功能描述

Optimize content for AI citation (GEO). Use when user says "GEO", "generative engine optimization", "AI citation", "get cited by AI", "AI-friendly content", or creating content for ChatGPT/Claude/Perplexity visibility.

使用说明 (SKILL.md)

GEO Content Optimizer

Name: GEO Content Optimizer
Author: artyomx33

When To Use

Creating content for AI citation
Refactoring articles for AI compatibility
Improving quotability for AI responses
Competing in AI-first search
Adding authority signals AI systems recognize

Core Concept

SEO = Rank in search results GEO = Get cited in AI-generated answers

The 8 GEO Dimensions

Dimension	Low (1-2)	High (4-5)
Definition Clarity	Vague	Citable definitions with metrics
Quotable Statements	Generic claims	Specific facts with sources
Factual Density	Opinion-heavy	Data-packed
Source Citations	None	Traceable to authority
Q&A Format	Prose only	Explicit Q&A sections
Authority Signals	No credentials	Expert bylines, credentials
Content Freshness	Outdated	Dated citations, recent data
Structural Clarity	Poor hierarchy	Clear headers, lists, tables

The GEO Score

Score each dimension 1-5. Total /40:

32-40: AI-ready
24-31: Needs optimization
16-23: Major work needed

Quick Wins (30-minute edits)

Add specific statistics with dates and sources
Create standalone definition paragraphs
Include expert quotes with credentials
Add comparison tables
Create FAQ section with 5-7 questions
Replace vague claims with verified facts
Insert authoritative source citations

Output Format

## GEO Audit
Current Score: [X]/40

### Dimension Scores
| Dimension | Score | Quick Fix |
|-----------|-------|-----------|
| [dimension] | [1-5] | [action] |

## Optimized Content Sections

### Definition (Citable)
[Term] is [category] that [function], [key metric].

### Key Statistics
- [Stat with source and date]
- [Stat with source and date]

### FAQ Section
**Q: [Common question]?**
A: [Direct, quotable answer with citation]

Integration

Compounds with:

app-planning-skill → Plan content strategy
writing-plans → Structure content projects

See references/dimensions.md for scoring details See references/patterns.md for optimization patterns See references/examples.md for before/after examples

安全使用建议

This is an instruction-only editorial checklist for making content more likely to be cited by LLMs; it doesn't request credentials or install anything, so the direct security risk is low. Before installing, consider: (1) the skill owner is unknown — prefer skills from known authors if you want provenance; (2) SKILL.md references patterns/examples files that are missing from the bundle (harmless but means the skill may be incomplete); (3) the guidance encourages adding expert quotes and citations — avoid fabricating quotes or unverifiable sources (ensure any quoted expert or statistic is real and linked to a legitimate source); (4) do not paste sensitive or proprietary content into the skill's workflows unless you're comfortable with how that data will be used by your agent, since the agent can invoke skills autonomously by default. If you want higher assurance, ask the publisher for the missing reference files or a source/homepage before installing.

功能分析

Type: OpenClaw Skill Name: geo-optimizer Version: 1.0.0 The skill bundle is benign. It consists entirely of markdown files that define a methodology for 'Generative Engine Optimization' (GEO). The files provide instructions and criteria for an AI agent to analyze and optimize content for AI citation. There is no executable code, no external network calls, no attempts at data exfiltration, persistence, or malicious execution. The instructions in SKILL.md and references/dimensions.md are purely descriptive for the task and do not contain any prompt injection attempts to subvert the agent's intended behavior or security.

能力评估

✓ Purpose & Capability

Name/description (GEO content optimization) match the SKILL.md guidance: scoring dimensions, quick fixes, and output templates all target making content more 'AI-citable'. No unexpected binaries, env vars, or cloud credentials are requested.

ℹ Instruction Scope

The runtime instructions are self-contained editorial guidance (scoring rubric, templates, quick wins). They do not instruct the agent to read system files, access secrets, or call external endpoints. One coherence issue: SKILL.md references additional files (references/patterns.md and references/examples.md) that are not present in the bundle — this is likely a packaging omission and reduces usefulness but is not itself a security risk.

✓ Install Mechanism

Instruction-only skill with no install spec and no code files. This is the lowest-risk install profile: nothing is written to disk or fetched at install-time by the skill bundle.

✓ Credentials

The skill declares no required environment variables, credentials, or config paths. The instructions ask for adding citations and expert bylines, which are editorial and do not require secrets.

✓ Persistence & Privilege

Flags show always:false and default model invocation allowed. That is normal. The skill does not request permanent presence or elevated system privileges and does not modify other skills' configs.

版本历史

v1.0.0

Initial release - Optimize content for AI citation (Generative Engine Optimization). By Artem Tolmachev, Teddy Kids, TISA & Claude.

元数据

Slug geo-optimizer

版本 1.0.0

许可证 —

累计安装 7

当前安装数 5

历史版本数 1

常见问题