ai-search-guruai-search-guru/getcito-worlds-first-open-source-aio-aeo-or-geo-tool/skills/winback/SKILL.md

winback

Skill432 starsChanged 11 days agoMITView on GitHub

Finds pages that lost citations and refreshes them against what AI cites now.

1 other project uses a version of this.

Adopted by

Most recently taken up by

ansvisor/ansvisorword for word, first seen Nov 1, 2026

Other versions1 project uses a version of this.
Word for word · 1
ansvisor/ansvisor★ 233100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- analyzeSkill
- answerfirstSkill
- audit-fixSkill
- auditSkill
- beatSkill
- compareSkill
- createSkill
- factsSkill
- faqSkill
- featuresSkill
- gapsSkill
- getcito-aeo-coachSkill
- getcito-aeo-coach-standaloneSkill
- listingsSkill
- marketsSkill
- new-reportSkill
- opportunitiesSkill
- optimizeSkill
- publishSkill
- qualitySkill
- questionsSkill
- refreshSkill
- reportSkill
- rivalsSkill
- shoppingSkill
- startSkill
- tasksSkill
- translateSkill
- wrongclaimSkill

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Not for a page that was never cited: the Beat a competitor or Comparison page skill fits better.
line 17
Distinctive:
When to check again: after the next tracking runs.
line 39
Distinctive:
Keep the passages AI still quotes word for word.
line 43
Distinctive:
Never say the refresh will bring the citations back, or that a change caused the loss.
line 44
Distinctive:
Never publish yourself: the app decides whether a page goes live, and asks the person unless an Admin allowed this agent to go live on its …
line 45

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Win back lost citations

Find the brand's pages that AI engines stopped citing, see what they cite instead, and refresh the pages to win the citations back.

When to use

"Win back the citations we lost this week", "Which pages lost citations on Google AI Overviews?", "Why did our guide stop being cited?"
Not for a page that was never cited: the Beat a competitor or Comparison page skill fits better.

What to read

list_citations with the owned filter, for the last 7 days and the 7 before (or the periods the person names): the brand's pages and how their citations changed.
get_gsc_summary when Search Console is connected: whether clicks fell with the citations.
get_prompt_performance for the prompts those pages served, lowest visibility first.
list_ai_answers for one or two of those prompts: which pages AI cites now, and what they answer that the brand's page doesn't.
get_fanouts for the topic: questions the page doesn't cover yet.
get_draft when a draft of the page exists: its passages, and which ones AI still quotes (locked).

Steps

Find the pages that lost citations, the biggest loss first; work on two at most in one run.
Compare each with the pages AI engines cite now for the same prompts: newer facts, a direct answer, a table, an FAQ, a date.
Refresh each page: keep, update, add or cut, each change tied to what the cited pages do. Save it as a new version with create_draft, method optimize, with the live page's address as its source; the app asks the person first when it should.
Sending the drafts to the site's CMS, and publishing them, aren't part of this skill: the person does both in the Content Library (Send to CMS, then Publish), or an agent with the Ready to publish skill does.

Output

A table: Page, Citations before, Citations now, Cited instead, Main change.
For each page: the refreshed passages, and what the person must supply as [placeholders].
When to check again: after the next tracking runs.

Don't

Keep the passages AI still quotes word for word.
Never say the refresh will bring the citations back, or that a change caused the loss.
Never publish yourself: the app decides whether a page goes live, and asks the person unless an Admin allowed this agent to go live on its own.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free