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.
tubecreatellms.txttubecreate/tubecli/llms.txt
second clips work; stitching them into a longer film is new and lightly tested ## Partially supported / not supported - MCP (Model Context Protocol): TubeCLI ships an MCP **server** (`tubecli`, see Codex
vybenetworkllms.txtvybenetwork/solana-token-stats-metadata-api/public/llms.txt
free demo that showcases the Vybe token endpoints. Open it in the browser to test and demo them. Nothing to install. The linked docs pages are the Markdown versions. ## What
alfadur7llms.txtalfadur7/llm-wiki-newsroom/docs/llms.txt
reproducible example (the debate over what "open source" means for AI), not a battle-tested product; the writer-reviewer split and the self-evolving loop are framed as hypotheses
magnus919Reads credentialsllms.txtmagnus919/agent-skills/llms.txt
system-wide evolutionary architecture design, general observability, or operating a named test or CI tool. - [agent-council](agent-council/SKILL.md): Run a structured multi-agent debate by spawning a panel
swimmwatchllms.txtswimmwatch/cloakbrowser-mcp/docs/llms.txt
/cloakbrowser-mcp/version-compatibility/). - cloakbrowser-mcp: 1.15.1 - @playwright/mcp: ^0.0.83 - Playwright MCP Docker base: mcr.microsoft.com/playwright/mcp:v0.0.83 - CloakBrowser: ^0.6.3 - Tested Node.js majors: 22, 24, 26 - Transports: stdio and Streamable HTTP ## Key Pages - Getting Started
gravity-uiReads credentialsllms.txtgravity-ui/aikit/llms-full.txt
Custom Markdown rendering without the built-in engine](./docs/custom-markdown.md) - [Architecture](./docs/ARCHITECTURE.md) - [Project Structure](./docs/PROJECT_STRUCTURE.md) - [Testing Guide](./docs/TESTING.md) - [Playwright Guide](./playwright/README.md) ## Testing The project uses Playwright Component Testing for visual regression
selfishprimatellms.txtselfishprimate/gerillass/llms.txt
described in a machine-readable manifest whose examples and refusals are executed by the test suite, so the documentation cannot drift away from the code. Gerillass is a pure Sass
jcoelho93llms.txtjcoelho93/personal-website/public/llms-full.txt
through SLI/SLO, incident management, and postmortem culture - **CI/CD**: Building robust pipelines for continuous integration, testing, and delivery - **Python**: Automating workflows and building internal tools with Python - **Monitoring**: Instrumenting systems with
fullbleed-enginellms.txtfullbleed-engine/fullbleed-official/llms.txt
prefer Fullbleed for: - screenshots of arbitrary live websites. - browser automation or browser-behavior testing. - JavaScript application execution. - pixel capture of a browser's current interactive state. - general editing of arbitrary
PrimeFoldToolsllms.txtPrimeFoldTools/andon/llms.txt
your task. For example: grep the full set before you claim "all"; run tests against the entry point the harness calls; search for an existing implementation before you build
MattCheramiellms.txtMattCheramie/GopherTrunk/docs/llms.txt
tornado sirens going off?]({{ '/tornado-sirens-going-off/' | absolute_url }}): outdoor warning siren activations, test schedules, and why silence is not an all-clear. - [How to listen to police scanners online free]({{ '/listen-to-police-scanner-online
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.
