seo-geo
Skill10 starsChanged 28 days agoMITView on GitHub
Optimize content to be cited inline by AI answer engines — AI Overviews, ChatGPT, Perplexity, and Bing Copilot. Scores passage-level citability, generates llms.txt, audits AI-crawler access, and recommends structured-data and brand-mention signals. Uses DataForSEO for LLM-mention tracking when connected; otherwise scores citability and gives on-page guidance without live mention data. Trigger when the user says "AI Overviews", "GEO", "generative engine optimization", "AI search optimization", "Perplexity citations", "ChatGPT search", "AI visibility optimization", or "llms.txt".
58 other projects use a version of this.
Adopted by
Most recently taken up by
- FlorentCoulonBS/claude-skillstheir own version, first seen Nov 16, 2026
- martinbattaglia-commits/Claude-skillstheir own version, first seen Nov 16, 2026
- yotamwiesel/claude-skillstheir own version, first seen Nov 16, 2026
- joaoguirunas/team-ostheir own version, first seen Nov 15, 2026
- theexperiencecompany/gaiatheir own version, first seen Nov 13, 2026
- YerayRodri/claude-skillstheir own version, first seen Nov 13, 2026
Used with
Projects with it also use seo-agentic, seo-images and 2 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
AgriciDanielSkillseo-agentic
Audit and fix agent readiness: the Lighthouse Agentic Browsing fraction, accessibility tree for agents, robots.txt and Content-Signal for AI agents, WAF treatment of agent traffic, llms.txt, Markdown delivery, ai-catalog.json, /.well-known discovery files, and WebMCP tools. Use when the user asks whether AI agents can use or browse the site, or about llms.txt or WebMCP. Exclude AI citability and brand signals (seo-geo) and commerce protocol depth (seo-ecommerce).
Also in 5 projects that use this
megastepSkillseo-images
Image optimization analysis for SEO and performance. Checks alt text, file sizes, formats, responsive images, lazy loading, and CLS prevention. Use when user says "image optimization", "alt text", "image SEO", "image size", or "image audit".
Also in 20 projects that use this
timruebenachSkillseo-maps
Maps intelligence for local SEO — geo-grid rank tracking, GBP profile auditing via API, review intelligence across Google/Tripadvisor/Trustpilot, cross-platform NAP verification (Google/Bing/Apple/OSM), competitor radius mapping, and LocalBusiness schema generation from API data. Three-tier capability: free (Overpass + Geoapify), DataForSEO (full intelligence), DataForSEO + Google (maximum coverage). Use when user says "maps", "geo-grid", "rank tracking", "GBP audit", "review velocity", "competitor radius", "maps analysis", "local rank tracking", "Share of Local Voice", or "SoLV".
Also in 10 projects that use this
timruebenachSkillseo-flow
FLOW framework integration — evidence-led SEO using the Find → Leverage → Optimize → Win loop. Surfaces stage-specific AI prompts from the FLOW knowledge base (41 prompts, CC BY 4.0). Use when user says "FLOW", "FLOW framework", "seo flow", "evidence-led SEO", "find leverage optimize win", or wants stage-specific SEO prompts.
Also in 9 projects that use this
Other versions58 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 58
- AgriciDaniel/claude-seo★ 30ksame name
- ReScienceLab/opc-skills★ 1.9ksame name
- theexperiencecompany/gaia★ 327same name
- eunomia-bpf/eunomia.dev★ 244same name
- seranking/seo-skills★ 201same name
- zhtyyx/codex-seo★ 152same name
- PostPlusAI/postplus-skills★ 27same name
- chuhaiqu/skills★ 22same name
- coopersimson96/ai-content-system★ 17same name
- whyashthakker/agent-skills-marketing★ 15same name
48 more not listed
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 repository46 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- blast-promptSkill
- client-outreachSkill
- content-draftSkill
- copywritingSkill
- csv-to-reportSkill
- design-accessibilitySkill
- design-buildSkill
- design-croSkill
- design-dimensionsSkill
- design-motionSkill
- design-researchSkill
- design-system-genSkill
- design-system-persistSkill
- design-tokens-emitSkill
- design-visual-qaSkill
- html-extractSkill
- parallel-buildSkill
- portable-html-portSkill
- qa-gateSkill
- route-codex-reviewSkill
- route-gemini-contextSkill
- route-three-brainSkill
- seo-auditSkill
- seo-backlinksSkill
- seo-clusterSkill
- seo-competitor-pagesSkill
- seo-content-briefSkill
- seo-contentSkill
- seo-dataforseoSkill
- seo-driftSkill
- seo-ecommerceSkill
- seo-firecrawlSkill
- seo-googleSkill
- seo-hreflangSkill
- seo-image-auditSkill
- seo-image-genSkill
- seo-local-unifiedSkill
- seo-pageSkill
- seo-programmaticSkill
- seo-schemaSkill
- seo-sitemapSkill
- seo-strategySkill
- seo-sxoSkill
- seo-technicalSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.
