How real projects summarise themselves for language models.
coralogixllms.txtcoralogix/cx-skills/llms.txt
agentskills.io) ## What is Coralogix Coralogix is an observability platform for logs, metrics, traces, and security data. It supports OpenTelemetry-native collection, real-time analytics, dashboards, alerting, APM, infrastructure monitoring
csnyder256llms.txtcsnyder256/org-memory-os/docs/llms.txt
temporal memory, context compaction, degradation avoidance, prompt caching, prompt-injection defense, memory poisoning, agent security, Rule of Two, budget governor, LLM cost attribution, chargeback, GDPR right to erasure, crypto-shredding
cyanseekllms.txtcyanseek/dsh-native-playbook/llms.txt
version compatibility gate - Atomic profile update, DSH composition check, automatic rollback - No credential, security-policy, network-provider, or arbitrary-command mutations - Verified Tier-1 recipe: official session full-text search
danieljohnmorrisllms.txtdanieljohnmorris/ai-coworkers/llms.txt
github.com/danieljohnmorris/ai-coworkers/blob/main/CONTRIBUTING.md): dev setup, PR flow, coding conventions, what we won't merge, security-issue reporting. - [Release process + semver stance](https://github.com/danieljohnmorris/ai-coworkers/blob/main/docs/release-process.md): what MAJOR/MINOR/PATCH mean here, cut steps, deprecation
dioniipereyraallms.txtdioniipereyraa/ClaudeTool/docs/llms.txt
Source code](https://github.com/dioniipereyraa/ClaudeTool): the whole project, one repository. - [Threat model and security controls](https://github.com/dioniipereyraa/ClaudeTool/blob/main/SECURITY.md): what the bridge accepts, how pairing works, and what redaction does
ellmos-aillms.txtellmos-ai/ellmos-filecommander-mcp/llms.txt
Claude Code - [README (Deutsch)](https://github.com/ellmos-ai/ellmos-filecommander-mcp/blob/master/README_de.md): German version - [SECURITY.md](https://github.com/ellmos-ai/ellmos-filecommander-mcp/blob/master/SECURITY.md): Bilingual security policy for local stdio, explicit `fc_web_fetch` egress, process risks, and safe-mode boundaries
ellmos-aillms.txtellmos-ai/skills/llms.txt
German landing page with the same public user guidance. - [SECURITY.md](https://github.com/ellmos-ai/skills/blob/master/SECURITY.md): Bilingual security policy, Zero-Egress guarantees, and privacy boundary enforcement. - [THIRD_PARTY_LICENSES.md](https://github.com/ellmos-ai/skills/blob/master/THIRD_PARTY_LICENSES.md): Third-party software
Gadsotekllms.txtGadsotek/artifactflow/llms.txt
visible-cell manifest, and DOCX preview receives only a validated passive PDF derivative. The security page and threat model document these boundaries and their residual risks. Team sharing follows live
gaurav0107llms.txtgaurav0107/superhuman/llms.txt
github.com/gaurav0107/superhuman/blob/main/CONTRIBUTING.md): Repo layout, test conventions, and the agent-prompt / extracted-script split. - [SECURITY](https://github.com/gaurav0107/superhuman/blob/main/SECURITY.md): Full safety model and vulnerability reporting. - [TELEMETRY](https://github.com/gaurav0107/superhuman/blob/main/TELEMETRY.md):
grainulationllms.txtgrainulation/farmer/site/llms.txt
tailscale) are optional. ## Optional - [Issues](https://github.com/grainulation/farmer/issues): for bug reports and feature requests. - [Security policy](https://github.com/grainulation/farmer/blob/main/SECURITY.md): for responsible disclosure. - [Contributing guide](https://github.com/grainulation/farmer/blob/main/CONTRIBUTING.md): for contributors
humanity4aillms.txthumanity4ai/project_human/llms-full.txt
with new interfaces - May prefer step-by-step guidance - May be wary of online security ## Boundaries ### Always - Use minimum 16px font for body text - Ensure 4.5:1 contrast ratio (WCAG
humanity4aillms.txthumanity4ai/project_human/llms.txt
Issues**: https://raw.githubusercontent.com/humanity4ai/project_human/main/docs/good-first-issues.md - **Governance**: https://raw.githubusercontent.com/humanity4ai/project_human/main/GOVERNANCE.md - **Code of Conduct**: https://raw.githubusercontent.com/humanity4ai/project_human/main/CODE_OF_CONDUCT.md - **Security Policy**: https://raw.githubusercontent.com/humanity4ai/project_human/main/SECURITY.md - **Maintainers**: https://raw.githubusercontent.com/humanity4ai/project_human/main/MAINTAINERS.md - **Release Notes**: https://raw.githubusercontent.com/humanity4ai/project_human/main/RELEASE_NOTES.md - **Roadmap
hypeprinter007-stackllms.txthypeprinter007-stack/anchor-x402/docs/llms.txt
account. Methods: `peer/hello`, `capabilities/list`, `peer/quote`, `peer/receipt`. Our card follows A2A 0.3.0 (`protocolVersion`, `securitySchemes`/`security`, `provider.organization`) and carries a detached JWS in `signatures` (ES256 over the JCS-canonicalized card
infotradescoutllms.txtinfotradescout/Selective-Intelligence/docs/llms.txt
github.com/infotradescout/Selective-Intelligence/issues/new?template=feedback.yml Improvement suggestions: https://github.com/infotradescout/Selective-Intelligence/issues/new?template=suggestion.yml Questions and ideas: https://github.com/infotradescout/Selective-Intelligence/discussions Private security reports: https://github.com/infotradescout/Selective-Intelligence/security/advisories/new License: https://github.com/infotradescout/Selective-Intelligence/blob/main/LICENSE Companion project: Platynum-47 is a separate
irfad7llms.txtirfad7/claude-power-skills/docs/llms.txt
Claude Code: session memory and consolidation, context compression, multi-agent coordination, adversarial bug hunting, security review, calibrated effort estimation and decision archaeology. No wrappers, no dependencies. Just SKILL.md files. Claude
isatimurllms.txtisatimur/excalidraw-skill-pack/web/llms.txt
chart, venn, pyramid, evidence, comparison, high-level, it-state, data-flow, dp-integration, dp-security-matrix, bar, line, scatter, radar — each with editable .excalidraw + PNG at /gallery/ ## vs diagram-design
ivanestarllms.txtivanestar/eitr/llms.txt
scaffolding, CI + TMS wiring. Not a fit: unit testing, API-only testing, load/performance testing, security scanning. See the README's "When to use EITR" section for the full list
jenrehllms.txtjenreh/appkit/llms.txt
development standards and best practices - [CI/CD Best Practices](.github/instructions/github-actions-ci-cd-best-practices.instructions.md): GitHub Actions workflow structure and security - [Terraform Guidelines](.github/instructions/terraform.instructions.md): Terraform coding conventions - [Azure Terraform](.github/instructions/terraform-azure.instructions.md): Specific guidelines for Azure resources
kelgirechandrakant-cpullms.txtkelgirechandrakant-cpu/vibe-coding-playbook/llms.txt
Vibe Coding Playbook > A practical methodology and rules template for building, debugging, securing, and shipping production software using AI coding agents (Cursor, Antigravity, Claude Code, Windsurf, GitHub Copilot). ## Core Concepts
lpalboullms.txtlpalbou/AIRelays/llms-full.txt
click "Sign in again" repair that refreshes the account slot in place. ## Security Defaults - default listener `127.0.0.1:8080` (CLI) / `0.0.0.0:8317` (desktop, with a one-click loopback switch) - protected routes
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.
