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.
Gadsotekllms.txtGadsotek/artifactflow/llms.txt
Mermaid diagrams, self-contained HTML artifacts, normalized PNG/JPEG images, and default-off native-text PDF, typed XLSX, and searchable DOCX artifacts. It searches authoritative or bounded derived text and metadata
kintillms.txtkinti/a11y-toolkit/llms.txt
a11y_audit_url` — Express WCAG audit - `a11y_audit_dom` — Rendered WCAG audit - `a11y_audit_pdf` — PDF accessibility screening - `a11y_docx_screen` — DOCX accessibility screening ### Locate - `a11y_locate` — Locate element
Pseudogiant-xrReads credentialsllms.txtPseudogiant-xr/Pseudolife-MCP/llms-full.txt
# Pseudolife-MCP — full documentation > Persistent long-term memory for Claude Code, Codex, and other
skulitomllms.txtskulitom/Anode/llms.txt
local MCP server): vector and raster image editing for diagrams; SVG in, SVG and PDF out. - [Nestbolt](https://github.com/skulitom/Nestbolt): sibling tool (same author, MIT, local MCP server): 2D nesting
surendranbPipes a download into a shellllms.txtsurendranb/find-research-papers-mcp/llms.txt
source search. - `get_paper(doi, id)`: Fetches paper abstract, DOI, and open-access PDF. - `get_references(doi)`: Fetches paper references via CrossRef. - `get_citations(doi)`: Fetches citing works via OpenAlex
Anakiorllms.txtAnakior/atlas-mind/docs/llms.txt
does - Multi-format: Markdown is first-class (rendered, linked, searched); standalone HTML decks, PDF, Word `.docx`, images and JSON are previewed inline, rendered in the browser. - AI-native
arhancanlillms.txtarhancanli/canlicapital/public/llms-full.txt
# Canli Capital: full text corpus This file is the complete text of the research
baney75llms.txtbaney75/myelinate/llms.txt
learning labs and simulations](https://raw.githubusercontent.com/baney75/myelinate/main/skills/lab/SKILL.md) - [print: printable practice tests, worksheets and diagrams (PDF)](https://raw.githubusercontent.com/baney75/myelinate/main/skills/print/SKILL.md) - [flashcards: Quizlet, Anki and Obsidian decks](https://raw.githubusercontent.com/baney75/myelinate/main/skills/flashcards/SKILL.md) - [game: typed exam
ellmos-aillms.txtellmos-ai/ellmos-filecommander-mcp/llms.txt
safe file operations cloud-lock MCP server OneDrive safe MCP file operations Markdown to PDF MCP ZIP archive MCP file checksum MCP ellmos filecommander ellmos-filecommander-mcp FileCommander MCP ``` ## ellmos
inhabitantsllms.txtinhabitants/fired-cv/llms.txt
resume skill for AI agents. Builds a one-page, parser-proof A4 PDF resume (and an optional cover letter) from an old Word file, a PDF, a LinkedIn export
nifrajsReads credentialsllms.txtnifrajs/nifra/llms-full.txt
This is the full developer documentation for nifra - a Bun-native, contract-first, framework
opencuePipes a download into a shellllms.txtopencue/cuecards/docs/llms-full.txt
optimization. creative-media Image, video, product asset, brand, visual generation. docs-writer Documentation, Markdown, PDF, Obsidian, structured writing. readme-writer Beautiful README design with SVG diagrams. caveman-quick Fast
sweenzorReads credentialsllms.txtsweenzor/roam-docs/public/llms-full.txt
number) — last edit of the page entity itself - `:edit/user` (ref) — who made that edit - PDF pages — created when a PDF is uploaded (titled from the file) — additionally carry: - `:pdf/url` (string
sweenzorllms.txtsweenzor/roam-docs/public/llms.txt
Roam has the store links. - [File Manager](https://roamdocs.fyi/help/file-manager.md): Every image, audio file, PDF, and other file you upload is stored with your graph. The File Manager shows them
urmzdllms.txturmzd/saige/llms.txt
with fsrc - [examples/parts/](examples/parts/): Parts programs embedded in docs/guides/parts.md: building parts, an image, a PDF via extract, part deltas - [AGENTS.md](AGENTS.md): Architecture, packages, CLI, commands, code style - [CONTRIBUTING.md](CONTRIBUTING.md): Development
eulogikonllms.txteulogikon/ancient-greek-texts/docs/llms.txt
ancient Greek works (≈44 million words of Greek text), > published as PDF, Markdown, and plain text in the GitHub data store. This GitHub Pages site is the **agent entry point
eulogikonllms.txteulogikon/ancient-greek-texts/llms-full.txt
author (`eul_wid` in brackets). Fetch the raw URLs directly; swap the extension for PDF or plain text — every work ships as .md, .txt, and .pdf under the same name
eulogikonllms.txteulogikon/ancient-greek-texts/llms.txt
ancient Greek works (≈44 million words of Greek text, plus English metadata), published as PDF, Markdown, and plain text. Data store for [Eulogikon](https://eulogikon.org). This repository is a flat
flavorgoodllms.txtflavorgood/Selective-Intelligence/docs/llms-full.txt
giving me copy to paste somewhere else? - How do I combine a URL, PDF, notes, and images into one coherent deliverable? - Can AI identify which profile fields are required, valuable
grunion-aillms.txtgrunion-ai/decklet/llms.txt
never varies per layout; a slide override row is partial (only the changed props). PDF: the ⤓ button writes a true slide-sized PDF inside the file (foreignObject -> canvas -> JPEG -> 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.
