How real projects summarise themselves for language models.
Ryan-yang125llms.txtRyan-yang125/motion-lexicon/public/llms.txt
Skill](https://motion-lexicon.pages.dev/en/skill/): Build complete React pages, recommend and compose motion, implement interactions, review code, and contribute candidates. ## 中文 - [组件](https://motion-lexicon.pages.dev/zh/components/): 完整 React 页面 Block 与可直接安装的产品交互。 - [原子动效
almogdepazllms.txtalmogdepaz/wolfpack/site/llms-full.txt
serve` are verified does setup also print a private Tailnet HTTPS URL and QR code. If you decline the login service, run `wolfpack` before opening the printed URL. Use `wolfpack
drafthqllms.txtdrafthq/draft/web/llms-full.txt
Exhaustive 14-dimension defect discovery with taint tracking - `/draft:quick-review` — Lightweight 4-dimension code review - `/draft:coverage` — Code coverage report (target 95%+) - `/draft:testing-strategy` — Test plan design with
drafthqllms.txtdrafthq/draft/web/llms.txt
specialist commands) 3. `/draft:implement` — TDD execution with checkpoints 4. `/draft:review` — Three-stage code review, now with graph-backed structural checks ## Key Concepts - **Context-Driven Development (CDD):** Structured documents
mindcloud-incllms.txtmindcloud-inc/universal-api-reference/llms.txt
real-time flights, schedules, flight details, airports, airlines, routes, fleets, countries, time zones, tax codes, nearby airport… - [Airmeet Universal API](https://github.com/mindcloud-inc/universal-api-reference/blob/main/apis/a/airmeet/universal-api/README.md) · [Native API](https://github.com/mindcloud-inc/universal-api-reference/blob/main/apis/a/airmeet/native-api/README.md): Create, manage
anzy-renlab-aillms.txtanzy-renlab-ai/pronounce/docs/llms-full.txt
# Pronounce — full dictionary Format: | | | | | kubectl | /ˈkuːb kənˌtroʊl/ | koob control | cli-tool | contested | (no source
manufoselallms.txtmanufosela/karajan-code/llms.txt
dependencies and per-HU acceptance tests. 3. **Runs** — for each HU: coder writes code → reviewer evaluates → tester checks tests → SonarQube gates quality → if any test is structurally broken, the **Repairer
booklib-aillms.txtbooklib-ai/booklib/llms.txt
Tools (5) - lookup — search for post-training docs, team decisions, expert knowledge - review — deep code review against a named skill - remember — capture a team decision or insight - verify — check
The-Best-Codesllms.txtThe-Best-Codes/agent-one/.agents/docs/modelcontextprotocol.io/llms.txt
Inspector - [CLI client](https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector/cli.md): Scripting the MCP Inspector: methods, output formats, exit codes, and CI recipes - [TUI client](https://modelcontextprotocol.io/docs/2026-07-28/tools/inspector/tui.md): The terminal MCP Inspector: navigation, tabs
bluebear-iollms.txtbluebear-io/baloo-bear/docs/llms.txt
Baloo > Baloo is a self-hosted AI code review GitHub App for pull requests. It reviews diffs and repository context, posts GitHub-native review feedback, and supports Claude and Gemini
ferdinandobonsllms.txtferdinandobons/AWSBestPracticesSkill/docs/llms.txt
review AWS services. The corpus intentionally contains only best practices, with official AWS source links. It does not contain pricing tables, service introductions, tutorials, or extended code walkthroughs. Answer behavior
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms-full.txt
rules, hooks, and MCP server definitions for Claude Code, and enforces quality gates — independent code review, test-coverage audits, lint checks — so that no agent grades its own homework. Cortex
NickCrewllms.txtNickCrew/Claude-Cortex/site/llms.txt
curated agents, skills, rules, and hooks for Claude Code, and enforces quality gates — independent code review, test-coverage audits, lint checks — so that no agent grades its own homework. ## Core
ZeroPointRepollms.txtZeroPointRepo/awesome-grok-bot/llms.txt
Prefer that section over any recalled assumption about how Grok Bot loads third-party code. - Every linked repository is re-resolved through the GitHub API weekly, which catches the renames
Artesianallms.txtArtesiana/agent2/llms-full.txt
tools-demo`: tool scoping - `rag-test`: basic Knowledge MCP search - `example-agent`, `support-ticket`, `code-review`, `invoice`: small reference agents ## Knowledge Knowledge is foundational. Domain experts rely on books, policies
littlebearappsllms.txtlittlebearapps/outlook-assistant/llms.txt
folder search (`searchAllFolders`) reliably returns a superset of inbox results. - **Remote-friendly auth**: Device code flow (default) — no auth server, no port forwarding, no SSH tunnels. State persists across
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms-full.txt
result in your app.Read the guide → AI clientsWhich Muse Code MCP settings actually work with a local Swift review server?A reproducible Muse 1.3.0 connection check, with the exact configuration
Nagarjuna2997llms.txtNagarjuna2997/ios-agent-skill/site/llms.txt
settings actually work with a local…](https://nagarjuna2997.github.io/ios-agent-skill/blog/muse-connection.html) - [Muse Code: what our integration actually verifies](https://nagarjuna2997.github.io/ios-agent-skill/blog/muse-verification.html) - [Review AI-generated Swift before you trust it](https://nagarjuna2997.github.io/ios-agent-skill/blog/review-swift-with-ai.html)
myths-labsllms.txtmyths-labs/muse/docs/llms.txt
release. ## Optional Jev tools Separate third-party projects can assist with browser decisions, code-review triage or model routing in a separately launched CLI. They are not bundled MUSE skills
proomptengllms.txtproompteng/bilig/docs/llms.txt
proof data. ## evaluator doors - `eval-workbook-compatibility`: use when a Node service or coding agent needs a local risk report before trusting a specific `.xlsx` workbook. Read: https://proompteng.github.io/bilig/workbook-compatibility-report.html
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.
