Systems Lab

Agent skill

ai-citations-report

Generate an AI Citations Report (GEO) for a domain — which AI-search prompts cite the site across Google AI Overview and ChatGPT, plus organic-traffic context and per-article citation coverage.

activeNeeds a keyActs undeclared403 words

Filed under Analytics and reporting.

From OpenClaudia/openclaudia-skills · 61 skills · 664 · pushed 2026-08-25

What it does when it runs

Generate an AI Citations Report (GEO) for a domain — which AI-search prompts cite the site across Google AI Overview and ChatGPT, plus organic-traffic context and per-article citation coverage. Use when the user asks for an 'AI citations report', 'GEO citations report', or 'which AI prompts cite <domain>'.

Read from the skill and the 0 files bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
  • ENCEPTION_API_KEY
Hosts it reaches
  • www.enception.ai
Tool permissions it declares
No allowed-tools in the frontmatter. It does act, so it runs under whatever permissions your session already grants.
Actions present in the files
shell

Ask about ai-citations-report

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/OpenClaudia/openclaudia-skills.git /tmp/openclaudia-skills
git -C /tmp/openclaudia-skills sparse-checkout set "skills/ai-citations-report"
mkdir -p ~/.claude/skills/ai-citations-report
cp -R "/tmp/openclaudia-skills/skills/ai-citations-report/." ~/.claude/skills/ai-citations-report/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Before you install: this skill will not complete its job on a bare agent. It needs ENCEPTION_API_KEY, which you have to obtain separately.

Reproduced in full from OpenClaudia/openclaudia-skills/blob/221b37d7ab95c14d5343c7b24fd9f9367a3fb400/skills/ai-citations-report/SKILL.md, which is licensed MIT (repository). 403 words, 7 headings.

AI Citations Report

Generate a styled, client-ready GEO report showing which AI-search prompts cite a domain across Google AI Overview and ChatGPT.

This skill is a thin client over the Enception AI Citations API (POST https://www.enception.ai/api/external/ai-citations). Do not re-implement the data pull or report HTML locally — all logic (LLM Mentions pull, cited-vs-retrieved classification, traffic trend, content coverage, HTML→PDF) runs server-side.

Disclosure: This skill was contributed by Enception AI and calls Enception's paid API. Citation data comes from DataForSEO LLM Mentions; traffic figures are modelled estimates.

API docs: https://www.enception.ai/doc/api-ai-citations

Requirements

  • ENCEPTION_API_KEY — access key for the Enception API. Self-serve: sign up at https://www.enception.ai, then generate a free-tier key under Account → API Key (10 reports/month free; contact the team for higher limits).

What it produces

A styled PDF (or HTML/JSON) with:

  • Summary table of every prompt that cited or retrieved the domain
  • Organic traffic, 12-month month-over-month trend, and position distribution
  • Full cited-prompt answer cards with the domain's source highlighted
  • Retrieved-but-not-cited gap cards (content opportunities)
  • Optional per-article citation coverage for URLs you pass in

How to run

curl -X POST https://www.enception.ai/api/external/ai-citations \
  -H 'Content-Type: application/json' \
  -d '{
    "domain": "example.com",
    "brandName": "Example Inc",
    "locationCode": 2840,
    "articles": ["my-article-slug", "https://example.com/articles/another-post"],
    "passcode": "'"$ENCEPTION_API_KEY"'"
  }' \
  -o ai-citations-example.com.pdf

Then open the PDF and visually verify (traffic cards, trend deltas, source highlights) before presenting it.

Options

  • domain (required) — the site to analyze.
  • brandName, locationCode, languageCode, genDate (optional) — default to the domain, 2840 (US), en, and today. Common location codes: 2840 = US, 2826 = UK, 2124 = Canada.
  • articles[] (optional) — article slugs or full URLs for the content-coverage section. Omit to skip that section.
  • format (optional) — pdf (default), html, or json (json returns {citedCount, retrievedCount, promptCount, html}; useful for debugging or piping counts elsewhere).

Honesty guardrails (enforced in the report template)

  • Says "not yet cited in AI answers", never "not indexed" — LLM Mentions verifies AI citations, not Google indexation.
  • Traffic is labelled modelled estimates (DataForSEO), not measured analytics.
  • Never promise future AI citations in client-facing docs — citations are an emergent outcome of content quality, not a deliverable you can guarantee.

Notes

  • Rate limit: 20 requests/hour.
  • A domain with zero AI citations still gets a valid report — the gap cards and traffic context are the value in that case.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what ai-citations-report does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.