Geo Content Optimizer

Optimize content for AI citations in ChatGPT, Perplexity, AI Overviews, Gemini, Claude. AI引用优化/GEO优化/AI搜索

Security Scan

The skill is instruction-only and its requested reads/writes (agent memory, connector data) match its stated purpose of optimizing content for AI citation surfaces.

Purpose & Capability

Name and description (GEO / AI-citation optimization) align with the runtime instructions. The skill only uses document templates, analysis rubrics, and memory handoffs appropriate for content optimization; it does not request unrelated credentials, binaries, or installs.

Instruction Scope

The SKILL.md requires reading shared docs (CLAUDE.md, State Model) and agent memory (memory/entities/<slug>.md) and writing handoffs to memory/* files (hot-cache.md, decisions.md, open-loops.md). This is coherent for a content-optimization skill but means it will access and update agent memory and (when connected) external connectors (e.g., Search Console, AI monitor, SEO tool). Review what lives in memory and connector scopes before use.

Install Mechanism

Instruction-only skill with no install spec and no code to execute. No downloads, third-party packages, or binaries are declared — low install risk.

Credentials

No environment variables, credentials, or config paths are requested. The skill references optional connectors (e.g., `~~search console`, `~~AI monitor`, `~~SEO tool`) which are proportional to its purpose but rely on whatever connector permissions the agent has.

Persistence & Privilege

The skill writes structured outputs and promotes items into memory (memory/content/, memory/hot-cache.md, memory/decisions.md, memory/open-loops.md). That is expected for a workflow-oriented skill, but users should be aware it will persist analysis/decisions into agent memory if allowed.

Scan Findings in Context

[no_regex_findings] expected: The static scanner found nothing to analyze because this is an instruction-only skill (no code files). Absence of findings is expected but not evidence of safety; review instructions and memory interactions.

Assessment

This skill appears coherent for GEO/AI-citation optimization. Before installing, confirm: (1) that the agent's memory does not contain sensitive secrets you don't want read or written (the skill explicitly reads/writes memory/entities and memory/* handoff files); (2) which connectors (Search Console, SEO tools, AI monitors) the agent can access and whether you consent to those data connections; (3) that you trust the GitHub source (homepage provided) or inspect the referenced docs (CLAUDE.md, entity-geo handoff schema) if you want deeper assurance. If you prefer, test the skill on non-sensitive sample content first and restrict connector permissions until you’re comfortable with its behavior.

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 references/ai-overview-recovery.md 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, quality constraints, and prior decisions from CLAUDE.md and the shared State Model when available. 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-optimizer 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, memory/decisions.md, and memory/open-loops.md.
• Next handoff: 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.

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.

Reference: See references/instructions-detail.md for the full CORE-EEAT GEO target tables, AI engine preferences, analysis templates, optimization report template, self-check matrix, and examples.

Example

User: "Optimize this paragraph for GEO: 'Email marketing is a good way to reach customers. It's been around for a while and many businesses use it.'"

Output adds a clear definition, dated/source-backed facts, structured list, quotable statements, and a before/after GEO score. See the full pattern in references/instructions-detail.md.

GEO Optimization Checklist

Reference: See the GEO Readiness Checklist in references/geo-optimization-techniques.md for the full checklist covering definitions, quotable content, authority, structure, and technical elements.

Tips for Success

Answer first, be specific, cite dated sources, stay current, match query format, and build authority. Full list in references/instructions-detail.md.

Save Results

On user confirmation, save a dated summary to memory/content/YYYY-MM-DD-<topic>.md and promote key conclusions to memory/hot-cache.md.

Reference Materials

• Instructions Detail - Full 5-step workflow, CORE-EEAT GEO targets, self-check matrix, worked example, tips
• GEO Optimization Techniques - Detailed before/after examples, templates, and checklists for each technique
• AI Citation Patterns - How Google AI Overviews, ChatGPT, Perplexity, and Claude select and cite sources
• Quotable Content Examples - Before/after examples of content optimized for AI citation

Next Best Skill

• Primary: content-quality-auditor — verify the optimized content is strong enough to ship and cite.