geo-skills

A free, open-source GEO (Generative Engine Optimization) skill pack. Built as portable Agent Skills - runs in Claude Code, Codex, and other agents that read skill files.

geo-skills: your site URL into the geo orchestrator, scored across 6 weighted categories into a GEO Score and a prioritized fix list

Traditional SEO ranks you in Google's blue links. GEO gets you quoted inside the AI answer - by ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews. This pack scores how citable your site is to those engines and writes you a prioritized fix list. No dashboard subscription, no paid API required. It runs locally in Claude Code.

What it does

Point the orchestrator at a URL. It crawls your site, runs a panel of specialist subagents, and hands you a single GEO Score (0-100), weighted across 6 categories:

Category	Weight	What it measures
AI Citability	25%	How quotable and extractable your content is for an LLM
Brand Authority	20%	Third-party mentions and entity-recognition signals
Content E-E-A-T	20%	Experience, Expertise, Authoritativeness, Trustworthiness
Technical GEO	15%	AI crawler access, index/preview control (nosnippet), rendering, speed
Schema / Structured Data	10%	Schema.org markup for rich results and entity clarity
Platform Optimization	10%	Presence on the platforms AI models cite

Then it ranks every issue by severity (critical first, quick wins flagged) and gives you a 30-day action plan.

Paste-ready search intelligence prompts

The optional prompt-packs/dataforseo-intelligence
pack turns live search and AI-visibility data into decision-ready reports. It includes
site explorer, keyword research, competitor gap, technical audit, AI visibility,
community-demand, and owner-intent mapping prompts.

These are not generic "write me an SEO report" prompts. Each one has a spend cap,
coverage receipt, evidence-state labels, fail-closed missing-data rules, and an exact
handoff. The owner-intent prompt is the front door to TokenMax: it decides whether to
upgrade, create, consolidate, or hold a page before generation starts.

What's in the pack

GEO core (the flagship):

Skill	What it does
`geo`	The orchestrator. Runs a full GEO audit and produces the composite score.
`geo-audit`	Full website GEO+SEO audit with parallel subagent delegation.
`geo-citability`	Scores content passages (0-100) for AI extractability, suggests rewrites.
`geo-crawlers`	Audits robots.txt and headers for AI crawler access (GPTBot, ClaudeBot, PerplexityBot...).
`geo-ai-index-access`	The hard prerequisites: Bing indexation + IndexNow (ChatGPT's retrieval pipeline), preview-control (nosnippet) audit, server-rendered HTML check.
`geo-fanout`	Query fan-out / topic-cluster optimization: map the sub-query space engines actually retrieve from, engineer titles/slugs for it.
`geo-youtube`	YouTube citation playbook: transcript-first videos, chapters, verbatim-query titles — the rank-free citation lane.
`geo-measurement`	Volatility-aware measurement: share-of-citation prompt panels, position tracking, anti-overreaction reporting.
`geo-llmstxt`	Anti-hallucination facts hedge: validates or generates an `llms.txt` so models get your details right (hygiene, not a visibility lever).
`geo-brand-mentions`	Maps where your brand is cited across the web; scores brand authority.
`geo-platform-optimizer`	Platform-specific optimization for Google AIO, ChatGPT, Perplexity, Gemini, Copilot.
`geo-schema`	Detects, validates, and generates JSON-LD schema for rich results and entity clarity.
`geo-technical`	Technical SEO + GEO checks (crawlability, SSR, rendering, Core Web Vitals).
`geo-content`	E-E-A-T and content-quality assessment for AI citability.
`geo-report` / `geo-report-pdf`	Business-facing GEO reports (markdown + professional PDF).
`geo-proposal` / `geo-prospect` / `geo-compare`	Client tooling: proposals, pipeline, month-over-month deltas (optional, for agencies).
`ai-seo`	The GEO strategy guide - the theory, the 3 pillars, platform-specific tactics.
`token-max-factory`	Point-and-shoot programmatic page factory: scan a site, expand it into hundreds of validated 2,800+ word answer-first pages via Archon. Hard uniqueness gates, packet-only facts, never deploys. Engine: token-max-site-factory.
`tokenmax-fleet-orchestrator`	Resumable, fail-closed controller for sequencing many TokenMax sites through consumer-defined audit, pilot, batch, build, deploy, live-proof, and indexing-queue stages. Includes atomic state, process locking, schema, tests, and systemd templates without hard-coded sites.

Supporting SEO skills:

programmatic-seo · schema-markup · competitor-alternatives · seo-audit · content-strategy · site-architecture

Subagents (in agents/, used by the orchestrator): geo-ai-visibility, geo-content, geo-platform-analysis, geo-schema, geo-technical.

Compatibility

These are standard Agent Skills - each one is a SKILL.md instruction document plus a rubric and output format. That makes them portable:

Runtime	Status	Notes
Claude Code	Native	Full support, including the orchestrator's parallel subagents.
Codex	Works	Drop the skills in `~/.codex/skills/`. Run skills directly.
Other agents (Cursor, Hermes, etc.)	Works	Any agent that loads skill / instruction files can run the individual skills.

The individual skills (citability, crawlers, schema, content, and the rest) are plain instruction docs - any capable agent that can fetch a URL and write a file can run them. The one Claude Code-native piece is the geo orchestrator's parallel subagent fan-out (it launches 5 specialists at once). On other runtimes you invoke the skills directly, or the agent runs them in sequence - same checks, same output. The allowed-tools frontmatter is advisory and is safely ignored by agents that don't use it.

Install

See INSTALL.md. Short version: copy skills/ into your agent's skills directory (~/.claude/skills/ for Claude Code, ~/.codex/skills/ for Codex) and, on Claude Code, agents/ into ~/.claude/agents/. Then:

/geo audit https://yoursite.com

Free-first

Every skill in this pack works with no paid API. Where a third-party data tool could help (rank trackers, backlink suites), it is always marked optional and the skill degrades gracefully without it. Research figures cited in the skills come from published studies and are attributed inline.

The optional DataForSEO prompt pack is intentionally separate from the free core. It
uses DataForSEO's paid-per-use API through the official MCP server, requires an active
account, and tells the agent to stop at the operator's task/row cap. No DataForSEO
credentials belong in a prompt or repository file.

The heavy-artillery skills are token-max-factory, which drives the free, MIT Archon CLI and engine repo, and tokenmax-fleet-orchestrator, which sequences consumer-owned site/deploy adapters. They use the coding-agent subscription already running the pack (codex by default, claude opt-in). Still no SEO APIs, no data vendors, no dashboards.

License

MIT. See LICENSE. Built by SmokeDev. PRs welcome - see CONTRIBUTING.md.