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.
meshcode-aillms.txtmeshcode-ai/skills/llms.txt
producing verified .docx files via pandoc or docx libraries. Use when user says - [docs-pdf](https://skills.meshcode.ai/skills/docs-pdf/SKILL.md): PDF production — print vs screen route selection, page layout, font embedding
Nizokallms.txtNizoka/pdfnative-mcp/llms.txt
pdfnative-mcp > MCP server for PDF generation, PDF/A archival, PDF/X-4 print exchange (alone or as a dual claim with PDF/A-2), fine typography, right-to-left text, operator fonts, PAdES signing
ogasurfproject-jpgllms.txtogasurfproject-jpg/horizon-shield/llms.txt
cite it. - [JCCDB v1.2.2 paper on Zenodo (DOI)](https://doi.org/10.5281/zenodo.20019572): The accompanying paper (PDF), not the dataset. The dataset itself is deposited separately as a Zenodo Dataset: https://doi.org
olamlabsllms.txtolamlabs/research/llms.txt
behavioral evaluations, and how each model plays. (2026-09-25; canonical https://olamlabs.ai/research/diplomacy; PDF https://olamlabs.ai/research/diplomacy/paper.pdf) - [Multi-Agent Arena: Methodology](https://raw.githubusercontent.com/olamlabs/research/main/posts/multi-agent-arena/multi-agent-arena.md): How Multi-Agent Arena runs
presendappllms.txtpresendapp/presend/llms.txt
binary/file endpoints -- hash, clean-image, malware-check, file-type, image-similarity, merge-and-compress-pdf, qr-scan -- which don't fit an AI agent's text context well). Send
Rao-Abrar-Ahmadllms.txtRao-Abrar-Ahmad/Portfolio/public/llms-full.txt
covering physical print orders, digital document sales, Stripe payment processing with webhook handling, automated PDF generation, and email attachment delivery for digital products. - Built a full-featured organizer
Rao-Abrar-Ahmadllms.txtRao-Abrar-Ahmad/Portfolio/public/llms.txt
covering physical print orders, digital document sales, Stripe payment processing with webhook handling, automated PDF generation, and email attachment delivery for digital products. - Built a full-featured organizer
Rumeasiyanllms.txtRumeasiyan/roomsmith/docs/llms.txt
into > scaled floor plans, wall elevations, isometric cutaways, photoreal renders and a client-ready > PDF report in which every single design change carries a specification, a design reason
sananthanarayanllms.txtsananthanarayan/skilldrop/llms.txt
Excel workbook, web page, CSV, JSON, text file, email (.eml or Outlook .msg) or PDF into clean Markdown - [Use guide-builder](https://raw.githubusercontent.com/sananthanarayan/skilldrop/main/guides/how-to/skills/use-guide-builder.md) *(how-to)*: Turn raw notes
shimo4228llms.txtshimo4228/shimo4228/llms-full.txt
# Shimo (@shimo4228) — AI-Facing Reference Self-contained AI-facing reference for the five practice
shimo4228llms.txtshimo4228/shimo4228/llms.txt
observations, concepts, testimonies, essays - [pdf2anki](https://github.com/shimo4228/pdf2anki): CLI that turns PDF, text, and Markdown files into Anki cards with Claude — Vision-based image cards, review TUI, extraction cache
shuji-bonjillms.txtshuji-bonji/houki-nta-mcp/llms.txt
法基通 1-3の2-N） - 「インボイス」「軽減税率」「電子帳簿」など実務テーマで通達・QA・タックスアンサーを横断検索したい - 改正通達（一部改正通達）の本文と添付 PDF（kind 分類済 / pdf-reader-mcp 連携 hint 付き）を取得したい - 国税局・税務署が依拠する事務運営指針（jimu-unei）を確認したい - 過去の文書回答事例
sohaibdevvllms.txtsohaibdevv/claude-skills/docs/llms-full.txt
markdown deck → single-file HTML presentation with keyboard nav, presenter mode, and print-to-PDF). Output is single-file HTML (Google Fonts + Prism.js CDN the only permitted externals). --- ## Agents
techhorizonlabsPipes a download into a shellllms.txttechhorizonlabs/gearlist/llms-full.txt
uvicorn --host 0.0.0.0 binds every interface. Apache-2.0. Source checked: 2026-10-28 OpenDataLoader PDF | Agent tools https://opendataloader.org A local PDF parser that turns documents into Markdown, JSON with
tstfullyReads credentialsllms.txttstfully/youtube-to-case-study/llms.txt
case-study slideshow: a single self-contained HTML file (reveal.js) with speaker notes, PDF export, and every fact linked to the exact second in the video. Styles: business case study
vish288Reads credentialsllms.txtvish288/mcp-coda/llms-full.txt
Poll with coda_get_export_status; downloadLink expires quickly. Formats: html, markdown. No PDF via API. - Max page content size via API: ~256 KB HTML. - Pack formulas appear as placeholder
vyre-aiPipes a download into a shellllms.txtvyre-ai/vyre/site/llms-full.txt
Word templates from a record and the records linked to it, as Word or PDF. Signing sends a document for signature from a record; the signer needs no account
yubinkim444llms.txtyubinkim444/ai-first-scraper/llms.txt
free Markdown extraction API for LLM and AI agent consumption. Fetches any URL or PDF, strips ads / nav / scripts / trackers, returns clean Markdown. Public instance: https://ai-first-scraper.onrender.com ## Endpoints - `GET /scrape
yubinkim444llms.txtyubinkim444/ai-first-scraper-mcp/llms.txt
Args | Returns | |------|------|---------| | `fetch_page` | `url: str, max_tokens?: int` | Clean Markdown body (HTML or PDF). | | `fetch_pages_batch` | `urls: list[str] (≤25), max_tokens?: int` | Per-URL `{url, ok, data
110kc3Pipes a download into a shellllms.txt110kc3/seo/llms-full.txt
echoempire-machine-foundry) - url: https://foundry.echoempire.org/ - category: api · pricing: paid · tags: scraping, rag, youtube, pdf, apify - Machine-readable catalog of EchoEmpire's pay-per-event Apify Actors for AI agents
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.
