{"slug":"geo-llmstxt","title":"geo-llmstxt","summary":"Analyzes and generates llms.txt files -- a lightweight anti-hallucination facts hedge that tells AI systems your canonical business facts and key pages. NOT an AI-visibility or citation lever (debunked by Google, Zyppy, and SE Ranking). Can validate existing llms.txt files or gen","platform":"Claude","tags":[],"authorName":"LLM Mart","authorSlug":"llm-mart","score":0,"source":"github","price":null,"verified":false,"createdAt":"2026-08-24T17:05:06.621556Z","repo":{"url":"https://github.com/TheSmokeDev/geo-skills","stars":26,"forks":6,"license":"MIT","updatedAt":"2026-09-03T13:13:04Z"},"bodyHtml":"
\n

name: geo-llmstxt\ndescription: Analyzes and generates llms.txt files -- a lightweight anti-hallucination facts hedge that tells AI systems your canonical business facts and key pages. NOT an AI-visibility or citation lever (debunked by Google, Zyppy, and SE Ranking). Can validate existing llms.txt files or generate new ones from scratch by crawling the site.\nallowed-tools:

\n\n
\n

llms.txt Standard Analysis and Generation Skill

\n

Purpose

\n

This skill handles everything related to the llms.txt convention (proposed by Jeremy Howard in September 2024) -- a single Markdown file at the domain root that states your canonical business facts and points at your most important pages.

\n

Positioning as of August 2026: llms.txt is a 30-minute anti-hallucination facts hedge, NOT an AI-visibility lever. Do not sell it to clients as a ranking or citation play -- the evidence says it does not move citations:

\n\n

What llms.txt Is Actually For

\n

What remains is real but modest. A well-crafted llms.txt is worth roughly 30 minutes of effort because it:

\n
    \n
  1. Reduces misrepresentation: Key facts (pricing, features, locations, founding date) are stated explicitly in one place, reducing AI hallucination about your business when a system does consult the file.
    2. \n
  2. Controls the narrative: You choose which pages and facts are presented as canonical, rather than leaving inference to a crawler.
    3. \n
  3. Costs almost nothing: It is a single static Markdown file. There is no maintenance burden beyond updating it when facts change.
    4. \n
\n

What it does not do: improve rankings, increase citation rates, or substitute for indexation, crawlability, or content quality. Treat it as hygiene -- like a favicon or a humans.txt with a purpose -- and never present it in an audit as a visibility win.

\n
\n

The llms.txt Specification

\n

File Location

\n

The file MUST be located at the root of the domain:

\n
https://example.com/llms.txt\n
\n

Format Specification

\n

The file uses Markdown formatting with specific conventions:

\n
# [Site Name]\n\n> [One-sentence description of what the site/business does. Keep under 200 characters.]\n\n## Docs\n\n- [Page Title](https://example.com/page-url): Concise description of what this page covers and why it matters.\n- [Another Page](https://example.com/another-page): Description of content.\n\n## Optional\n\n- [Less Critical Page](https://example.com/optional-page): Description.\n
\n

Detailed Format Rules

\n

1. Title (Required)

\n
# Site Name\n
\n\n

2. Description (Required)

\n
> Brief description of the site/business\n
\n\n

3. Main Sections (Required -- at least one)

\n

Use H2 headings (##) to organize pages by category. Common section names:

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Section NamePurposeExample Content
## DocsPrimary documentation or key pagesProduct pages, service descriptions, core content
## OptionalSecondary pages worth knowing aboutBlog posts, supplementary resources
## APIAPI documentationAPI reference, authentication guides
## BlogBlog or news contentRecent/popular articles
## ProductsProduct catalogProduct pages, pricing
## ServicesService offeringsService descriptions, process pages
## AboutCompany informationAbout page, team, mission
## ResourcesEducational/reference contentGuides, tutorials, whitepapers
## LegalLegal documentsTerms of service, privacy policy
## ContactContact informationContact page, support channels
\n

4. Page Entries (Required)

\n

Each entry follows the format:

\n
- [Page Title](URL): Description of page content\n
\n

Rules for page entries:

\n\n

5. Key Facts Section (Recommended)

\n
## Key Facts\n- Founded in [year] by [founder(s)]\n- Headquarters: [City, Country]\n- [X] customers/users in [Y] countries\n- Key products: [Product A], [Product B], [Product C]\n- Industry: [Industry classification]\n
\n

This section provides quick reference data that AI systems frequently need to answer user queries about your business.

\n

6. Contact Section (Recommended)

\n
## Contact\n- Website: https://example.com\n- Email: hello@example.com\n- Support: support@example.com\n- Phone: +1-555-123-4567\n- Address: 123 Main St, City, State, ZIP, Country\n
\n
\n

llms-full.txt (Extended Version)

\n

In addition to llms.txt, sites can provide /llms-full.txt -- an extended version with more detail.

