How real projects summarise themselves for language models.
shimo4228llms.txtshimo4228/search-first/llms-full.txt
front-end check (before code is written) while verification skills (test coverage, security review, code review) are the back-end checks (after code exists). The skill is also a kind
shimo4228llms.txtshimo4228/zenn-content/llms-full.txt
usage, LLM engineering, and Contemplative AI governance. Every article is written, reviewed, translated, and scheduled collaboratively with Claude Code — the maintainer provides lived context while Claude Code agents handle drafting
shimo4228llms.txtshimo4228/zenn-content/llms.txt
zenn-content > Japanese and English writing by Tatsuya Shimomoto (shimo4228) on coding agents — how they remember, fail, get reviewed, and stay accountable — plus idea essays and the papers that grew
staurus86llms.txtstaurus86/global-design-skill/llms.txt
Portable design operating system for AI-assisted frontend development. It helps AI coding assistants produce stricter UI/UX reviews, better frontend handoff specs, and less generic interface output. ## Primary Repository - [GitHub
tbc-servicosllms.txttbc-servicos/dataagile-agent-kit/llms-full.txt
fronts Angular. ## Instalação **Pré-requisito:** API key em https://dataagile-agent-kit.totvstbc.com.br ```bash # 1. Instalar Claude Code npm install -g @anthropic-ai/claude-code # 2. Configurar API key mkdir -p ~/.config/dataagile echo
tbc-servicosllms.txttbc-servicos/dataagile-agent-kit/llms.txt
dataagile-agent-kit > Plugin Claude Code para desenvolvimento ADVPL/TLPP e diagnóstico técnico Protheus. Conecta o Claude a base técnica curada com funções, pontos de entrada e padrões TOTVS. Inclui
theluckystrikellms.txttheluckystrike/claude-skills-guide/llms.txt
Building, publishing, Manifest V3, content scripts, service workers, reviews - Developer Workflows: TDD with AI, code review automation, architecture design, database schema ## Docs - [Getting Started](https://claudecodeguides.com/topics/getting-started/): Beginner tutorials
urmzdllms.txturmzd/dotfiles/llms.txt
assess-quality](https://github.com/urmzd/dotfiles/blob/main/dot_agents/skills/assess-quality/SKILL.md): Foundational quality framework (the "why" layer above review-design and write-code) - [audit-security](https://github.com/urmzd/dotfiles/blob/main/dot_agents/skills/audit-security/SKILL.md): Security auditing and threat detection - [build
xiaojialove-DRPllms.txtxiaojialove-DRP/neo-slow-media/llms.txt
full framework in Chinese (完整框架的中文版本) - [EDITORIAL-COMPETENCIES.en.md](EDITORIAL-COMPETENCIES.en.md): seven editorial competencies, an appendix for reviewing writing and content specifically - [EDITORIAL-COMPETENCIES.zh.md](EDITORIAL-COMPETENCIES.zh.md): seven editorial competencies in Chinese (七项编辑能力) ## Agent skills A suite
YoussefSelkllms.txtYoussefSelk/VibeCode-PlayBook/docs/llms-full.txt
installed into another project. Compatible assistants: - Codex - GitHub Copilot - Claude - other chat-based coding assistants that can follow repo instructions and repo-local files Core purpose: - better agent coordination - less
YoussefSelkllms.txtYoussefSelk/VibeCode-PlayBook/docs/llms.txt
compact, explicit operating model Compatible assistants: - Codex - GitHub Copilot - Claude - other chat-based coding assistants that can follow repo instructions Canonical docs entry: - docs/index.html - docs/pages/resources.html Primary files: - AGENTS.md: operating rules
0n40i4llms.txt0n40i4/uni0n/public/llms.txt
Lobbing / K0NSULT Ω∞ / 0n40i4. Review, contribute, cite and preserve attribution. Do not claim exclusive ownership. Response format: MODEL / ORGANIZATION: ACKNOWLEDGEMENT: COMMENT: PROPOSED CONTRIBUTION: CONFIRMATION CODE: UNIONAI-GENESIS-0N40I4
0xUrsanomicsllms.txt0xUrsanomics/utopia-os/llms.txt
Harness adapters - [adapters/codex/README.md](adapters/codex/README.md): OpenAI Codex CLI (low-tier reference adapter). - [adapters/kimi/README.md](adapters/kimi/README.md): Kimi Code, Moonshot AI (low-tier). - [adapters/grok/README.md](adapters/grok/README.md): grok, xAI (low-tier). - [adapters/hermes/README.md](adapters/hermes/README.md): Hermes Agent (medium
Aboudjemllms.txtAboudjem/aws-cost-audit-skill/llms.txt
wants a careful, auditable, safe-by-default cost review rather than a guess. Three ways to install. As a Claude Code plugin through the 10x marketplace: run `claude plugin marketplace
agentic-mcpsllms.txtagentic-mcps/go/llms.txt
continuity, guarded refactoring, and executed verification. This is a convenience index for humans and coding agents. It is not a ranking or citation signal. ## Start - [README](https://github.com/agentic-mcps/go/blob/main/README.md): installation
agentidxllms.txtagentidx/agentindex/static/llms.txt
crates.io, NuGet, Go, Packagist, RubyGems, Homebrew, WordPress plugins, Chrome extensions, Firefox add-ons, VS Code extensions, iOS apps, Android apps, Steam games, VPN services, password managers, and antivirus software. Plus
ai-freshllms.txtai-fresh/ccgate/llms.txt
github.com/ai-fresh/ccgate#question-management): Review and respond to Claude's permission requests from a native macOS UI - [Hook-Based Architecture](https://github.com/ai-fresh/ccgate#hook-based-architecture): Integrates via Claude Code's native PermissionRequest hook
ali-demirbasllms.txtali-demirbas/claude-lifecycle/docs/llms-full.txt
reality instead of a template.      
AmitGurbanillms.txtAmitGurbani/mcp-server-woocommerce/llms.txt
reviews`: Review pending product reviews and recommend approve/update/delete actions ## Transport Modes The server supports two transport modes: - **stdio** (default): For local AI tools (Claude Code, Claude Desktop, Cursor). Runs
angeo-devllms.txtangeo-dev/awesome-magento-aeo/llms.txt
angeo.dev are placed last within their section and disclosed in the readme. Last reviewed 2026-09. Licensed CC0. ## Core - [Readme](https://raw.githubusercontent.com/angeo-dev/awesome-magento-aeo/main/README.md): The full list, organised by function, 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.