0
Common
Most of the 53 edited versions we read keep these.
3
Distinctive
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: line 81
Tier 1 — DataForSEO MCP: When connected, pull live LLM-mention / AI-visibility tracking to ground the brand-mention recommendations in real …
- Distinctive: line 88
Tier 4 — guided: If no mention data is available, deliver the citability score + on-page fixes and name DataForSEO as the way to add hard …
- Distinctive: line 103
Always end by stating which tier ran and what mention data a higher tier would add.
“Common” is measured: kept by at least 6 in 10 of the 53 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
seo-geo
Family: seo Status: Stable
Purpose
Optimize for AI-powered search, where the win condition is being cited inline by the AI answer, not ranking #1. That requires different content patterns: passages that make specific, verifiable, standalone claims; discoverability via llms.txt and AI-crawler access; and structured data (a top-5 GEO citation factor in the GEO study, Aggarwal et al., KDD 2024).
Triggers
- "ai overviews" / "SGE" / "GEO" / "generative engine optimization"
- "AI search" / "LLM optimization" / "AI visibility optimization" / "ai citations"
- "perplexity" / "chatgpt search" / "bing copilot" / "llms.txt"
Inputs
- A page URL and/or its content (file)
- An optional
robots.txt(file or live) for the AI-crawler-policy verdict - Target platforms (AI Overviews / Perplexity / ChatGPT / all)
Steps
- Run the GEO checker (with the weighted scorecard):
It scores each passage's citability (sourced + self-contained + answer-first → 0-100), counts structured-data blocks, reads the robots AI-crawler policy, and rolls those signals into a weighted 0-100 GEO score with a per-category breakdown (re-normalized over whatever signals are present, so a content-only offline run still scores). Addpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/geo_check.py" --content page.html \ --robots robots.txt --scorecard --human--url https://site.comto also check/llms.txtand fetch live robots. Seereferences/geo-scorecard.mdfor the weight rationale, the passage rubric, and the crawler-verdict semantics. - Passage citability — rewrite the weak passages it lists so each leads with one specific, sourced claim (number/date/named source) that survives extraction.
- Query fan-out coverage — AI Mode splits a query into sub-questions and cites a
passage per sub-question. List the sub-questions the page should answer (PAA,
seo-clusteroutput, sales/support FAQs, comparisons, costs) one per line, then:
Each uncovered question lists its missing terms — the brief for the passage to add. It is a lexical proxy (python3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/geo_check.py" --content page.html --questions subqs.txt --humanreferences/seo-geo/ai-surfaces-2026.md), so read the covered answers too. - llms.txt — generate a curated, valid one and check it (it is low-confidence,
so it is weighted lightest):
Passpython3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/llms_txt.py" --from-urls key-urls.txt --name "Site" --summary "..." --out llms.txt python3 "${CLAUDE_PLUGIN_ROOT}/scripts/seo/llms_txt.py" --validate llms.txt --human--llms llms.txttogeo_check.pyto score a local file offline. - AI-crawler access — read the checker's crawler-policy verdict
(
citable-training-blockedis best practice;retrieval-blockedis the anti-pattern). Ensure retrieval bots (OAI-SearchBot, PerplexityBot, Claude-SearchBot) are allowed so the site stays citable, even if training crawlers are blocked. - Structured data — add Article/Organization/Breadcrumb schema via
seo-schema. - Brand mentions — recommend earning mentions on sources LLMs trust; if the DataForSEO extension is present, pull LLM-mention tracking, else note it.
- Render platform-specific action items per surface (AI Overviews, AI Mode,
ChatGPT search, Perplexity, Claude, Copilot — see
references/seo-geo/ai-surfaces-2026.md), and recommend guarding the access layer withseo-drift --robots(rule D15).
Capability routing
This skill follows the plugin's capability-tier cascade
(references/CAPABILITY-TIERS.md) and always returns a citability report:
- Tier 1 — DataForSEO MCP. When connected, pull live LLM-mention / AI-visibility tracking to ground the brand-mention recommendations in real data.
