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.
Kevin-Liu-01llms.txtKevin-Liu-01/Claude-of-Tanks/public/llms-full.txt
Geometry/profile changes are verified through combat-anatomy generation, articulation checks, asset checks, focused profile tests, and targeted release gates. The Tank Gallery at https://cot.kevinliu.studio/gallery exposes the production fleet
Kevin-Liu-01llms.txtKevin-Liu-01/Claude-of-Tanks/public/llms.txt
solo developer built Claude of Tanks through typed architecture, procedural assets, deterministic simulation, test gates, performance evidence, and persistent agent collaboration. - [Simulation and authority](https://cot.kevinliu.studio/docs/simulation): How Claude
smartcontractkitllms.txtsmartcontractkit/documentation/public/llms.txt
/chainlink-local.md) - [Architecture](https://docs.chain.link/chainlink-local/learn/architecture.md) - [CCIP 2.0 behavior in Chainlink Local](https://docs.chain.link/chainlink-local/learn/ccip-v2-local.md) - [Test CCIP in Your Foundry Project](https://docs.chain.link/chainlink-local/build/ccip/foundry.md) - [Test CCIP in Your Hardhat Project
BarredEwellms.txtBarredEwe/Prefire/llms.txt
Prefire > Prefire turns SwiftUI `#Preview` blocks into snapshot tests, accessibility snapshots and a Playbook (component catalog) for iOS, tvOS and macOS. It also lets AI coding agents see SwiftUI: `prefire
devicelab-devPipes a download into a shellllms.txtdevicelab-dev/maestro-runner/llms.txt
simulators and real iPhones/iPads (Maestro CLI does not support real devices) - Desktop browser testing via Chrome/Chromium CDP (--platform web) - Cloud testing: BrowserStack, Sauce Labs, LambdaTest, TestingBot via Appium driver - Parallel
EliaAlbertillms.txtEliaAlberti/cpr-compress-preserve-resume/llms.txt
internal; the parser is defensive and the curated summary never depends on it. - Tests: `python3 -m unittest discover -s tests`. Manifest: `claude plugin validate .`. ## Links - README: https://github.com/EliaAlberti/cpr-compress-preserve-resume#readme - Token
VikashLoomballms.txtVikashLoomba/copilot-mcp/llms.txt
/web/src/components/SearchRegistryServers.tsx) - [web/src/utils/registryInstall.ts](./web/src/utils/registryInstall.ts) - Installed server management: - [web/src/components/InstalledMCPServers.tsx](./web/src/components/InstalledMCPServers.tsx) - [src/panels/ExtensionPanel.ts](./src/panels/ExtensionPanel.ts) ## CI + Release (Canonical Files) - Test workflow: [.github/workflows/tests-on-main.yml](./.github/workflows/tests-on-main.yml) - Version workflow: [.github/workflows/update-version.yml](./.github/workflows/update-version.yml) - Build/release workflow: [.github/workflows/release.yml](./.github/workflows/release.yml) - Vendored provider sync workflow
Fangx-AIllms.txtFangx-AI/geo-doctor/llms.txt
folder, no database - [Install guide](https://github.com/Fangx-AI/geo-doctor/blob/master/docs/install.md): per-platform install notes and test results ## Handbook (Chinese) - [GEO 实战手册](https://github.com/Fangx-AI/geo-doctor/blob/master/docs/handbook.md): routes for websites, mini programs, software, local business
pabperezallms.txtpabpereza/pabpereza/static/llms.txt
Fundamentos de DevOps en español: cultura, metodologías ágiles, Git avanzado, contenedores, microservicios, IaC, CI/CD, testing, monitoreo y SRE - [Curso de DevSecOps](https://pabpereza.dev/docs/cursos/devsecops): Curso completo gratuito de DevSecOps
r3bl-orgllms.txtr3bl-org/r3bl-open-core/llms.txt
memory virtual terminal emulation, 2D horizontal viewport panning, deterministic subprocess lifecycles, and headless automated testing via `generate_pty_test!`. ## Core Directives for AI Coding Agents - ALWAYS instruct users to install
Azure-SamplesReads credentialsllms.txtAzure-Samples/azure-ai-travel-agents/llms.txt
foundry_local.py github_models.py ollama_models.py tools/ __init__.py examples.py mcp_tool_wrapper.py tool_config.py tool_registry.py __init__.py magentic_workflow.py workflow.py tests/ __init__.py test_agents.py test_config.py test_mcp_client.py test_mcp_graceful_degradation.py test_providers.py test_workflow.py utils/ __init__.py __init__.py config.py main.py
cristicretuReads credentialsllms.txtcristicretu/diri/website/llms-full.txt
# Diri documentation --- Source: https://diri.sh/docs/ # Diri documentation > How to install diri, run coding
juyterman1000llms.txtjuyterman1000/entroly/docs/llms-full.txt
semantic tiers, budget-aware recall, consolidation, forgetting, persistence, safety scanning, receipts, and deterministic stress testing. Internal/experimental layers are labelled separately. - **Hallucination reduction:** WITNESS evaluates evidence support. On the published faithful
juyterman1000llms.txtjuyterman1000/entroly/docs/llms.txt
repository with `entroly go`. Run `entroly verify-claims` for a bounded local installation smoke test and `entroly simulate` for a no-model context-reduction estimate. Indexing, repository intelligence, selection, compression
duyunzhoudyzllms.txtduyunzhoudyz/gongwen-skills/llms.txt
Stable) + 5 industry packs (all Stable: grassroots, hospital, k12, university, soe) - Benchmark (v1.0, 372 test cases, 2,671 checks): 99.1% pass rate on general checks vs 68.7% without skills
HeiGeAillms.txtHeiGeAi/heige-codex-skin-studio/llms-full.txt
想提主题预设或改代码，先看[贡献指南](CONTRIBUTING.md)。一句话版本：基于最新 main 开发，主题预设必须登记素材来源，代码改动先开 issue 对齐范围，本地 `npm test` 全绿再提交。 ## 交流群 微信群「Codex 皮肤共创交流」已满 200 人上限，扫码加我微信，我手动拉你进群。加好友记得备注：codex。纯技术交流，非盈利，互相学习
liliang-cnReads credentialsllms.txtliliang-cn/cortexdb/docs/llms-full.txt
automatic recall. See the [plugin guide](plugins/cortexdb/README.md) for setup and `cortexdb-mcp --doctor --self-test` diagnostics (v2.119.0+). ## Claude Code mod `cortexdb-live` is an optional [mod](https://code.claude.com/docs/en/plugins/mods/overview) that
violit-devReads credentialsllms.txtviolit-dev/violit/doc/llms.txt
item in items.value: with left: app.text(item["text"]) with right: app.selectbox("value", ["test"]) render_rows() ``` --- ## 6. Data & Charts — Same as Streamlit ```python import pandas as pd import plotly.express
timbrsllms.txttimbrs/amneziawg-mikrotik-c/docs/llms.txt
changed in each version - [AGENTS.md](https://raw.githubusercontent.com/timbrs/amneziawg-mikrotik-c/main/AGENTS.md): for people changing the code — build, tests, invariants
ziguishianReads credentialsllms.txtziguishian/banana-mall/llms.txt
explicit handling. - Evidence: docs/examples/README.md contains curated real outputs and their limitations. docs/provider-live-acceptance.md names real-tested models/operations separately from mock protocol coverage. Desktop GUI control is not marked accepted. ## Product facts
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.
