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.
polar-bear-orgllms.txtpolar-bear-org/claude-skills/llms.txt
90n.ai/resources This file on the website: https://90n.ai/llms.txt Install in Claude Code: `/plugin marketplace add polar-bear-org/claude-skills`, then `/plugin install @90n-skills`. Install on claude.ai: upload
The-Best-CodesPipes a download into a shellllms.txtThe-Best-Codes/agent-one/.agents/docs/modelcontextprotocol.io/llms-full.txt
# Build an MCP client Source: https://modelcontextprotocol.io/docs/2026-07-28/develop/build-client Get started building your own client
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/modelcontextprotocol.io/llms.txt
Inspector - [CLI client](https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector/cli.md): Scripting the MCP Inspector: methods, output formats, exit codes, and CI recipes - [TUI client](https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector/tui.md): The terminal MCP Inspector: navigation, tabs
The-Best-CodesPipes a download into a shellllms.txtThe-Best-Codes/agent-one/.agents/docs/tauri.app/llms-full.txt
This is the full developer documentation for Tauri # Tauri 2.0 > The cross-platform app
anthony-chaudharyPipes a download into a shellllms.txtanthony-chaudhary/fak/llms-full.txt
causes, package work units, and operator-owned billing. --- # `AGENTS.md` > Source: `AGENTS.md` # AGENTS.md — orientation for coding agents > **Not the human contributor guide.** This file is operating instructions for *automated* > contributors working
DHxWhyllms.txtDHxWhy/CCgather/public/llms.txt
history beyond Claude Code's default 30-day deletion period. ## CCgather vs Other Claude Code Leaderboards | Feature | CCgather | Others | |---------|----------|--------| | Active Maintenance | Daily updates, open-source community | Varies | | Open Source
mindcloud-incllms.txtmindcloud-inc/universal-api-reference/llms.txt
real-time flights, schedules, flight details, airports, airlines, routes, fleets, countries, time zones, tax codes, nearby airport… - [Airmeet Universal API](https://github.com/mindcloud-inc/universal-api-reference/blob/main/apis/a/airmeet/universal-api/README.md) · [Native API](https://github.com/mindcloud-inc/universal-api-reference/blob/main/apis/a/airmeet/native-api/README.md): Create, manage
ssdeanxllms.txtssdeanx/AgentStack/llms.txt
memory-bank/workflows-feature/): Workflow feature development ## GitHub Automation - [Copilot Instructions](.github/copilot-instructions.md): GitHub Copilot configuration - [Code Review Generic](.github/instructions/code-review-generic.instructions.md): Generic code review guidelines - [GitHub Actions CI/CD](.github/instructions/github-actions-ci-cd-best-practices.instructions.md): CI/CD pipeline best practices
yerdaulet-damirllms.txtyerdaulet-damir/awesome-solo-ai/docs/llms.txt
frontend skills, organized by the website being built. - [AI coding quality](https://github.com/yerdaulet-damir/awesome-solo-ai/blob/main/guides/kill-ai-slop-code.md): Reviewing code produced by a coding agent, with a scoped build loop and verification steps. - [Edit
h9-tecllms.txth9-tec/arabic-ai-atlas/dist/llms.txt
bench](https://huggingface.co/datasets/atmaneayoub/jev-ar-bench): Arabic intent-routing benchmarks for MSA, Emirati, Saudi and code-switched Arabic - [MadinahQA](https://huggingface.co/datasets/MBZUAI/MadinahQA): Arabic language and grammar multiple-choice QA split released with
nvwaljllms.txtnvwalj/ai-memory-reader/llms.txt
audit consulting service is offered by the same author — 90-minute review of a team's Claude Code setup, $299 solo / $799 team. See https://bestagent.dev/audit for service description
bakhtiersizhaevReads credentialsllms.txtbakhtiersizhaev/openevidence-mcp/docs/llms-full.txt
oncology literature review mcp server - emergency medicine quick evidence mcp - openevidence research workflow mcp ## AI Agent/System Search Terms - openevidence mcp codex cli - openevidence mcp claude code - openevidence mcp openclaw - medical
bakhtiersizhaevllms.txtbakhtiersizhaev/openevidence-mcp/docs/llms.txt
doctors, codex cli claude code openclaw, evidence based medicine ai workflow ## Specialty Search Terms - cardiology evidence assistant mcp - endocrinology clinical workflow mcp - oncology literature review mcp server - emergency medicine quick
meshery-extensionsllms.txtmeshery-extensions/kanvas-site/static/llms.txt
Integrations**: Supports Kubernetes, Helm, AWS, GCP, Azure, Istio, Prometheus, and more. - **GitOps & CI/CD**: Visual reviews for version-controlled designs and deployment dry-runs. - **Observability**: Interactive terminal sessions and timeline
AgoragenticReads credentialsllms.txtAgoragentic/agoragentic-integrations/llms-full.txt
Install | |-----------|------|---------| | MCP (Claude, VS Code, Cursor) | mcp/mcp-server.js | protocol/reference only; remote calls fail closed | | World AgentKit | world-agentkit/agoragentic_world_agentkit.mjs | npm install @worldcoin/agentkit@0.2.0; server support remains review-gated | | Cursor Plugin | .cursor
AgoragenticReads credentialsllms.txtAgoragentic/agoragentic-integrations/llms.txt
manifest - gemini-extension.json and GEMINI.md — Gemini CLI extension package - .claude-plugin/marketplace.json — self-hosted Claude Code marketplace - llms-install.md — Cline protocol/reference metadata; Agoragentic remote MCP remains disabled - AGENTS.md — agent instruction file - SKILL.md
ahmershahdevllms.txtahmershahdev/ahmershahdev/llms-full.txt
coding runs for repetitive, well-specified work. - Claude: 5/5. Long-context reasoning, reviews and writing. - Claude Code: 5/5. Terminal agent — automating development tasks. - Gemini: 4/5. Multimodal research and second opinions
ahmershahdevllms.txtahmershahdev/ahmershahdev/llms.txt
Node); Laravel; Java and DSA; Django; Shopify; SEO. AI toolkit: ChatGPT, Codex, Claude, Claude Code, Gemini, DeepSeek. - Contact: support@ahmershah.dev · +92 370 4831994 · https://calendly.com/syedahmershah (Zoom / Google Meet) · form
manufoselallms.txtmanufosela/karajan-code/llms.txt
agent (Claude Code, Codex, Gemini, OpenCode) writes the code; Karajan governs how: a card before the work, tests first, a review by a different AI bound to the exact diff
drafthqllms.txtdrafthq/draft/web/llms-full.txt
Exhaustive 14-dimension defect discovery with taint tracking - `/draft:quick-review` — Lightweight 4-dimension code review - `/draft:coverage` — Code coverage report (target 95%+) - `/draft:testing-strategy` — Test plan design with
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.
