# Improve Content for AI Search Citations

Web content often lacks the structure and attribution that AI search engines use when selecting citations. This skill explains GEO practices and audits public web pages for citation readiness.

## Install

```bash
npx skillstore add sickn33/geo-fundamentals
```

## Metadata

- Status: approved
- Slug: sickn33-geo-fundamentals
- Skillstore revision: r2
- Version status: missing
- Tree hash: e3409a52635260461a46fb800193ffa3391a1d31c564d209e6588ca46a6bdb67
- Author: sickn33
- GitHub username: sickn33
- License: MIT
- Repository: https://github.com/sickn33/antigravity-awesome-skills/tree/main/skills/geo-fundamentals
- Ref: 88a8e9a07f4c54ab105c1c41b6267c287146b07b
- Supported tools: Claude, Codex, Claude Code
- Audit status: complete
- Agent install advisory: allowed
- Manual install advisory: allowed
- Artifact signature: available
- Audit attestation: unavailable
- Human verification: not\_verified
- Risk factors: external\_commands
- Quality score: 75
- Public page: https://skillstore.pages.dev/skills/sickn33-geo-fundamentals
- Manifest: https://skillstore.pages.dev/api/skills/sickn33-geo-fundamentals/manifest

## Capabilities

- Explains how Generative Engine Optimization differs from traditional search engine optimization.
- Provides checklists for citable content, structured data, author attribution, freshness, and crawler access.
- Finds likely public pages in HTML, JSX, and TSX files within a local project.
- Checks up to 30 pages for JSON-LD, heading structure, author details, and publication dates.
- Detects FAQs, lists, tables, entity markup, statistics, and direct-answer patterns.
- Reports per-page scores, key issues, and an average citation-readiness score.

## Use Cases

- Plan Citable Articles: Build article briefs with clear definitions, sourced data, expert attribution, FAQs, and structured sections.
- Audit Web Components: Review HTML, JSX, and TSX pages for structural signals that support AI retrieval and citation.
- Prioritize GEO Improvements: Compare page scores and reported issues to focus optimization work across a website.

## Prompt Templates

### Learn GEO Basics

```
Explain GEO for a beginner. Compare it with SEO and list five content elements that improve AI citation readiness.
```

### Review a Page Plan

```
Review this page outline for GEO readiness: [outline]. Identify missing definitions, sources, author details, dates, FAQs, lists, and structured data.
```

### Interpret an Audit

```
Interpret this GEO checker output: [results]. Prioritize the three most important improvements and explain how each addresses a reported issue.
```

### Design a Sitewide GEO Program

```
Create a sitewide GEO improvement plan for [site]. Use [audit results], audience needs, content ownership, implementation effort, and measurable citation-readiness indicators.
```

## Limitations

- The checker reads source files only and does not crawl deployed sites or query AI search engines.
- Pattern detection uses regular expressions and can miss dynamic markup or produce false positives.
- All passed checks have equal weight, so the score is not a validated citation probability.
- The checker skips Markdown, documentation, tests, configuration files, build directories, and pages beyond the first 30.

## Best Practices

- Validate automated findings against rendered pages because dynamic content may not appear in source scans.
- Support claims with named, current sources and keep author and date information accurate.
- Use the score to prioritize review, then measure real citations and AI-referred traffic separately.

## Anti Patterns

- Do not present unsourced statistics or invented expert quotes to improve apparent authority.
- Do not treat a high checker score as proof that an AI engine will cite a page.
- Do not add irrelevant schema, repetitive FAQs, or excessive headings only to satisfy checks.

## Security Audit

- Audited at: 2026-07-23T23:29:18.944\+00:00
- Summary: The only static finding is a false positive: SKILL.md line 157 contains a Markdown-formatted usage command, not Ruby or shell execution. No prompt injection, data exfiltration intent, or other semantic security issue was found in the reviewed files.

## Stats

- Views: 96
- Downloads: 15
- Favorites: 0
- Popularity score: 0