Why it helps:** The research hour is done. The brief is framed as a data-informed bet, never a promise of citations. * **Shortcut:** the [`oppin_content_brief`](https://docs.oppin.ai/mcp/commands#content-brief) command runs the same analysis. * **Take it further:** Notion or Google Docs, and a Slack ping to the content team; see [Gap to brief to content team](https://docs.oppin.ai/mcp/use-cases/content.md#gap-to-brief-to-content-team). ### Own-page health check *Workflow · Ranked list (+ CSV)* Find your pages that are losing AI attention before traffic shows it. ```text wrap theme={null} Using Oppin, which of our own pages does AI use, and which are losing ground? Compare the last 30 days with the 30 before. For the three biggest drops, show which questions they used to be used for, what AI reads instead now, and whether each page needs a refresh, a rewrite or nothing. ``` * **You get:** A table (page, uses before and after, change, questions lost, what replaced it, a one-line diagnosis). * **Why it helps:** Content that stopped earning AI attention is usually the fastest win. * **Note:** "Did our refresh of \[URL] on \[date] work?" runs the same check on one page, 30 days either side. ### Pre-publish check *Workflow · Deliverable (your draft, annotated)* Catch what a draft is missing before it goes live, not a month after. ```text wrap theme={null} Using Oppin, here's a draft we plan to publish for [question or topic]: [paste]. Compare it with the pages AI reads most for those questions and the related fan-out queries. Give me the draft back with inline notes wherever it misses a question, a fact or a name those pages cover. ``` * **You get:** Your own draft, annotated where it falls short, plus a short edit list. * **Why it helps:** Turns "write something AI will cite" into a checklist against what AI reads today. ### Double down on what works *Workflow · Interactive page (a board)* Find what already carries your AI visibility, and extend it into the weak spots right next to it. ```text wrap theme={null} Using Oppin, find what's driving our AI visibility: the pages and sites most often cited when AI mentions us, and the topics and questions we win. Then find nearby questions in those same topics where we're weak, and suggest new content modeled on what already works for us. Show it as a two-column board: the pages that already win on the left, each linked to the new ideas modeled on it on the right. ``` * **You get:** A board: what's working on the left (your pages and the outside sites carrying you, with numbers), and on the right three to five ideas, each naming the weak question it targets, new page or extension, format and evidence. * **Why it helps:** Every other content idea starts from a loss. This one starts from a format that already works in a topic where AI already trusts you, which is usually the cheaper win. * **Shortcut:** the [`oppin_double_down`](https://docs.oppin.ai/mcp/commands#double-down) command with output `page` runs the same analysis. * **Note:** Being cited next to your mentions shows association, not that the page caused them. The command says so and doesn't promise new content will be cited. ### Gap to brief to content team *Workflow · Notion database entry + Slack ping* Find your biggest content gap, brief it in Notion, and tell the content team. ```text wrap theme={null} Using Oppin, find our biggest content gap, write a brief for it, save the brief in our Notion content database, and tell #content it's ready with a two-line summary. ``` * **Why it helps:** From "we're invisible here" to an assigned brief in one prompt. * **Needs:** Notion, Slack, connected in your assistant. ### Content backlog *Workflow · Structured data (Notion or Sheets rows)* A prioritized content backlog in Notion or Sheets, grounded in Oppin data. ```text wrap theme={null} Using Oppin, find our 10 biggest content opportunities, group them into themes, and build a prioritized backlog in [Notion / Google Sheets]: theme, question, who wins it today, the sources AI reads, suggested format, and why it matters. Explain the order using Oppin data, not made-up scores. ``` * **Why it helps:** A quarter of content planning, grounded in what AI reads. * **Needs:** Notion or Google Sheets, connected in your assistant. ### Content calendar to measurement *Workflow · Answer (questions per article) + questions added on approval, then a citation check* Give every article a scorecard before it ships. ```text wrap theme={null} Using Oppin and our content calendar in [Notion / Google Sheets], for each article we publish next month, suggest 2 or 3 questions it is meant to win, tagged with the article's name, and add them after I approve. In 6 weeks, tell me which articles AI now cites, and for which questions. ``` * **You get:** Two or three tagged questions per upcoming article, then, six weeks on, which articles AI cites and for which questions. * **Why it helps:** Content teams can show that an article earned an AI citation, the proof a content budget needs. * **Needs:** Notion or Google Sheets, connected in your assistant. * **Changes tracking:** needs a connection with write access. The assistant shows the changes and waits for your yes. * **Note:** The six-week check is a second request: ask again then, or set it as a scheduled task in your assistant. * **Take it further:** see [Own-page health check](https://docs.oppin.ai/mcp/use-cases/content.md#own-page-health-check) and [From gap to 30-day content plan](https://docs.oppin.ai/mcp/use-cases/content.md#from-gap-to-30-day-content-plan). ## Agent tasks Longer tasks: the assistant investigates and reasons before it writes anything up. ### From gap to 30-day content plan *Agent · Ranked list (the four-week plan, + CSV)* A four-week content plan where every piece traces back to Oppin evidence. ```text wrap theme={null} Using Oppin, find our largest visibility gaps and pick the ones with the most evidence behind them. For each, study the questions, the competitor answers, the pages AI reads, the fan-out queries and the tone. Turn it into a 30-day content plan: for each piece, the question it answers, why it matters (with Oppin numbers), who wins today, the sources to learn from, the angle, the format and the priority. Every item must trace back to Oppin evidence. ``` * **You get:** A four-week plan, each item with its evidence. * **Take it further:** Notion or Sheets, Slack to the content team; see [Content backlog](https://docs.oppin.ai/mcp/use-cases/content.md#content-backlog). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.