Systems Lab

Agent skill

geo-difficulty

Score how hard a keyword is to rank for in the AI-search era — page-level URL Rating of real competitors (not just domain DR), Ahrefs keyword difficulty, and whether a given site already ranks or is cited in Google's AI Overview.

activeReaches the webActs undeclared358 words

Filed under Content and SEO.

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

What it does when it runs

Score how hard a keyword is to rank for in the AI-search era — page-level URL Rating of real competitors (not just domain DR), Ahrefs keyword difficulty, and whether a given site already ranks or is cited in Google's AI Overview. Use when the user asks 'how hard is <keyword> to rank', 'geo difficulty for <keyword>', or 'keyword difficulty for <domain>'.

Read from the skill and the 1 file 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
None found.
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 geo-difficulty

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

Install it

View source on GitHub ↗
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/geo-difficulty"
mkdir -p ~/.claude/skills/geo-difficulty
cp -R "/tmp/openclaudia-skills/skills/geo-difficulty/." ~/.claude/skills/geo-difficulty/

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.

The skill

Source on GitHub ↗

Reproduced in full from OpenClaudia/openclaudia-skills/blob/221b37d7ab95c14d5343c7b24fd9f9367a3fb400/skills/geo-difficulty/SKILL.md, which is licensed MIT (repository). 358 words, 4 headings.

GEO Difficulty

Score keyword ranking difficulty for the AI-search era. Unlike plain Ahrefs KD or domain DR, this:

  • uses page-level URL Rating (UR) of the results that actually target the query — so a generic article on a huge domain (e.g. mckinsey.com) stops inflating the score;
  • is client-relative — the same SERP is a wall for a no-name site but ~won for a site already ranking or cited in Google's AI Overview;
  • folds in the AI Overview citation as a first-class signal.

Disclosure: contributed by Enception AI. Backed by the free public API behind https://www.enception.ai/tools/geo-difficulty (POST https://www.enception.ai/api/tools/geo-difficulty, no API key). Server-side data comes from Ahrefs and SerpAPI.

Usage

bash scripts/score.sh "ai form real estate" "ai slide legal" --client example.com
  • Pass one or more keywords (quote each). Up to 10 per call.
  • --client <domain> is optional; add it to get the client-relative verdict (WON / FOOTHOLD / NOT RANKING).
  • GEO_DIFFICULTY_URL env var overrides the endpoint (rarely needed).

Or call the API directly:

curl -s -X POST https://www.enception.ai/api/tools/geo-difficulty \
  -H 'content-type: application/json' \
  -d '{"keywords":["ai presentation maker"],"client":"example.com"}' --max-time 150

Output columns

  • absolute — difficulty 0–100 for a brand-new site (0.35·KD + 0.40·median competitor page-UR + 0.25·targeting%).
  • client_verdict / client_diff — only with --client. WON (top-3 or AI-Overview cited), FOOTHOLD (ranks 4–10), NOT RANKING (with the gap to close, credited for the client's DR).
  • KD — Ahrefs keyword difficulty; - for zero-volume long-tail.
  • UR — median page-level URL Rating of the real competitors.
  • tgt% — share of the top-10 that actually target the query.
  • AIO — cited (client in the AI Overview), Nsrc (AIO shown, N sources), none, or n/a (AIO not available for this query).
  • competitors — the targeting results with their UR.

Notes

  • The AI Overview leg depends on Google actually showing an AIO for the query (intermittent); it degrades gracefully to none/n/a.
  • Numbers shift day to day as SERPs and UR change — treat as a current snapshot, not a fixed grade.
  • Each keyword takes a few seconds server-side; keep --max-time generous for batches.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

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 geo-difficulty 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.