How real projects summarise themselves for language models.
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
damionrashfordllms.txtdamionrashford/RivalSearchMCP/docs/llms.txt
source discovery and key finding extraction - [Document Analysis](https://github.com/damionrashford/RivalSearchMCP#tools): Extract text from PDF, Word, Text, and Images with EasyOCR - [Scientific Research](https://github.com/damionrashford/RivalSearchMCP#tools): Academic paper search
JasonColapietrollms.txtJasonColapietro/suede-creator-skills/docs/llms.txt
skills, and a ninety-day practice plan. Source Markdown: https://github.com/JasonColapietro/suede-creator-skills/tree/main/book. Print edition (PDF): https://skills.suedeai.ai/book/s-tier.pdf ## Workflow skills: from planning a change to grading whether it ships - [Suede
deepnoodle-aiReads credentialsllms.txtdeepnoodle-ai/dive/llms.txt
TextContent` - Plain text (most common) - `ImageContent` - Image from URL or inline bytes - `DocumentContent` - Document (PDF, etc.) from URL or inline bytes, with optional citations - `ToolUseContent` - Tool call requested
hemanthllms.txthemanth/piragi/playground/llms.txt
chunking, embedding, storage) and `RetrievalPipeline` (query transformation, parallel search, reranking, answering). - **Format Support**: Markdown, PDF, Word, Excel, source code, text files, and remote blob storage (`s3://`, `gs://`, `az://`, web crawling
cjnonamellms.txtcjnoname/excelts/llms.txt
documonster > Zero-dependency TypeScript toolkit for Excel (XLSX/XLSB), Word (DOCX), PDF, CSV, Markdown, XML, ZIP/TAR and > Mermaid diagrams. ESM-only, Node.js >= 22.13, Bun and modern browsers. Every module
mycelium-ioPipes a download into a shellllms.txtmycelium-io/mycelium/docs/llms-full.txt
# Mycelium Documentation (full) Coordination layer for multi-agent systems. Concatenated from the source docs
trahloffllms.txttrahloff/Aldine/site/llms.txt
errors back with file and line, fixes them and typesets again, and shows the PDF in the chat (inline on claude.ai, Claude Desktop and Cowork; a signed link in Claude
sandbaseaillms.txtsandbaseai/deepseek-harness-handbook/site/llms.txt
production boundaries. ## Download - [DeepSeek Harness Field Guide v0.1.0](https://github.com/sandbaseai/deepseek-harness-handbook/releases/download/v0.1.0/DeepSeek-Harness-Field-Guide-v0.1.0.pdf): Ten-page visual PDF for onboarding and offline reference. ## Project boundary This is a community-maintained handbook from SandBase
ScraperNodellms.txtScraperNode/awesome-n8n-templates/public/llms-full.txt
internet and delivers 18. AI-powered WhatsApp chatbot for text, voice, images, and PDF with RAG URL: https://scrapernode.github.io/awesome-n8n-templates/templates/support-chatbot/4827-ai-powered-whatsapp-chatbot-for-text-voice-images-and-pdf-with-rag/ Views: 259,051 ### Who is this for? This template
ScraperNodellms.txtScraperNode/awesome-n8n-templates/public/llms.txt
views) - https://scrapernode.github.io/awesome-n8n-templates/templates/personal-productivity/8527-learn-n8n-basics-in-3-easy-steps/ 18. AI-powered WhatsApp chatbot for text, voice, images, and PDF with RAG (259,051 views) - https://scrapernode.github.io/awesome-n8n-templates/templates/support-chatbot/4827-ai-powered-whatsapp-chatbot-for-text-voice-images-and-pdf-with-rag/ 19. Analyze Landing Page with OpenAI
agents-uillms.txtagents-ui/agents-kit/llms-full.txt
# Agents Kit 0.3.0 > React components for voice agents, conversations, generated results, and agent interactions
JSv4llms.txtJSv4/Docxodus/docs/llms.txt
documents into a redline with native tracked changes, render DOCX to HTML or PDF, project DOCX to anchor-addressed markdown, and edit a document in place — programmatically, from
omarluqReads credentialsllms.txtomarluq/cc-relay/llms.txt
header (not `api-key`), deployment names as model IDs - **Ollama**: No prompt caching, no PDF support, base64 images only ### Routing Strategies 1. `simple-shuffle` - Weighted random (default) 2. `round-robin
skulitomllms.txtskulitom/Pixelbolt/llms.txt
# Pixelbolt > An MIT-licensed, zero-dependency pixel art and sprite animation toolkit for AI
sfrangulovPipes a download into a shellllms.txtsfrangulov/claude-code-handbook-ru/llms-full.txt
память, рабочие процессы, скиллы, агенты и CLI-флаги на одном листе. Скачай [готовый PDF](./cheatsheet/cheatsheet.pdf) или распечатай страницу сам через `⌘P`. --- ## С чего начать - **Первый запуск.** Пройди [быстрый старт](#quickstart
sfrangulovllms.txtsfrangulov/claude-code-handbook-ru/llms.txt
разделами Skills / Sub-agents / Plugins / Hooks / MCP / Templates - [Шпаргалка на одну страницу (HTML + PDF)](https://sfrangulov.github.io/claude-code-handbook-ru/): печатная reference-карточка A4 portrait — горячие клавиши, слэш-команды, MCP, память, workflows
UpstageAIReads credentialsllms.txtUpstageAI/korean-tax-calc-mcp/llms.txt
tools, tax years 2016–2026, deterministic code (no generative AI except 3 optional PDF tools). Install: `uvx korean-tax-calc-mcp` (Claude Code: `claude mcp add korean-tax-calc
jangtrinhllms.txtjangtrinh/design-os-studio/docs/llms-full.txt
Visual Proof & Diff** | Automated CI screenshot capture and pixel and SSIM comparison | `PNG` / `SVG` / `PDF` / `JPG` + diff report | `designos-studio --gpu --screenshot` + `designos-diff` | --- ### Figma-style micro-interactions The Studio
ClickHousellms.txtClickHouse/loom/llms.txt
search and RAG for agents](docs/use-cases/document-search.md): Loom indexes your documents (Markdown and text, and PDF, `.docx` and `.pptx` files that its extractor service converts) and lets agents search them with
gizmaxReads credentialsllms.txtgizmax/Sandcastle/llms-full.txt
connector name (slack, teams, gmail, ...). - report: `report_config: { template: research-report, format: pdf, theme: professional, title, author }`. Renders a branded PDF. - sub_workflow: `sub_workflow: { workflow: "summarize", input_mapping: { text
A markdown file at a website's root that gives language models a short guide to the site and links to the pages worth reading.
The same idea with the content included, so an agent can read the documentation in one request.
Agents and tools that fetch documentation on someone's behalf. It's a proposal, not a standard, and support varies.
Start with a one-line summary, then sections of links with a sentence each. The examples here show what real projects do.
