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.
LoomA8osAgentllms.txtLoomA8osAgent/a8-loom-coordinator/llms.txt
coordinator) as the autonomous senior engineer on a > software project — any language, any framework, frontend or backend. Its enforced > idea: **discover-then-reuse** — retrieve what the codebase already provides
nirholasllms.txtnirholas/carbide/llms-full.txt
/api/comps sold comps for a model, narrowed to ±3 model years public/index.html single-file frontend, no build step data/listings.json normalized corpus data/sold.json verified auction results ``` Everything derived (cohort medians, outlier
sandraschiReads credentialsllms.txtsandraschi/libreoffice-mcp/llms-full.txt
MODEL LIBREOFFICE_MCP_SAMPLING_USE_CLIENT_LLM LIBREOFFICE_MCP_PREFAB_APPS ## Ports Backend 10981 | Frontend 10983 | Extension bridge 8765 ## Host LibreOffice 26.2.3.2+ recommended on Windows (soffice.exe
sandraschillms.txtsandraschi/libreoffice-mcp/llms.txt
EXTENSION_BRIDGE_URL, LIBREOFFICE_MCP_SAMPLING_BASE_URL, LIBREOFFICE_MCP_SAMPLING_MODEL Backend: 10981 | Frontend: 10983 | MCP: http://localhost:10981/mcp
sweenzorReads credentialsllms.txtsweenzor/roam-docs/public/llms-full.txt
encrypted graphs, offline graphs). - **Warning**: the backend can be a few changes behind the frontend while local changes are still syncing. - Return:: - Promise resolving to the query results - Example:: - ```javascript
sweenzorllms.txtsweenzor/roam-docs/public/llms.txt
/developer-documentation/data-model.md): Your graph is a DataScript database. - [Roam Alpha API](https://roamdocs.fyi/developer-documentation/roam-alpha-api.md): The frontend JS API (window.roamAlphaAPI): datalog q/pull, block & page CRUD, UI control, file storage - [Roam Depot/Extension
adiprmxllms.txtadiprmx/atlys/llms.txt
guideline - [brutalist-skill](design/brutalist-skill/SKILL.md) (design): Raw mechanical interfaces fusing Swiss typographic print with military - [frontend-image-direction](design/frontend-image-direction/SKILL.md) (design): Section references, mobile screen concepts, and brand-consistent image - [gpt-tasteskill
edumgtReads credentialsllms.txtedumgt/domain-rag-lab/llms.txt
symbol atlas in `frontend/app.js`; run via `docker compose exec api python -m app.ops.backfill_ohlcv` ## Frontend - [frontend/index.html](frontend/index.html), [frontend/app.js](frontend/app.js), [frontend/auth.js](frontend/auth.js), [frontend/style.css](frontend/style.css): main static SPA (chat, stock view with
Git-Rocky-Stackllms.txtGit-Rocky-Stack/Team-X/docs/llms.txt
Cancel all running agents" ### Employee Roles (57 total) **Engineering:** Full Stack Engineer, Backend Engineer, Frontend Engineer, DevOps Engineer, Security Engineer, QA Engineer, Database Architect **Design:** UI/UX Designer, Graphic Designer, Product
Iron-Markllms.txtIron-Mark/Iron-Mark/llms.txt
first emergency UX (ResQLink)](https://www.marksiazon.dev/writing/offline-first-ux): designing for zero connectivity ## Social and community - [Frontend Mentor](https://www.frontendmentor.io/profile/Iron-Mark): front-end challenge profile - [TikTok](https://www.tiktok.com/@iron_markk): short-form build
Iron-Markllms.txtIron-Mark/Iron-Mark/public/llms-full.txt
verification dates, prefer https://www.marksiazon.dev/llms-full.txt. ## Social and community - LinkedIn: https://www.linkedin.com/in/mark-siazon/ - Frontend Mentor: https://www.frontendmentor.io/profile/Iron-Mark - TikTok: https://www.tiktok.com/@iron_markk ## What is Mark Siazon open to? **Key takeaway
isatimurllms.txtisatimur/presentation-md/web/llms.txt
prompt decks: `scaffold_deck` → `studio_share_url`. Honest compare: https://presentation-md.vercel.app/vs/hallmark - **vs. frontend-slides:** Same discovery energy (3 live theme previews); plus schema-validated Deck JSON, 75 structured proofs
kalturaReads credentialsllms.txtkaltura/kaltura-agents-api-guides/llms.txt
users — event invitations, attendance... - [Kaltura Unisphere Framework API](/raw/KALTURA_UNISPHERE_FRAMEWORK_API.md): Unisphere is Kaltura's micro-frontend framework for embedding composable experiences. Load a workspace, configure runtimes (AI search, media... ## Sharing & Distribution
kennetvnllms.txtkennetvn/nextcore-skills/llms.txt
production product built and run by AI coding > agents: nextcore-design (UI), nextcore-dev (frontend ↔ backend contract), nextcore-workflow (running agents). Agents: read AGENTS.md first — it routes "is this useful
mattbutlerengineeringReads credentialsllms.txtmattbutlerengineering/mattbutlerengineering/llms-full.txt
export const accordionCatalogMeta = { name: "Accordion", description: "Grouped set of collapsible panels. Use for FAQs
parousia8888llms.txtparousia8888/web-app-security-skill/llms.txt
SKILL.md` name field. ## What the skill does - Runs a phased security program: scope gate, frontend exposure, API security, LLM security and federated identity, server-side code audit, database isolation, supply
qmmughalllms.txtqmmughal/AgentWire/llms.txt
data leakage. ## Architecture - Backend: ASP.NET Core 10, .NET Aspire - Database: PostgreSQL, ClickHouse, Redis - Frontend: Next.js, React, Tailwind CSS - Infrastructure: Docker, Kubernetes ## Key Features - 100% Open Source (Apache 2.0) with zero
sandraschiReads credentialsllms.txtsandraschi/arxiv-mcp/llms-full.txt
Python 3.11+, uv, pypdf, optional React/Vite dashboard (`web_sota/`, ports **10770** backend / **10771** frontend). - **Transports:** stdio (`python -m arxiv_mcp --stdio`) and streamable HTTP (`--serve`, FastMCP `http_app` at `/mcp
sandraschillms.txtsandraschi/bookmarks-mcp/llms-full.txt
default, the web dashboard runs on port **10802**. *(Assigned ports: **10802** (Web dashboard frontend), **10803** (Web dashboard backend))* To start the webapp: 1. Navigate to the `webapp` (or `web`, `frontend
sandraschiReads credentialsllms.txtsandraschi/email-mcp/llms-full.txt
replies, approve_reply, auto_respond_now ## Architecture - **Backend**: FastMCP 3.2+ / FastAPI on port 10813 - **Frontend**: React 19 + Vite + Tailwind on port 10812 - **DB**: JSON file-based (contacts, drafts, rules, signatures
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.