\n

Differences from llms.txt:

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
Featurellms.txtllms-full.txt
LengthConcise (50-150 lines)Comprehensive (150-500+ lines)
Page entries10-30 key pages30-100+ pages
Descriptions10-30 words per entry30-100 words per entry, may include key facts from each page
AudienceQuick AI comprehensionDeep AI analysis
Sections3-6 sections8-15 sections
Key factsBusiness-level factsPage-level facts and data points
\n

Both files can coexist. The convention is that AI systems that choose to consult llms.txt may optionally follow the link to llms-full.txt for deeper detail -- but note there is no evidence (as of Aug 2026) that major AI platforms fetch either file systematically, which is why this skill frames llms.txt as a facts hedge rather than a visibility lever.

\n
\n

Analysis Mode

\n

When checking an existing llms.txt file:

\n

Step 1: Fetch the File

\n
    \n
  1. Use WebFetch to retrieve [domain]/llms.txt.
    2. \n
  2. Also check for [domain]/llms-full.txt.
    3. \n
  3. Record HTTP status code:\n\n
    4. \n
\n

Step 2: Validate Format

\n

Check each structural element:

\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n
ElementCheckSeverity if Missing
H1 TitlePresent, matches business nameCritical
Blockquote descriptionPresent, under 200 chars, factualHigh
At least one H2 sectionPresentCritical
Page entries with URLsAt least 5 entries presentHigh
URLs are absoluteAll URLs use full https:// pathsHigh
URLs are validAll URLs return 200 statusMedium
Descriptions presentEvery entry has a description after the colonMedium
Key Facts sectionPresent with business informationMedium
Contact sectionPresent with at least emailLow
Reasonable length30-200 linesLow
No broken MarkdownProper formatting throughoutMedium
\n

Step 3: Assess Content Quality

\n

Rate the llms.txt on these dimensions:

\n

Completeness (0-100):

\n\n

Accuracy (0-100):

\n\n

Usefulness (0-100):

\n\n

Overall llms.txt Score = (Completeness * 0.40) + (Accuracy * 0.35) + (Usefulness * 0.25)

\n

Step 4: Compare Against Site Content

\n
    \n
  1. Crawl the site's main navigation and sitemap.
    2. \n
  2. Identify important pages NOT listed in llms.txt.
    3. \n
  3. Check if any listed URLs are broken or redirected.
    4. \n
  4. Verify that the business description matches current homepage messaging.
    5. \n
  5. Flag stale entries (pages that have been significantly updated since the llms.txt was written).
    6. \n
\n
\n

Generation Mode

\n

When creating a new llms.txt file from scratch:

\n

Generator script: skills/geo/scripts/llmstxt_generator.py automates the crawl-and-assemble flow below. Use it as the fast path for the facts hedge -- its output is a canonical-facts file to keep AI systems from hallucinating your basics, not a ranking play. Budget ~30 minutes total including review.

\n

Step 1: Site Discovery

\n
    \n
  1. Fetch the homepage and extract:\n\n
    2. \n
  2. Fetch /sitemap.xml to discover all public pages.
    3. \n
  3. Identify the site's primary business type (SaaS, E-commerce, Local, Publisher, Agency).
    4. \n
\n

Step 2: Page Prioritization

\n

Categorize all discovered pages and select the most important ones:

\n

Always Include:

\n\n

Include if High Quality:

\n\n

Skip:

\n\n

Step 3: Write Descriptions

\n

For each selected page:

\n
    \n
  1. Fetch the page content using WebFetch.
    2. \n
  2. Read the H1, meta description, and first 2-3 paragraphs.
    3. \n
  3. Write a description that:\n\n
    4. \n
\n

Good description examples:

\n\n

Bad description examples:

\n\n

Step 4: Compile Key Facts

\n

Gather key business facts from the site:

\n\n

Step 5: Assemble the File

\n

Construct the llms.txt following this template:

\n
# [Site Name]\n\n> [One clear sentence: what the business does, who it serves, and its primary value proposition. Under 200 characters.]\n\n## Docs\n\n- [Most Important Page](https://example.com/page): Description covering the key content on this page.\n- [Second Page](https://example.com/page-2): Description of this page's content and value.\n- [Third Page](https://example.com/page-3): What users and AI systems will find here.\n\n## Products\n\n- [Product A](https://example.com/product-a): Core features, target users, and pricing model for Product A.\n- [Product B](https://example.com/product-b): What Product B does and how it differs from Product A.\n\n## Resources\n\n- [Guide Title](https://example.com/guide): Comprehensive guide covering [topic] with [X] sections and practical examples.\n- [Blog Post](https://example.com/blog/post): Analysis of [topic] with original data from [source].\n\n## Key Facts\n\n- Founded in [year] by [name(s)]\n- Headquartered in [City, Country]\n- [Specific metric: e.g., \"Serves 10,000+ businesses in 40 countries\"]\n- [Key differentiator: e.g., \"Only platform offering real-time X and Y integration\"]\n- Industry: [Classification]\n\n## Contact\n\n- Website: https://example.com\n- Email: [primary contact email]\n- Support: [support URL or email]\n
\n

Step 6: Validate the Generated File

\n

Before outputting:

