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.
doanbactamllms.txtdoanbactam/agent-skills-directory/public/llms.txt
machine learning tools - **Data & Analytics** — Data processing, analytics, and database tools - **Coding & Development** — Frontend, backend, and fullstack development - **Mobile** — iOS, Android, and cross-platform mobile development - **Automation & Agents** — CI/CD, workflows
event4u-appllms.txtevent4u-app/agent-config/llms.txt
deploy to staging' without naming AWS. - [blade-ui](dist/agent-src/skills/blade-ui/SKILL.md): Use when the project's frontend stack is Blade — dispatched by `directives/ui/{apply,review,polish}.ts`. Covers views, components, partials, layouts
jigarbhoye04Pipes a download into a shellllms.txtjigarbhoye04/MatlabMCP/llms-full.txt
# Example Clients Source: https://modelcontextprotocol.io/clients A list of applications that support MCP integrations
me-publicDeletes or force-pushesllms.txtme-public/nemus/docs/llms-full.txt
Nemus? Your product's code is probably split across **many separate Git repos** — frontend, backend, auth, payments, shared libraries. Working on one feature means cloning, pulling, branching, and testing each
me-publicllms.txtme-public/nemus/docs/llms.txt
they were one project. Your product's code is split across many repos > (frontend, backend, auth, payments, shared libraries); Nemus pulls the repos you're > working on into a single
respeak-iollms.txtrespeak-io/episko/site/llms.txt
nothing to Respeak. Built with Tauri v2: a Rust backend with a vanilla-TypeScript frontend. ## Requirements - At least one supported agent CLI on your PATH (Claude Code, Codex
sandraschiReads credentialsllms.txtsandraschi/advanced-memory-mcp/llms-full.txt
FTS5) │ │ LanceDB (vector embeddings) │ │ Markdown files (human-readable) │ └──────────────────────────────────────┘ ↓ Webapp (port 10704/10705) ``` ## Ports | Service | Port | |---------|------| | Frontend (Vite React) | 10704 | | Backend (FastAPI + MCP HTTP) | 10705 | | MCP SSE transport | 10732 | ## MCP Tools
yangdcmllms.txtyangdcm/dsh-expert-team/llms.txt
上手：会话切到「专家团模式」→ `/team 做一个带登录的支付模块` - 角色（12）：`pm` · `architect` · `researcher` · `ui` · `backend` · `frontend` · `dba` · `sec` · `reviewer` · `qa` · `devops` · `docs` - 阶段（9）：`clarify` → `research` → `design` → `spec-review`（**硬门**）→ `方案确认`（确认门，默认开
AishwaryShrivastavllms.txtAishwaryShrivastav/vibe-testing/llms-full.txt
SvelteKit, Nuxt, Vue, Express, Fastify) - Detects monorepos (Turborepo, pnpm, yarn, Lerna) and finds frontend app - Parses all routes (file-based and code-defined, including src/ variants) - Extracts forms, buttons, dialogs
CLOUDWERX-DEVPipes a download into a shellllms.txtCLOUDWERX-DEV/gpt-image-1-mcp/.docs/llms-full.txt
# Example Clients Source: https://modelcontextprotocol.io/clients A list of applications that support MCP integrations
ssdeanxReads credentialsllms.txtssdeanx/secure-rag-multi-agent/llms.txt
This repository demonstrates production-ready governed RAG using Mastra's agentic architecture, combining Next.js frontend, Qdrant vector database, and OpenAI LLMs with comprehensive security controls for enterprise knowledge bases. ## Documentation
akustikrauschllms.txtakustikrausch/gonzales/llms.txt
automations - Dark/light theme support - Mobile-responsive design ## Technical Stack - Backend: Python, FastAPI, SQLAlchemy, SQLite - Frontend: React, TypeScript, Vite, Recharts, TanStack Query - Speed Testing: Ookla Speedtest CLI (third-party, separate license
heymiReads credentialsllms.txtheymi/aldus-palace/llms-full.txt
system inferred it. **It follows you.** One file, one API. Claude, Cursor, your own frontend, a script you write. ## Who it's for and when
sagarithmllms.txtsagarithm/sagarithm-kit/llms.txt
certification. - **DevOps, SRE & Cloud Governance**: Containerization, OpenTelemetry observability, SLO/SLI tracking, and release governance. - **Frontend & UI/UX Engineering**: Accessible design systems, state machines, and optimal Core Web Vitals. - **Marketing, AEO & Growth
webrenewReads credentialsllms.txtwebrenew/unicon/LLMs.txt
mode support **Live Site:** https://unicon.sh **Repository:** https://github.com/WebRenew/unicon **License:** MIT ## Tech Stack ### Frontend - **Framework:** Next.js 16 (App Router, React 19) - **Styling:** Tailwind CSS 4 - **UI Components:** Radix
bntvllntDeletes or force-pushesllms.txtbntvllnt/agent-skills/llms-full.txt
Detect domain: software 3. Select 10 perspectives: - Architect - DevOps - Security Engineer - Database Engineer - Frontend Developer - QA Engineer - Performance Engineer - SRE - Tech Lead - CTO 4. Launch all 10 agents in parallel
jimy-rReads credentialsllms.txtjimy-r/agent-workspace-architecture/docs/llms-full.txt
# Agent Workspace Architecture — full text > A redacted reference for building agent workspaces: the roles
Nanako0129llms.txtNanako0129/TokenBar-Tauri/llms.txt
updater ## Architecture - [Tauri shell source](https://github.com/Nanako0129/TokenBar/tree/main/src-tauri): Rust backend, native tray, animation frames - [Frontend source](https://github.com/Nanako0129/TokenBar/tree/main/src): React + Vite, react-three-fiber 3D graph - [tokscale upstream](https://github.com
ariaxhanllms.txtariaxhan/kernel-claude/llms.txt
kernel:human-pass`: the acceptance pass a human runs against a real build. - `/kernel:frontend` · `$kernel:frontend`: art direction derived from product and audience, not a house style. - `/kernel:marketing
nirholasllms.txtnirholas/task-queue-system/llms-full.txt
task files in `prompts/ /NN- .md` following the format in `PROMPT-SPEC.md`. **Example structure**: ``` prompts/ frontend/ 01-dashboard-layout.md 02-responsive-design.md 03-dark-mode.md backend/ 01-api-routes.md 02-database-schema.md 03-websocket-server.md tests/ 01-unit-tests.md 02-integration-tests.md ``` ### 3. Generate TASK-MANIFEST.md Run this
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.
