How real projects summarise themselves for language models.
lastmile-aillms.txtlastmile-ai/mcp-agent/LLMS.txt
flight_mod_agent or lost_baggage_agent swarm = AnthropicSwarm(agent=triage_agent, context_variables={...}) test_input = "My bag was not delivered!" result = await swarm.generate_str(test_input) print("Result:", result
anbeimellms.txtanbeime/skill/public/llms-full.txt
github.com/anbeime/skill/blob/main/SKILL_SOURCES.json ## 官方技能来源（顶级团队） 本技能商店收录了来自以下顶级团队的官方技能： - **Anthropic** (17个) - docx, pptx, xlsx, pdf, mcp-builder, webapp-testing 等 - **Vercel** (7个) - react-best-practices, next-best-practices, composition-patterns 等 - **Cloudflare** (7个) - agents
tw93llms.txttw93/Waza/llms.txt
across Claude Code, Codex, Cursor, Antigravity, OpenCode, Pi, and compatible agents. - `think`: pressure-test a requirement and produce a decision-complete plan - `ui`: build or polish a distinctive frontend interface
Q00llms.txtQ00/ouroboros/llms-full.txt
Multi-model consensus evaluation/trigger.py Consensus trigger matrix Stage 1: Mechanical ($0) Lint, build, test, static analysis, coverage (threshold: 70%) Any check fails -> pipeline stops Stage 2: Semantic ($$) AC compliance, goal
Q00llms.txtQ00/ouroboros/llms.txt
specific configuration (claude-code, codex) api/ # API reference (core, MCP) contributing/ # Contributor guides (architecture, testing, patterns) tests/ # Test suite examples/ # Example projects pyproject.toml # Package metadata: ouroboros-ai, requires Python
FlorianBruniauxllms.txtFlorianBruniaux/claude-code-ultimate-guide/llms-full.txt
OpusPlan** | `/model opusplan` | Opus for planning, Sonnet for execution | | Task | Model | Effort | |------|-------|--------| | Rename, boilerplate, test gen | Haiku | low | | Feature dev, debug, refactor | Sonnet | medium–high | | Architecture, security audit | Opus | high
FlorianBruniauxllms.txtFlorianBruniaux/claude-code-ultimate-guide/llms.txt
learning: installable learning-path skill with prerequisite gates, local evidence, scheduled reviews, and a tested seven-module companion project - Context window management: 1M-token context on Sonnet 5, Opus
tinyplexllms.txttinyplex/tinybase/docs/llms-full.txt
exceptionally small (5.3kB-11.7kB), has zero runtime dependencies, and maintains 100% test coverage. - **Website**: https://tinybase.org - **Repository**: https://github.com/tinyplex/tinybase - **Documentation**: https://tinybase.org/api/ - **License**: MIT - **Author**: James
eugeniughelburllms.txteugeniughelbur/obsidian-second-brain/llms.txt
every surface; README Contributors section. https://github.com/eugeniughelbur/obsidian-second-brain/releases/tag/v0.13.0 - v0.12.0 (2026-07-11) "The Stress Test": a 4-lane adversarial audit (32 AI agents: every command file, hostile synthetic vaults, live
dagucloudllms.txtdagucloud/dagu/llms.txt
they do not clone, fetch, or push. This example creates a generated branch, runs tests inside its worktree, and then removes the worktree explicitly: ```yaml working_dir: ./repo steps
txn2llms.txttxn2/kubefwd/docs/llms-full.txt
port forwarding. ## Quick Start ```bash # Idle mode - API enabled by default sudo -E kubefwd # Test the API curl http://kubefwd.internal/api/health ``` Base URL: `http://kubefwd.internal/api` ## Key Endpoints ### Health & Info
melgarafaelllms.txtmelgarafael/DeskcommCRM/public/llms.txt
Paid/Booked/Closed); Nuvemshop integration for the e-commerce vertical - Compliance: multi-tenant Postgres RLS (isolation tested in CI), LGPD by design (redact, data_request, anonymization), append-only audit log - Stack: Next.js
flypythoncomllms.txtflypythoncom/python/llms.txt
FlyPython Repository Index for LLMs and AI Agents > FlyPython provides production-tested Python engineering playbooks, challenge courses with objective verification and per-checkpoint claim codes, verifiable test-driven starter examples
truerallms.txttruera/trulens/docs/llms.txt
code written against the pre-1.0 API - [Development setup](https://www.trulens.org/contributing/development/): Building and testing TruLens itself - [Release history](https://www.trulens.org/contributing/release_history/) - [Blog](https://www.trulens.org/blog/) - [PyPI](https://pypi.org/project/trulens/):
Ataraxy-Labsllms.txtAtaraxy-Labs/sem/docs/llms.txt
objects, traits, enums, functions, vals, extensions | | Nix | .nix | bindings, inherit declarations | | Zig | .zig | functions, tests, variables | Plus structured data formats: | Format | Extensions | Entity Types | |--------|-----------|--------------| | JSON | .json | properties, objects
LangChainllms.txtlangchain-ai/langgraphjs/docs/docs/llms.txt
deployment (JavaScript)](https://docs.langchain.com/oss/javascript/langgraph/cloud/deployment/setup_javascript/) - [How to customize Dockerfile](https://docs.langchain.com/oss/javascript/langgraph/cloud/deployment/custom_docker/) - [How to test locally](https://docs.langchain.com/oss/javascript/langgraph/cloud/deployment/test_locally/) - [How to integrate LangGraph into your React application](https://docs.langchain.com/oss/javascript/langgraph/cloud/how-tos/use_stream_react/)
dimthinkllms.txtdimthink/PriceAI/public/llms.txt
Official API section focuses on official APIs, public documentation, public model routing platforms, free test quotas, and Token Plans that can be verified from public sources. It does not present
Googlellms.txtgoogle/zerocopy/anneal/v1/llms-full.txt
section`. **What this means for you:** You cannot use Lean's `#eval` command to test the runtime behavior of your verified functions computationally. They are strictly mathematical models. # Module
tractorjuicellms.txttractorjuice/arc-kit/docs/llms.txt
Design](https://arckit.org/guides/agent-design.md): `/arckit:agent-design` patterns, tool contracts, memory, orchestration, guardrails, and testing. - [AI Agent Governance](https://arckit.org/guides/agent-governance.md): `/arckit:agent-governance` oversight model, approvals, audit requirements, monitoring
mrgooniellms.txtmrgoonie/claudekit-skills/.claude/skills/claude-code/llms.txt
commands (/cook, /plan, /debug, /test) - Fix commands (/fix:fast, /fix:hard, /fix:types, /fix:test, /fix:ui, /fix:ci) - Documentation commands (/docs:init, /docs:update, /docs:summarize) - Git commands (/git
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.
