Geo Content Optimizer

GEO Content Optimizer

Optimizes content for AI-generated answers and citation surfaces such as ChatGPT, Perplexity, Gemini, Claude, and AI Overviews.

What This Skill Does

Improves structure, authority signals, factual density, quotable statements, source attribution, and overall GEO readiness.

Quick Start

Optimize this content for GEO/AI citations: [content or URL]
Make this article more likely to be cited by AI systems
Write content about [topic] optimized for both SEO and GEO
Audit this content for GEO readiness and suggest improvements
AI Overview is eating clicks on 12 head queries — build a recovery plan

See AI Overview Recovery for the 4-phase playbook (measure → diagnose → rewrite → monitor) tailored to recovery scenarios (as opposed to generic GEO optimization).

Skill Contract

Expected output: a ready-to-use asset or implementation-ready transformation plus a short handoff summary ready for memory/content/.

• Reads: the brief, target keywords, entity inputs, and quality constraints. Canonical entity profiles: if the content mentions a brand / person / product, this skill MUST consult memory/entities/<slug>.md (per the entity-geo handoff schema) to populate display_name, description_short, ai_resolution_status and decide whether disambiguation boilerplate is needed. If the profile is missing or stale (>90 days), declare DONE_WITH_CONCERNS and recommend entity-registry as an open loop.
• Writes: a user-facing content, metadata, or schema deliverable plus a reusable summary that can be stored under memory/content/.
• Promotes: approved angles, messaging choices, missing evidence, and publish blockers to memory/hot-cache.md and memory/open-loops.md; propose durable decisions as pending-decision items.
• Done when: each target AI query has a standalone, quotable answer block; a before/after GEO score and AI Query Coverage are reported; and the CORE-EEAT GEO self-check (C02, O03, O05, E01) has no unaddressed Fail.
• Primary next skill: use the Next Best Skill below when the asset is ready for review or deployment.

Handoff Summary

Emit the standard shape from skill-contract.md §Handoff Summary Format.

Data Sources

Use ~~AI monitor and ~~SEO tool when connected; otherwise ask for target queries, content, engines, competitor examples, and known AI-citation gaps. See CONNECTORS.md.

Measuring whether GEO work paid off: the changes this skill makes (extractable, quotable, answer-shaped content) move citability — testable in minutes by handing a live-fetch engine the URL and asking the target query. That is a proxy. Whether an engine then cites you unprompted (surfacing) is gated by its crawl/index refresh — week-scale and confounded, not minute-level. Do not conflate the two or promise fast surfacing. The latency of each signal, and why outcome deltas need a control group, are defined in references/measurement-protocol.md.

Keyless AI-citation probe (Tavily): python3 "${CLAUDE_PLUGIN_ROOT}/scripts/connectors/tavily.py" search "<target query>" --answer --limit 10 runs that citability test against a real AI answer engine, no key needed — check whether the synthesized answer cites your URL/domain and where the page ranks among the scored sources. This is Measured for Tavily's own layer and an Estimated proxy for ChatGPT/Perplexity/Google AI Overviews (different indexes, different retrieval). Re-run after shipping changes for a minutes-scale citability read; unprompted surfacing stays week-scale per the paragraph above. See scripts/connectors/README.md.

Instructions

When a user requests GEO optimization, run these five steps:

1. Load CORE-EEAT GEO-First Targets — prioritize C02, C09, O03, O05, E01, O02 plus engine-specific preferences.
2. Analyze Current Content — score clear definitions, quotable statements, factual density, source citations, Q&A format, authority signals, freshness, and structure clarity.
3. Apply GEO Techniques — add standalone 25-50 word definitions, sourced quotable statements, expert/source signals, Q&A/tables/lists, specific data, and visible-content-matching FAQ schema.
4. Generate GEO Output — report Changes Made, before/after GEO score, and AI Query Coverage.
5. CORE-EEAT GEO Self-Check — verify C02, C04, C09, O02, O03, O05, O06, R01, R02, R04, R07, E01, Exp10, Ept08 with Pass/Warn/Fail. Then run the slop self-check to strip AI-tell phrasing before the asset ships.

Label every metric Measured (tool/export), User-provided, or Estimated (model inference); never present an estimate as measured; if a required metric is unavailable, mark it N/A — do not invent it.

Reference: See Instructions Detail for the full CORE-EEAT GEO target tables, AI engine preferences, analysis templates, optimization report template, self-check matrix, and examples.