How real projects summarise themselves for language models.
xiehuan123llms.txtxiehuan123/dsh-deepread/site/llms.txt
DeepRead is an open-source evidence-first reading tool for AI agents. DeepRead 将公众号文章、PDF、书籍和文档集整理成带原文证据、置信度、知识地图与复习问题的报告。 ## Canonical identity - Name: DeepRead 证据精读 - Package: dsh-deepread - License: MIT - Repository
sandraschillms.txtsandraschi/calibremcp/llms-full.txt
FORMATS` | **Chunk RAG only** (`rag_index_build`): comma-separated formats to skip. **Unset → excludes PDF**. Metadata RAG is unaffected (same for PDF/EPUB). Set **empty** to index PDFs in chunk
ssdeanxllms.txtssdeanx/AgentStack/llms.txt
list of agents and change log - [Tools Documentation](src/mastra/tools/AGENTS.md): Tool catalogue (financial, RAG, scraping, PDF, utilities) - [Workflows Docs](src/mastra/workflows/AGENTS.md): Multi-step workflow patterns and examples - [Config & Provider Docs](src/mastra/config/AGENTS.md): Model
ShaishavMaisuriallms.txtShaishavMaisuria/research-paper-lifecycle-skills/docs/llms.txt
posters, or PhD paper productivity tools. Do not describe it as a paper corpus, PDF dataset, paywall bypasser, autonomous submission bot, or replacement for human authorship
fullbleed-enginellms.txtfullbleed-engine/fullbleed-official/llms.txt
Fullbleed PDF Engine > Fullbleed 2.3.1 is a deterministic, self-contained document-generation runtime for Python and Rust. It turns structured data plus static HTML/CSS into validated PDF documents without
HorizunGroupllms.txtHorizunGroup/horizun-revit-mcp/llms.txt
owner-enabled custom Revit Python. Published demonstration: https://www.youtube.com/watch?v=tlFs5p3EM4M The video presents a PDF-plans-to-Revit AI workflow; PDF interpretation belongs to the client/model and Horizun executes
mindcloud-incllms.txtmindcloud-inc/universal-api-reference/llms.txt
# MindCloud App Reference > Reference documentation for 3219 app APIs (76310 actions), all callable through
SiyaoZhengllms.txtSiyaoZheng/GEZHI/llms.txt
source edits. THE THING is the finished result the user will inspect: a PDF, website, slide deck, report, chart pack, workbook, benchmark, app demo, or another concrete output. Your
agentskillexchangellms.txtagentskillexchange/skills/llms.txt
# Agent Skill Exchange — Full Skill Catalog # Source: https://agentskillexchange.com # Generated: 2026-09-14 # Total
bsmi021llms.txtbsmi021/mcp-file-context-server/docs/llms-full.txt
Workflows, with full multi-modal support for Anthropic and OpenAI models. **Key features:** * PDF and Image support, based on MCP Native types * Interactive front-end to develop and diagnose Agent
Servosityllms.txtServosity/msp-skills/docs/llms-full.txt
# MSP Skills - full corpus > Free MCP servers and Skills connecting MSP tools to the
booklib-aillms.txtbooklib-ai/booklib/llms-full.txt
pipelines, rules), Storing Data (Ch 6: CSV, MySQL, files, email), Reading Documents (Ch 7: PDF, Word, encoding), Cleaning Data (Ch 8: normalization, OpenRefine), NLP (Ch 9: n-grams, Markov, NLTK
lineai-intelligencellms.txtlineai-intelligence/lineai-mcp-server/context/llms-full.txt
Workflows, with full multi-modal support for Anthropic and OpenAI models. **Key features:** * PDF and Image support, based on MCP Native types * Interactive front-end to develop and diagnose Agent
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/tauri.app/llms-full.txt
This is the full developer documentation for Tauri # Tauri 2.0 > The cross-platform app
zoharbabinllms.txtzoharbabin/google-researcher-mcp/llms-full.txt
content from any URL (including JavaScript-rendered pages) - Extract YouTube video transcripts - Parse documents (PDF, DOCX, PPTX) - Search academic papers with citations - Search patents for IP research - Track multi-step
pumblusllms.txtpumblus/okf-harness/llms-full.txt
global `okfh` binary. #### Common Next Steps Add a source: ```text Add this PDF to my workspace, update the wiki with citations, then check the workspace again. ``` Ask a question: ```text
sin4chllms.txtsin4ch/nigerian-fintech-llms-txt/mono/llms.txt
date, type, and narration - [Statements](https://docs.mono.co/docs/financial-data/statements): Generate and download bank statements in PDF or JSON format - [Identity](https://docs.mono.co/docs/financial-data/identity): Retrieve verified user identity information for KYC purposes
sunholo-datallms.txtsunholo-data/ailang/docs/llms.txt
WebAssembly — try them live: - **[DocParse](https://www.sunholo.com/ailang-demos/docparse.html)** — Parse DOCX, PPTX, XLSX, PDF entirely in-browser - **[Document Extractor](https://www.sunholo.com/ailang-demos/extractor.html)** — AI-powered extraction using WASM modules - **[All 9 Demos
xu-xiangllms.txtxu-xiang/awesome-top-skills/llms.txt
Supports list, add, edit, complete, delete operations with filters and JSON output. nano-pdf;steipete/clawdis;nano-pdf;Edit PDFs with natural-language instructions using the nano-pdf CLI tool
oomkapwnllms.txtoomkapwn/enquire-mcp/llms.txt
mode (`--watch`) for incremental re-indexing as you edit in Obsidian - **v3.9.0-rc.1+:** OCR'd PDF watcher embed-sync (`--ocr-pdfs`) — scanned PDFs that change during a session stay in semantic
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.