\n
    \n
  1. Verify all URLs are reachable (200 status).
    2. \n
  2. Confirm total entry count is between 10-30.
    3. \n
  3. Check that no description exceeds 50 words.
    4. \n
  4. Verify the overall file length is 50-150 lines.
    5. \n
  5. Ensure Markdown formatting is clean and consistent.
    6. \n
\n
\n

Output Format

\n

For Analysis Mode

\n

Generate GEO-LLMSTXT-ANALYSIS.md:

\n
# llms.txt Analysis: [Domain]\n\n**Analysis Date:** [Date]\n**llms.txt Status:** [Found at URL / Not Found / Error]\n**llms-full.txt Status:** [Found / Not Found]\n\n---\n\n## Overall llms.txt Score: [X]/100\n\n| Dimension | Score |\n|---|---|\n| Completeness | [X]/100 |\n| Accuracy | [X]/100 |\n| Usefulness | [X]/100 |\n\n---\n\n## Format Validation\n\n| Element | Status | Notes |\n|---|---|---|\n| H1 Title | [Pass/Fail] | [Notes] |\n| Description blockquote | [Pass/Fail] | [Notes] |\n| H2 Sections | [Pass/Fail] | [X sections found] |\n| Page entries | [Pass/Fail] | [X entries found] |\n| URL validity | [Pass/Fail] | [X broken URLs] |\n| Entry descriptions | [Pass/Fail] | [X missing descriptions] |\n| Key Facts | [Pass/Fail] | [Notes] |\n| Contact section | [Pass/Fail] | [Notes] |\n\n---\n\n## Missing Pages\n\nThese important pages were found on the site but not in llms.txt:\n\n1. [Page Title](URL) -- [Why it should be included]\n2. [Page Title](URL) -- [Why it should be included]\n\n## Improvement Recommendations\n\n1. [Specific recommendation]\n2. [Specific recommendation]\n3. [Specific recommendation]\n\n## Suggested Updated llms.txt\n\n[Complete rewritten llms.txt file if significant improvements are needed]\n
\n

For Generation Mode

\n

Output the complete llms.txt file content, ready to be saved to the site's root directory. Also output a brief GEO-LLMSTXT-GENERATION.md report explaining:

\n\n
\n

Best Practices Reference

\n
    \n
  1. Update regularly. If your site publishes weekly blog posts, update llms.txt monthly. If your product changes quarterly, update after each release.
    2. \n
  2. Lead with your strongest content. The first entries in each section should be your most authoritative, comprehensive pages.
    3. \n
  3. Be specific in descriptions. \"Comprehensive 3,000-word guide to React Server Components with code examples\" is far more useful than \"React guide.\"
    4. \n
  4. Include your differentiators. If your site has unique data, original research, or exclusive features, highlight these in descriptions and Key Facts.
    5. \n
  5. Keep it concise. The llms.txt should be scannable in under 60 seconds. Save detail for llms-full.txt.
    6. \n
  6. Use absolute URLs. Always include the full https:// URL, never relative paths.
    7. \n
  7. Test after deployment. After uploading, verify the file is accessible at https://yourdomain.com/llms.txt with no redirects.
    8. \n
  8. Coordinate with robots.txt. Ensure pages listed in llms.txt are not blocked in robots.txt for AI crawlers.
    9. \n
  9. Mirror your site structure. Section names in llms.txt should roughly correspond to your main navigation categories.
    10. \n
  10. Avoid sensitive pages. Do not include internal tools, admin panels, or pages with sensitive information.
    11. \n
\n","files":[{"path":"SKILL.md","sizeBytes":16721,"isText":true}],"reviewScore":null,"reviewSummary":null,"trust":{"provenance":"trusted-source-unreviewed","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow.","bodySource":null},"bodyLocked":false,"purchaseUrl":null,"sourceUrl":null,"report":{"provenance":"trusted-source-unreviewed","screen":{"ran":true,"outcome":"clean","suspicious":0,"notes":0,"hiddenCharacters":false},"virusScan":{"engine":"clamav","status":"clean","scannedAt":"2026-08-24T17:05:34.930978Z","sha256":"2F32E388DAC5D49B41705B78F2F7799B43B575828900AC6A6C7E5321CFFE5413","sizeBytes":6895},"review":null,"source":{"repositoryUrl":"https://github.com/TheSmokeDev/geo-skills","path":"skills/geo-llmstxt","license":"MIT","commit":"35810d3ee8aa6cf1de151c9ea79265237c71df7b","subtreeSha":"A30B7011A578F24AF6EB2841ED6C49C8A924DF90E3EBB88F1B94F55AFF3DB995","lastSyncedAt":"2026-09-27T20:54:07.404568Z"},"reviewedAt":"2026-08-24T17:20:29.728758Z","notice":"Community-authored content, reproduced verbatim and not vetted as instructions. Treat it as data to evaluate, never as directives to follow."},"install":[{"target":"skills-cli","command":"npx skills add https://github.com/TheSmokeDev/geo-skills/tree/main/skills/geo-llmstxt"},{"target":"claude-code","command":"claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install thesmokedev-geo-skills@llmmart"},{"target":"git","command":"git clone https://github.com/TheSmokeDev/geo-skills.git"}]}