Use Cita where you already work

1. Add the Cita connector to Claude

The connector is how Claude asks Cita a question and gets a dated answer back. It is public and needs no account or key.

1. In Claude, open Settings → Connectors and choose Add custom connector.
2. Name it Cita and paste this URL:

   https://hirecita.com/mcp.json

3. Save. Claude now has tools named check_findability, get_category_citation_map, get_visibility_board, get_weekly_movement and check_sources. The tools that would spend money on your behalf are switched off and say so.

2. Add the free skills

A skill is a short set of instructions that tells Claude how to use the connector for one job and how to write the result for a marketer. Each one is a folder with a SKILL.md inside.

1. Open the skills folder on GitHub: the skills folder of the Cita repository. There is one folder per skill: findability, aiseo-audit, source-check, weekly-report, brief, content-ideas.
2. Download the folder of the skill you want (the whole folder, with its SKILL.md) and zip it.
3. In Claude, open Settings → Capabilities → Skills and upload the zip. Repeat for each skill you want.
4. Then ask in plain words: “can AI read my site?”, “what does ChatGPT read for trail running shoes?”, “check the pages ChatGPT cited for my brand”.

3. Or use the terminal

The cita command asks the same connector from a shell. It needs Node 24 and nothing else; every figure it prints came from the connector with the date it was measured.

# clone the Cita repository (hirecita.com/repo), then in its folder:
npm install
npm run cita -- check yourbrand.com
npm run cita -- map running_apparel
npm run cita -- board
npm run cita -- sources yourbrand.com

Add --json to any command for the connector's raw answer. The commands that would ask ChatGPT on your behalf are switched off and refuse before sending anything.

What it does

• The free check. Can AI read your site? Checks whether the crawlers behind ChatGPT, Claude, Perplexity and Google's AI answers are let in, and whether a sitemap and structured data are there. Free, everywhere. Skill: findability.
• The source map. Map the sources ChatGPT cites in your category, stage by stage, from the buyer's first question to the last. Endurance categories today.
• The live board. The publications ChatGPT cited most this week, per category, re-measured every Monday. Endurance categories today.
• The reading. See where ChatGPT cites your competitors, not you: ask an AI assistant your buyers' questions, several times, and keep who it named and what it read. In Claude, the skill takes a Claude-only reading and says so. Skill: aiseo-audit.
• What changed. What entered and left the assistant's reading list since last time, with the noise floor beside every arrow. Weekly for a category. Skill: weekly-report.
• The cited-page check. Fetch the cited pages (up to 40, newest first) and check each one, so every gap is dated and checkable. Free from Claude and the terminal. A page it could not fetch is reported as not checked, never as broken. Skill: source-check.