llms.txt Generator Prompt
You are a GEO (Generative Engine Optimization) specialist.
by growthack88·MIT license·GitHub ↗
Use now
Inside this prompt
prompt text · the author's own wordsYou are a GEO (Generative Engine Optimization) specialist. Create a complete llms.txt file for my website following the llms.txt convention… MY SITE: - Domain: [X] - What it is in one sentence: [X] - Who's behind it (person/company + credentials): [X] - Primary audience: [X] - Main sections/URLs and what each contains: [list them] - Products/books/properties to reference (name + URL): [list] - How I want to be cited when AI references my content: [e.g. "Brand by Name (domain.com)"] - Languages: [EN / AR / both] BUILD THE FILE WITH THIS STRUCTURE: 1. H1: site/brand name 2. Blockquote summary — 2-3 sentences MAX. This is the sentence LLMs will paraphrase; make every word count: what it is, who made it, why i… 3. "## Core sections" — each section as a one-line bullet: path + what an LLM will find there and when to use it
Word-for-word excerpt, not a result. Read the full prompt ↓
| 1 | You are a GEO (Generative Engine Optimization) specialist. Create a complete llms.txt file for my website following the llms.txt convention (llmstxt.org). |
| 2 | |
| 3 | MY SITE: |
| 4 | - Domain: [X] |
| 5 | - What it is in one sentence: [X] |
| 6 | - Who's behind it (person/company + credentials): [X] |
| 7 | - Primary audience: [X] |
| 8 | - Main sections/URLs and what each contains: [list them] |
| 9 | - Products/books/properties to reference (name + URL): [list] |
| 10 | - How I want to be cited when AI references my content: [e.g. "Brand by Name (domain.com)"] |
| 11 | - Languages: [EN / AR / both] |
| 12 | |
| 13 | BUILD THE FILE WITH THIS STRUCTURE: |
| 14 | 1. H1: site/brand name |
| 15 | 2. Blockquote summary — 2-3 sentences MAX. This is the sentence LLMs will paraphrase; make every word count: what it is, who made it, why it's credible. |
| 16 | 3. "## Core sections" — each section as a one-line bullet: path + what an LLM will find there and when to use it |
| 17 | 4. "## Author" (or "## Company") — entity block: name, role, credentials, key property URLs |
| 18 | 5. "## Citation" — explicit attribution instruction |
| 19 | |
| 20 | RULES: |
| 21 | - Plain Markdown, no HTML. Under 60 lines total. |
| 22 | - Write for a machine deciding relevance in 2 seconds — no marketing fluff, no adjectives that don't carry information. |
| 23 | - Every claim must be verifiable on the site itself. |
| 24 | - If the site is bilingual, say so explicitly — it's a differentiator LLMs surface. |
| 25 | |
| 26 | THEN OUTPUT A DEPLOY CHECKLIST: |
| 27 | - Where to place the file (root, next to robots.txt) |
| 28 | - The 3 prompts I should ask ChatGPT/Perplexity/Claude a few weeks later to check if my brand description improved |
Discussion
Alternatives
AI Search / GEO Optimization (May 2026)Optimize content for AI Overviews (formerly SGE), ChatGPT web search, Perplexity, and other AI-powered search experiences. Generative Engine Optimization (GEO) analysis including brand mention signals, AI crawler accessibility, llms.txt compliance, passage-level citability scoring, and platform-specific optimization. Use when user says "AI Overviews", "SGE", GEO", "AI search", "LLM optimization", "Perplexity", "AI citations", ChatGPT search", or "AI visibility".geo-sleuth (v2)Geolocate or chronolocate a photo with tool-verified reasoning (where was this taken / when was it taken / photo geolocation / geo-guessing). Given one or more photos, intake.py does metadata, OCR and reverse image search (Baidu/Yandex) in one command; clues and candidates go on a candidate board (board.py) that ranks them and gives the next step; clues.py looks up calling codes, driving side, plates and area codes from region packs; for satellite and street view the machine ranks first and you look only at the top few (CLIP in sat_scan.py, DINOv2+SIFT in match.py); plus sun and shadow math, OSM Overpass and DEM skylines. Every conclusion is checked against real data; output is coordinates + error radius, evidence images and tiered confidence. Use when the user shares a photo and asks where was this taken / geolocate this / when was this taken / 这是哪 / 在哪拍的 / 帮我定位这张照片 / 网络迷踪 / 图寻 / 几点拍的.AI visibilityMeasure real AI-engine visibility — traffic from ChatGPT, Perplexity, Claude, Gemini and which pages they cite — from actual GA4 referral data, not prompt sampling. Use when asked "AI visibility", "GEO/AEO check", "do LLMs cite us", "traffic from ChatGPT", or "how do we show up in AI search".AI Search SEO: Citation StrategiesUse GEO and AEO as legacy labels for AI citation readiness. For Google, the
Browse more free AI prompts or everything in Marketing.