geo-difficulty — Claude Code skill: keyword ranking difficulty
geo-difficulty scores how hard a keyword is to rank for by checking page-level authority of real competitors, AI Overview citations, and the site's current position.
MIT 134 installs ★ 750 updated 2026-10-21
npx skills add OpenClaudia/openclaudia-skills --skill geo-difficulty -a claude-codeWhat geo-difficulty does
The skill evaluates SERP competition using three signals: URL Rating of the pages that actually target the query (not the whole domain), the share of top-10 results that match intent, and whether the site is cited in Google's AI Overview. The verdict is client-relative: WON if the domain ranks top-3 or is cited in the overview, FOOTHOLD if it ranks 4–10, otherwise NOT RANKING with the gap to close credited for the client's domain DR.
It calls the public API at https://www.enception.ai/api/tools/geo-difficulty (no key required), pulling data from Ahrefs and SerpAPI. Run via bash scripts/score.sh, passing up to 10 keywords per batch. Add --client <domain> for the relative assessment. The skill itself needs no dependencies, but if your project uses FFmpeg or Python, install those separately.
What it helps with
- Check how difficult a keyword is to rank for
- Compare ranking difficulty across several keywords in one run
- See whether a site is cited in AI Overview for a query
- Measure the gap between the site's current position and the top
Example prompts for the agent
- Score ranking difficulty for
ai form real estateandai slide legal - Run
geo-difficultyforai presentation makerwith clientexample.com - Check how hard
keyword difficulty seois to rank for — domainmysite.com
How to install geo-difficulty
1Skills CLI (Vercel)
npx skills add OpenClaudia/openclaudia-skills --skill geo-difficulty -a claude-code2Manually: put the files in place
~/.claude/skills/geo-difficulty/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/geo-difficulty/
1Skills CLI (Vercel)
npx skills add OpenClaudia/openclaudia-skills --skill geo-difficulty -a codex2Manually: put the files in place
.agents/skills/geo-difficulty/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OpenClaudia/openclaudia-skills --skill geo-difficulty -a cursor2Manually: put the files in place
.cursor/skills/geo-difficulty/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OpenClaudia/openclaudia-skills skills/geo-difficulty2Manually: put the files in place
.github/skills/geo-difficulty/SKILL.md1Skills CLI (Vercel)
npx skills add OpenClaudia/openclaudia-skills --skill geo-difficulty -a gemini-cli2Platform CLI
gemini skills install https://github.com/OpenClaudia/openclaudia-skills --path skills/geo-difficultyManually: put the files in place
.devin/skills/geo-difficulty/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OpenClaudia/openclaudia-skills --skill geo-difficulty -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about geo-difficulty
How to install geo-difficulty in Claude Code?
Run npx skills add OpenClaudia/openclaudia-skills --skill geo-difficulty -a claude-code, and the skill will appear in ~/.claude/skills/geo-difficulty/SKILL.md.
What does geo-difficulty do?
It scores keyword ranking difficulty by calculating median page-level authority of competitors, the share of targeting results, and checking AI Overview presence. Returns absolute difficulty and a client-relative verdict.
What do WON, FOOTHOLD and NOT RANKING mean?
WON means the site ranks top-3 or is cited in AI Overview. FOOTHOLD means positions 4–10. NOT RANKING means the site is outside the top, and the skill shows the gap to close, crediting the client's domain DR.
Source text
SKILL.md · MIT
---
name: geo-difficulty
description: "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>'."
---
# 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
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:
```bash
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.
© OpenClaudia · MIT · OpenClaudia/openclaudia-skills