How real projects summarise themselves for language models.
xu-xiangllms.txtxu-xiang/awesome-top-skills/llms.txt
800/2205 skills) - product: ./llms/categories/product.txt (178/178 skills) - productivity: ./llms/categories/productivity.txt (479/479 skills) - research: ./llms/categories/research.txt (272/272 skills) - security: ./llms/categories/security.txt (400/400 skills) - web: ./llms/categories/web.txt (800/1089 skills) ## TOP 500 GLOBAL SKILLS find-skills;vercel-labs
elon-choollms.txtelon-choo/fablever/llms.txt
node install.mjs --uninstall` · `node install.mjs --uninstall --codex` ## Recommended install by user type - First-time / security-sensitive / work machine → style-only (no hooks, no MCP, no skills, no network). - Wants
oomkapwnllms.txtoomkapwn/enquire-mcp/llms.txt
onboarding - [Retrieval benchmarks](https://github.com/oomkapwn/enquire-mcp/blob/main/docs/benchmarks.md): NDCG@10, Recall@K, MRR with reranker ablation - [Security and privacy model](https://github.com/oomkapwn/enquire-mcp/blob/main/SECURITY.md): local-first guarantees, trust boundaries, and enforcement - [HTTP transport
thought2codellms.txtthought2code/mcp-annotated-java-sdk/llms-full.txt
examples. - Avoid competing with Spring AI on Boot auto-configuration, WebMVC/WebFlux integration, enterprise security, or observability. ## Requirements - **Java 17 or later** (required by official MCP Java SDK) ## Installation ### Maven
thought2codellms.txtthought2code/mcp-annotated-java-sdk/llms.txt
examples. - Avoid competing with Spring AI on Boot auto-configuration, WebMVC/WebFlux integration, enterprise security, or observability. ## Requirements - Java 17 or later ## Packaging For deployment with `java -jar`, build an executable
Aboudjemllms.txtAboudjem/solidity-style-guide/llms.txt
/Aboudjem/solidity-style-guide/main/CLAUDE.md): Claude Code–specific notes. - [CONTRIBUTING](https://raw.githubusercontent.com/Aboudjem/solidity-style-guide/main/CONTRIBUTING.md): how to propose new rules. - [SECURITY](https://raw.githubusercontent.com/Aboudjem/solidity-style-guide/main/SECURITY.md): disclosure policy. ## Tooling configs (copy-paste ready) - [.solhint.json](https://raw.githubusercontent.com/Aboudjem/solidity-style-guide/main/.solhint.json): Solhint
cubrid-labllms.txtcubrid-lab/cubrid-mcp-server/llms.txt
only and output limits. ## Docs - [README](README.md): features, configuration, installation, and MCP client setup. - [Security policy](SECURITY.md): read-only enforcement, output limits, deployment guidance, and vulnerability reporting. - [Changelog](CHANGELOG.md): released
nirholasllms.txtnirholas/github-to-mcp/llms.txt
Model Context Protocol)**: An open standard by Anthropic that allows AI models to securely connect to external tools and data sources. **MCP Server**: A program that exposes tools
paramount-engineeringllms.txtparamount-engineering/roku-dev-studio/docs/llms.txt
server — full tool/resource/prompt catalog, how agents connect (Cursor, Claude Desktop, VS Code), and security notes - [MCP Tool Reference](https://paramount-engineering.github.io/roku-dev-studio/mcp-tools.html): Every MCP tool with its input schema and (where
TT-Wangllms.txtTT-Wang/memem/llms.txt
redundant memories, deprecates outdated ones) - Cross-project (one shared knowledge graph, not per-repo) - Security scanning on every write (prompt injection, credential exfil) - Browsable Obsidian vault with graph view
zap-coding-agentllms.txtzap-coding-agent/zap-coding-agent/website/llms.txt
zap.justpush.cloud/docs.html#mcp) - [Autonomous Mode (/goal)](https://zap.justpush.cloud/docs.html#goal) - [Multi-Provider](https://zap.justpush.cloud/docs.html#providers) - [Security Boundary](https://zap.justpush.cloud/docs.html#security) - [Session Memory](https://zap.justpush.cloud/docs.html#session-memory) - [Commands Reference](https://zap.justpush.cloud/docs.html#commands) ## Comparisons - [System
racciolyllms.txtraccioly/docguard/llms-full.txt
Traceability validator | `cli/` | `shared-ignore.mjs`, `shared-validator-surface.mjs`, `shared-source.mjs`, `shared-git.mjs`, `shared-requirements.mjs`, `shared-trace-patterns.mjs`, `shared.mjs` | | **Templates** | Document skeletons (ARCHITECTURE, SECURITY, etc.) and slash command files for AI agents | `templates/` | `*.template`, `commands/*.md` | | **Extension** | Spec
racciolyllms.txtraccioly/docguard/llms.txt
canonical/ENVIRONMENT.md): Setup instructions, environment variables, and prerequisites - [REQUIREMENTS](docs-canonical/REQUIREMENTS.md): REQUIREMENTS documentation - [SECURITY](docs-canonical/SECURITY.md): Authentication, authorization, secrets management, and security policies - [TEST-SPEC](docs-canonical/TEST-SPEC.md
rsdouglasllms.txtrsdouglas/janee/website/llms.txt
Janee > Secrets management for AI agents. Local-first CLI with MCP integration, enforcement-based security, and exec mode for CLI tools. ## Overview Janee is a secrets management tool designed specifically
AnastasiyaWllms.txtAnastasiyaW/knowledge-space/docs/llms.txt
base with 1319+ curated articles across 28 domains. Covers software engineering, data science, DevOps, security, and more. Designed for software engineers and LLM agents seeking reliable, structured technical reference material
infiniVllms.txtinfiniV/ultra-instinct-claude-code/llms.txt
name: reviewer model: sonnet tools: Read, Grep, Glob --- Review git diff for bugs and security issues. Headless: `claude --bare -p "..."` skips all loading, ~14% faster for scripts/CI. --- ## 02 CLAUDE.md # Full
junnam586llms.txtjunnam586/goguma/site/llms.txt
query string and no cookies. A webhook is sent only if you configure one. ## Security Four binaries, one of which runs as root. The privileged helper answers six messages
waiaasllms.txtwaiaas/WAIaaS/site/llms.txt
Service for AI Agents > Self-hosted local daemon that gives AI agents secure, policy-controlled access to crypto wallets. ## Overview WAIaaS is an open-source Wallet-as-a-Service daemon
korniallms.txtkornia/bubbaloop/docs/llms.txt
YAML-based node and system configuration - [Architecture](https://kornia.org/bubbaloop/concepts/architecture/): Runtime design, daemon subsystems, security layers - [Messaging](https://kornia.org/bubbaloop/concepts/messaging/): Zenoh pub/sub patterns, topic conventions, wire format - [Memory](https://kornia.org
michielhdotethllms.txtmichielhdoteth/awesome-ai-agent-tools/llms.txt
Productivity 18, Content 13, Design 11, DevOps 8, Marketing 6, Testing 4, Data 4, Security 2) - **140 MCP Servers**: Model Context Protocol servers with install commands across 20 categories
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.