- Tier 2 — built-in (the default). Otherwise
geo_check.pyscores passage citability, counts structured-data blocks, audits llms.txt + the AI-crawler policy, and emits a weighted 0-100 GEO scorecard entirely offline (--content/--robots/--scorecard/--no-network) — the free, on-page GEO path is the product. - Tier 4 — guided. If no mention data is available, deliver the citability score + on-page fixes and name DataForSEO as the way to add hard mention tracking.
capability: geo-citability
tier1: DataForSEO MCP (LLM-mention / AI-visibility tracking)
tier1_signal: DATAFORSEO_USERNAME | DATAFORSEO_PASSWORD
tier2: geo_check.py (weighted GEO scorecard + passage citability + structured-data count + llms.txt / AI-crawler verdict, no key)
tier2_yields: weighted 0-100 GEO score + per-passage citability + weak passages to fix + crawler-policy verdict, zero spend
tier3: none
tier3_signal: none
tier4: manual GEO checklist; add a DataForSEO MCP for live LLM-mention tracking
needs_tier1: LLM-mention count, AI-answer citation shareAlways end by stating which tier ran and what mention data a higher tier would add.
Outputs
| Output | What it contains | Format | Quality bar (how it is scored) |
| GEO scorecard | weighted 0-100 score + per-category breakdown (passage citability 45 / crawler access 25 / structured data 20 / llms.txt 10), re-normalized over available signals | JSON (geo_score) + --human ASCII | deterministic; names every excluded category; never weights a signal it did not observe |
| Passage citability | per-passage 0-100 (sourced + self-contained + answer-first) + the weak passages to fix | JSON (citability) + ASCII | each weak passage carries a specific, actionable reason; citable stays sourced+standalone+≤120w |
| AI-crawler verdict | retrieval-vs-training stance + verdict (citable-training-blocked … retrieval-blocked) + recommendation | JSON (ai_crawler_policy) | judges against the best practice (stay retrievable, opt out of training); reads real robots grouping |
| Structured-data + brand-mention items | per-platform action items; llms.txt status | prose / Info group | every item carries a concrete fix |
| Tier line | which tier ran + what a higher tier would add | one sentence | states the tier honestly; LLM-mention count ships as a needs_tier1 proxy, never a fabricated number |
Filed to: the user's project workspace. LLM-mention count and AI-answer citation
share are never fabricated — they ship as a labeled needs_tier1 list (add a
DataForSEO / AI-visibility MCP).
Error Handling
| Condition | Detection | Behavior (degrade, never fail) | User-facing message |
| DataForSEO MCP absent | the MCP is not exposed / errors | run geo_check.py for the full offline scorecard | "Ran Tier 2 (geo_check.py). Add a DataForSEO MCP for live LLM-mention tracking." |
| No network / offline | --no-network, or a fetch is blocked | score --content + --robots; exclude llms.txt and re-normalize the scorecard | "Offline — scored content + supplied robots; --url would add llms.txt + live robots." |
| No robots supplied | neither --robots nor a live robots is available | exclude ai_crawler_access from the scorecard and say so | "No robots data — crawler-access category excluded; pass --robots or --url." |
Unreadable --robots file | open() raises | emit a JSON error and exit non-zero (does not invent a verdict) | "Could not read robots file — here is the expected path." |
| Empty / no content | --content missing or unreadable | report the error; score only the signals that exist | "No content scored — pass --content; the passage categories are excluded." |
| Internal / metadata URL | shared net_safety guard refuses it | no fetch happens; report the blocked URL | "Refused an internal/metadata URL (SSRF guard); supply a public URL or --content." |
Dependencies
scripts/seo/geo_check.py(required) — Python 3.10+, standard library onlyscripts/seo/llms_txt.py(required) — llms.txt generate / validate (imported by geo_check)scripts/seo/ai_crawlers.py(required, imported) — shared AI-crawler verdictreferences/seo-geo/ai-surfaces-2026.md(required) — per-surface playbook + fan-out methodseo-schema(structured data); optional DataForSEO (LLM-mention tracking)- Related:
seo-content(shares the citability lens; one-directional graph)
Notes
"AI visibility" here means optimizing content to get cited (the free, on-page
path); to measure/track LLM mentions with hard data, use seo-dataforseo (paid MCP).
GEO moves fast — the AI-crawler list lives in one place, scripts/seo/ai_crawlers.py
(--list prints it; --generate citable-no-training emits a ready robots.txt block),
and the dated landscape facts (AI Overviews / AI Mode sourcing, Google-Extended scope,
llms.txt confidence) live in references/shared/search-landscape-2026.md. Refresh both
quarterly.
The checker degrades gracefully offline (score content with --content alone).
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
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.

