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.
jfarcandllms.txtjfarcand/mirroir-mcp/llms.txt
accept # re-record every baseline; refuses to run in CI ``` Three verdicts, three exit codes: **0 = PASS**, **1 = FAIL**, **65 = DRIFT** — every structural assertion held and a drift metric moved
wazuhllms.txtwazuh/wazuh-documentation/source/llms.txt
sources](https://documentation.wazuh.com/current/deployment-options/wazuh-from-sources/index.md)** Compile and install the Wazuh manager and agent from source code as an alternative to the packages. Covers build dependencies, compiling, the installation wizard, enrollment
nirholasReads credentialsllms.txtnirholas/three.ws/llms-full.txt
# three.ws > Open-source platform for 3D AI agents. Turn text or a photo into
nirholasPipes a download into a shellllms.txtnirholas/three.ws/public/llms-full.txt
onto your page and tells the user what happened. Open SDK, one line of code, an accessible fallback, and a CLI that announces when your build finishes. ### Notifications
aws-samplesPipes a download into a shellllms.txtaws-samples/sample-well-architected-skills-and-steering/llms.txt
pillars (Operational Excellence, Security, Reliability, Performance Efficiency, Cost Optimization, Sustainability) to architecture discussions, code reviews, and design decisions. ## Installation Install via [skills.sh](https://skills.sh) (no clone needed): ``` npx skills
billy-enrizkyReads credentialsllms.txtbilly-enrizky/openbrowser-ai/stress-tests/llms-full.txt
papers are collected\n- [ ] Verify all 20 papers have complete metadata\n- [ ] Final review and completion" }} - Positive Examples: "evaluation_previous_goal": "Successfully navigated to the product page and found
mattrobinsonsrePipes a download into a shellllms.txtmattrobinsonsre/terrapod/llms.txt
first-class Terraform/OpenTofu provider, `terraform-provider-terrapod` (for managing Terrapod itself as code; see the `provider/` entry below and [docs/terraform-provider.md](docs/terraform-provider.md)). Deployed exclusively via a Helm chart on Kubernetes
QVerisAIPipes a download into a shellllms.txtQVerisAI/QVerisAI/agent/llms-full.txt
connects the runtime to professional data and tools, so the agent can find services, review their supported scope, and call them. They are complementary: OpenClaw provides an execution environment, while
QVerisAIPipes a download into a shellllms.txtQVerisAI/QVerisAI/agent/llms.txt
QVeris helps agents find, connect to, and call professional data and tool services, then review usage - They are complementary: OpenClaw supplies a runtime, while QVeris supplies service discovery, access, calling
pleaseaiReads credentialsllms.txtpleaseai/shunt/wiki/llms-full.txt
# shunt full documentation ## Overview Configuration exists to keep shunt generic: new upstreams are provider
SentryReads credentialsllms.txtgetsentry/dotagents/docs/public/llms.txt
getsentry/skills find-bugs # Add multiple skills at once npx @sentry/dotagents add getsentry/skills find-bugs code-review commit # Add all skills from a repo npx @sentry/dotagents add getsentry/skills
vinkius-labsReads credentialsllms.txtvinkius-labs/mcp-fusion/docs/llms.txt
# MCP Fusion > fusion is the TypeScript framework for production MCP servers. MVA architecture, structured
KyaniteLabsllms.txtKyaniteLabs/kinocut/docs/llms-full.txt
Creation: Hyperframes and local Revideo have separate runtime requirements. Custom executable scenes are trusted code. CPU/GPU availability alone does not prove encoder usability, decoded fidelity, portability or a fixed speedup
KyaniteLabsllms.txtKyaniteLabs/kinocut/llms.txt
github.com/KyaniteLabs/kinocut/blob/master/docs/VIDEO_RECEIPT.md - Rescue: https://github.com/KyaniteLabs/kinocut/blob/master/docs/RESCUE.md - 360 assembly: https://github.com/KyaniteLabs/kinocut/blob/master/docs/360_ASSEMBLY.md - AI-video review (dev tip): https://github.com/KyaniteLabs/kinocut/blob/master/docs/AI_VIDEO_REVIEW_AND_SALVAGE.md - FAQ: https://github.com/KyaniteLabs/kinocut/blob/master/docs/faq.md - Agent skill: https://github.com/KyaniteLabs/kinocut/blob/master/skills/kinocut/SKILL.md - Changelog
FlorianBruniauxllms.txtFlorianBruniaux/claude-cowork-guide/llms.txt
dashboards (beta) and animations (Motion, beta, Team and Enterprise) from any conversation - Execute task code in an isolated environment ## Boundaries to Keep in Mind - Folder access, the built-in browser
FlorianBruniauxllms.txtFlorianBruniaux/claude-cowork-guide/machine-readable/llms.txt
dashboards (beta) and animations (Motion, beta, Team and Enterprise) from any conversation - Execute task code in an isolated environment ## Boundaries to Keep in Mind - Folder access, the built-in browser
surendranbPipes a download into a shellllms.txtsurendranb/google-analytics-mcp/docs/llms-full.txt
error. | What varies | Values across these clients | |---|---| | Root key | `mcpServers` (most clients), `servers` (VS Code), `context_servers` (Zed), `mcp` (OpenCode), `mcp_servers` (Hermes), `mcp.servers` (OpenClaw, ZCode) | | Environment key | `env` (most
vstorm-collms.txtvstorm-co/agenticos/llms.txt
Configuration can only ever reach what code registered, which is what makes a no-code Builder safe to hand to somebody who is not an engineer. Companies end up with
oliver-zehentleitnerDeletes or force-pushesllms.txtoliver-zehentleitner/keep-the-why/llms.txt
framework already governs how the work gets done (brainstorming, planning, systematic debugging, TDD, code review), that workflow runs first; Keep the Why doesn't compete for that role, and preserves
sepehr071llms.txtsepehr071/awesome-iran-mcp/llms.txt
tools) - [.mcp.json](https://raw.githubusercontent.com/sepehr071/iran-mcp/main/.mcp.json): config for all servers - [marketplace.json](https://raw.githubusercontent.com/sepehr071/iran-mcp/main/.claude-plugin/marketplace.json): Claude Code plugin marketplace, one plugin per server plus bundles - [PLUGINS.md](https://raw.githubusercontent.com/sepehr071/iran-mcp/main/PLUGINS.md): plugins and skills
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.
