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.
JAYcodrllms.txtJAYcodr/claude-code-ultimate-guide-zh/llms.txt
/optimize, /git-worktree - Hooks: dangerous-actions-blocker, prompt-injection-detector, secrets-scanner (bash + PowerShell) - Skills: pdf-generator, tdd-workflow, guide-recap, landing-page-generator, skill-creator - Scripts: session-search, audit-scan
urbanmorphllms.txturbanmorph/mdshare/public/llms.txt
focused PDF/DOCX/PPTX/HTML conversion with table recovery (IBM) - [Marker](https://github.com/VikParuchuri/marker): fast, accurate PDF to markdown for LLM ingestion - [Firecrawl](https://www.firecrawl.dev): scrape any URL to clean markdown - [Jina Reader
vaquarkhanllms.txtvaquarkhan/mcp-test-harness/html/llms-full.txt
test -m perf` ## Reports `--report-format` console|junit|json|html. SARIF: `--sarif-output`. PDF: `mcp-test export-pdf report.html`. HTML is self-contained (no hosted dashboard). Real run data only
vaquarkhanllms.txtvaquarkhan/mcp-test-harness/html/llms.txt
experiment catalog | | `mcp-test conformance stateless` | SEP-2575 stateless HTTP certify | | `mcp-test export-pdf report.html` | PDF from HTML report | | `mcp-test scan-agents` | Hidden-Unicode scan of AGENTS.md / agent
31Carlton7llms.txt31Carlton7/mac-cli/site/llms.txt
keynote add-slide Deck --title "Q3" --body "Revenue up" mac keynote export Deck --format pdf --out ~/deck.pdf mac pages docs mac pages set-body Letter --text "Dear team," mac pages
ajflowllms.txtajflow/pdf2takeoff/public/llms.txt
pdf2takeoff > pdf2takeoff is a free, open-source (Apache-2.0) PDF takeoff and markup tool that runs entirely in the browser, plus a headless Node CLI and MCP server built
derob98Reads credentialsllms.txtderob98/ailmanac/static/llms.txt
code in a sandbox to hand you a finished Word doc, deck, spreadsheet or PDF. How to brief one, the 30MB ceiling, the toggle you have to turn
dotnetpowerllms.txtdotnetpower/infomesh/llms.txt
Search facets, result clustering, snippet highlighting - RAG support with chunked output and source attribution - PDF extraction, RSS/Atom feed parsing, structured data (JSON-LD, OpenGraph) - Language detection, code block extraction, HTML
LiquidBuiltItPipes a download into a shellllms.txtLiquidBuiltIt/Supersurf/docs/llms.txt
reads and writes go through content scripts; clicks, key presses, screenshots, network capture and PDF export go through Chrome's debugger API. - Uses your actual browser profile: real cookies, logins
michalstrnadelllms.txtmichalstrnadel/source-to-skill/docs/llms.txt
that turns YouTube videos, playlists and channels, podcasts and recordings (local Whisper), arXiv papers, PDF and EPUB books, web articles, GitHub repos, documentation sites (llms.txt), Obsidian or Markdown notes folders
MicrosoftReads credentialsllms.txtmicrosoft/aibast-agents-library/docs/vault/llms-full.txt
proceed? ## Output and exit criteria - **MVP poke document:** 1-2 pages, Word or PDF - **Email to customer:** sent with the document attached - **Timeline started:** the customer response window, usually
nirholasReads credentialsllms.txtnirholas/x402-print-mail/llms-full.txt
print-mail > Agents send physical letters and postcards via Lob's test environment: preview PDF returned in-response # x402-print-mail [](./LICENSE) [
shadoprizmllms.txtshadoprizm/videolens/site/llms.txt
preserved. Paste a YouTube link, choose a report style, and export a polished HTML, PDF, Markdown, or JSON artifact. Use free Private mode with your own OpenAI key or optional
vassiliylakhoninReads credentialsllms.txtvassiliylakhonin/agenda-intelligence-md/llms.txt
incomplete`. `agenda-intelligence review ` loads caller-selected local UTF-8, Markdown, DOCX, or optional PDF sources and renders the same result as reviewer-facing Markdown or JSON without repeating full
veggiemonkllms.txtveggiemonk/backlog/docs/llms.txt
that allows users to generate and export monthly performance reports in PDF format." \ -a "drew" \ -l "feature,frontend,backend" \ --priority "high" \ --ac "Report generation logic is accurate." \ --ac "Users
ahnafnafeellms.txtahnafnafee/ahnafnafee.dev/public/llms-full.txt
# Ahnaf An Nafee - Full Site Content > Complete text of every blog post, research entry
ahnafnafeellms.txtahnafnafee/ahnafnafee.dev/public/llms.txt
local OCR engine I built with a browser interface, flexible vision-model support, and PDF, HTML, Markdown, and text export. Topics: OCR, LLM, Vision Language Models, AI Engineering, Python, PDF
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.
