How real projects summarise themselves for language models.
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
Platanorllms.txtPlatanor/hardware-compliance-handbook/llms.txt
Cybersecurity Act / EUCC (Regulation (EU) 2019/881) — maintained by Platanor Technologies (platanor.com), an embedded security firm for IoT/hardware manufacturers in the EU. All content is in English. NOT legal advice
gbevinllms.txtgbevin/RouteMIDI/llms.txt
scripts: the generation contract, the `--schema json` metadata, the `--mcp` MCP server and its security model (stable as of 1.0.0, versioned by contractVersion) - [JAVASCRIPT.md](https://raw.githubusercontent.com/gbevin/RouteMIDI/master/JAVASCRIPT.md): the per-message
OptimNowllms.txtOptimNow/finops-mcp-resources/llms.txt
Cloud FinOps — cloud cost optimization, AI cost management, FinOps automation, tagging governance, and security guardrails. This open-source repository provides tutorials, server documentation, client guides, and governance frameworks for implementing
tcsenpaillms.txttcsenpai/specification-website-skill/references/llms-full.txt
page is about. The order matters when the tab is narrow: ```html HSTS · Security · The Website Specification The Website Specification — Security — HSTS ``` For the homepage, the site name
myclaude-shllms.txtmyclaude-sh/myclaude-creator-engine/llms.txt
Claude Code (not just install pre-built ones) - Has domain expertise worth packaging — law, security, marketing, coaching, finance, research, operations - Asks "what should I build?" or "how do I share
PIsbergllms.txtPIsberg/vibetags/llms.txt
fail as flakes far from this file, so the cost never points back here ## 🔐 Security-Critical Code - [JsonValueSpans](se.deversity.vibetags.processor.internal.JsonValueSpans): Security-critical code [Splices annotation text, including attributes copied
sgroy10llms.txtsgroy10/speclock/llms-full.txt
Coverage Audit (v5.4) Scans your codebase and tells you what's unprotected. Like a security scanner, but for AI constraint gaps. Suggests locks for exposed areas. ## Lock Strengthener (v5.4) Grades
AreevAIllms.txtAreevAI/areev/llms.txt
Python, the web console, and building a self-improving agent end to end. ## Compliance & security - [GDPR](docs/gdpr.md): Obligations mapped to mechanisms for a DPIA — DSAR access/portability, one-operation erasure, audit
dalrootllms.txtdalroot/agentic-seo/docs/llms-full.txt
reports. Agentic SEO inspects the codebase, writes JSON-LD schemas, repairs broken canonicals, pins security headers, and fixes HTML directly. 2. **Deterministic Evidence vs. Guesswork**: All evaluations run local, verified
dalrootllms.txtdalroot/agentic-seo/docs/llms.txt
Product, Article, Organization, LocalBusiness, FAQPage, BreadcrumbList). - **Technical SEO**: Inspects robots.txt, XML sitemaps, redirects, HTTP security headers, and Core Web Vitals (LCP, CLS, INP). - **GitHub Repository SEO**: Audits repository metadata, topics
khaskyllms.txtkhasky/awesome-agents-md/llms.txt
else is opt-in. ## Core - [AGENTS.md](https://github.com/khasky/awesome-agents-md/blob/main/AGENTS.md): the always-loaded ruleset — boundaries, security, the verification gate, workflow, debugging, the lazy-senior-dev coding ladder, communication style, the commit
arikusillms.txtarikusi/nakkas/llms-full.txt
instead of silently rendering broken output. If an attribute value is blocked by the security filter (event handlers, javascript: URIs, non-image data: URIs), the render succeeds but a design
backenlyllms.txtbackenly/backenly/public/llms.txt
repair. Update and delete need a non-empty filter. | | `set_rls` | Row-level security as exact SQL predicates, installed verbatim and read back. | | `generate_types` | TypeScript types, a typed client
CorpusIQllms.txtCorpusIQ/corpusiq-docs/llms-full.txt
Reference](/docs/api/endpoints) | Full endpoint documentation with request/response schemas | | [Authentication](/docs/api/authentication) | Bearer token management and security best practices | | [Connectors](/connectors) | Complete list of supported integrations | | [Security](/security) | Architecture, compliance, and data
CorpusIQllms.txtCorpusIQ/corpusiq-docs/llms.txt
QuickBooks, Shopify, Stripe, HubSpot, GA4, Google Ads, Meta Ads, Salesforce, Slack, Gmail, Notion, and - [Security](https://www.corpusiq.io/docs/security): - [Changelog](https://www.corpusiq.io/docs/changelog): Complete CorpusIQ changelog and version history. Track
heymegabytellms.txtheymegabyte/claude-skills/llms.txt
durable stance + stack defaults/constants - **Doctrinal rules** — 160 always-/pack-loaded rules in `rules/` (autonomy · verification · security · feature-flags · payments · …); routed via the Router's “Doctrinal principles” + pack lists - [Changelog](CHANGELOG.md) — package
ShieldNet-360llms.txtShieldNet-360/secure-vibe/docs/llms-full.txt
SecureVibe — full documentation Prevention-first security for AI-written code. This file concatenates the core docs for LLM ingestion. Source: https://shieldnet-360.github.io/secure-vibe/ ================================================================ # SOURCE: docs/index.md ================================================================ # SecureVibe Prevention-first security
ShieldNet-360llms.txtShieldNet-360/secure-vibe/docs/llms.txt
SecureVibe > Prevention-first security for AI-written code. Signed security skills shape what AI coding assistants (Claude Code, Cursor, Copilot, Codex, Windsurf, Cline, Antigravity, Devin) write at generation time; deterministic
AnayDhawanllms.txtAnayDhawan/openvidstudio/llms.txt
github.com/AnayDhawan/openvidstudio/blob/main/CODE_OF_CONDUCT.md) - Good first issues: Check the issues tab for the current list. ## Security - [Security policy](https://github.com/AnayDhawan/openvidstudio/blob/main/SECURITY.md): report vulnerabilities privately to dhawansanay@gmail.com, not as a public issue. ## Optional
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.
