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.
sabahattinkPipes a download into a shellllms.txtsabahattink/antigravity-fullstack-hq/llms.txt
additions for Claude Code, Codex, Antigravity, and project installs - [Agents](https://github.com/sabahattink/antigravity-fullstack-hq/tree/main/agents): architect, frontend, backend, database, code reviewer, test engineer, security auditor, DevOps, performance, and documentation specialists - [Skills
wundercorpPipes a download into a shellllms.txtwundercorp/loki/llms-full.txt
# @wundercorp/loki > Loki Agent — a self-improving AI agent by WunderCorp, Inc. This Doku context
heymegabyteReads credentialsllms.txtheymegabyte/agent-skills/llms-full.txt
skill set (category map · task routing · file hints) - [Skill Packs](_packs/README.md) — grouped bundles (core / frontend / backend / testing / design / …); one pack loads its whole graph - [Kernel](_kernel/index.md) — canonical shared definitions (WCAG
heymegabytellms.txtheymegabyte/agent-skills/llms.txt
skill set (category map · task routing · file hints) - [Skill Packs](_packs/README.md) — grouped bundles (core / frontend / backend / testing / design / …); one pack loads its whole graph - [Kernel](_kernel/index.md) — canonical shared definitions (WCAG
tcsenpaillms.txttcsenpai/specification-website-skill/references/llms-full.txt
# The Website Specification > A platform-agnostic, full specification of the technical features a good
wonsukchoillms.txtwonsukchoi/domain-experts/docs/llms.txt
method to confirm it solidifies after the section it feeds, isolating whether a gas… - [Frontend Engineer](https://domainexperts.dev/roles/frontend-engineer/): diagnosing which Core Web Vital (LCP/INP/CLS) a change actually affects before
zircoteReads credentialsllms.txtzircote/.claude/llms.txt
body #### Categories: - `01-core-development/` - Full-stack development (11 agents) - api-designer, backend-developer, frontend-developer, fullstack-developer - graphql-architect, microservices-architect, mobile-developer, ui-designer - electron-pro, websocket-engineer
nirholasReads credentialsllms.txtnirholas/pumpfun-claims-bot/llms-full.txt
Telegram - **skip cashback**: Cashback claims (user refunds, not creator activity) ## Web Dashboard Two React frontends are checked in, and they are not the same app: | Directory | What it is | Build
nirholasReads credentialsllms.txtnirholas/xspace-AI/llms-full.txt
handlers, routes, metrics ├── browser/ Puppeteer auth, launcher, orchestrator, selectors ├── audio/ Audio stream bridge └── client/ Frontend initialization & provider configs x-spaces/ Low-level Puppeteer automation scripts (JavaScript) ├── index.js Orchestration entry point
danicatllms.txtdanicat/skills/llms.txt
plate with mediocre extras. Counters AI bloat across product scope, writing, architecture, and frontend UX by elevating the hero ingredient, applying the Inverted Pyramid, replacing noisy text buttons with Material
mimnetsllms.txtmimnets/OpenHRApp/public/llms-full.txt
# OpenHRApp > OpenHRApp is free, open-source HR management software for small and mid-sized
nirholasReads credentialsllms.txtnirholas/pumpkit/llms-full.txt
Ready | | [`@pumpkit/tracker`](packages/tracker/) | Group call-tracking bot with leaderboards & PNL cards | ✅ Ready | | [`@pumpkit/web`](packages/web/) | Frontend dashboard and documentation site | 🏗️ Skeleton | > **npm:** Packages will be published to npm under the `@pumpkit
sandraschiReads credentialsllms.txtsandraschi/ocr-mcp/llms-full.txt
backend/app.py` | FastAPI web backend (scanner, upload, settings, auto-scan, book pipeline) | | `web_sota/src/` | React frontend | | `run_server.py` | PyInstaller entry point for NSIS builds | ### Ports | Service | Port | |---------|------| | Vite frontend | 10858 | | FastAPI backend
sandraschillms.txtsandraschi/ocr-mcp/llms.txt
repo root - **Web UI**: `just webapp` or see README “Web Interface”; backend and frontend ports in docs ## MCP listing - **Glama.ai**: Use [glama.json](glama.json) snippet for MCP client config - **GitHub
sandraschiReads credentialsllms.txtsandraschi/worldlabs-mcp/llms-full.txt
REST backend (port 10865) serves the webapp and spatial bridge. A Vite/React frontend (port 10864) provides a full control UI including world library, prompt memory, local LLM refinement
kimyoungwopollms.txtkimyoungwopo/cafe24-smart-design/llms.txt
Design Reference > Korean reference for Cafe24 Smart Design storefront work. It is built for frontend developers and AI coding agents that need safe, verifiable Cafe24 skin/module guidance. Canonical
skein-jsReads credentialsllms.txtskein-js/skein-js/llms-full.txt
activity, and graph updates as they happen. Connect with the LangGraph SDK and its frontend bindings, including React's `useStream`. [Streaming](./docs/streaming.md) · [Client integration](./docs/react-sdk.md) - **Human approvals and checkpoint history
skein-jsllms.txtskein-js/skein-js/llms.txt
with no license key or per-run bill. Connect React, Vue, Svelte, or Angular frontends, Agent Chat UI, services using the LangGraph JavaScript SDK or HTTP/SSE, the Skein console
glinckerReads credentialsllms.txtglincker/theauth/docs/llms-full.txt
# theAuth documentation # theAuth Source: https://docs.theauth.dev/ **Auth for AI agents and for the humans
JoahanMoralesReads credentialsllms.txtJoahanMorales/upiixia-agentic-kit/llms.txt
call (`uak next` ~2 s on GitHub) and `uak wait` instead of polling; a frontend gate (`product-ui` skill, `uak design-lint` after every UI edit, a design lock picked
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.
