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.
Unity-Technologiesllms.txtUnity-Technologies/com.unity.toonshader/llms.txt
menu item `Toon Shader > Generate Shader Files` (implemented in [UnityToonShaderGenerator.cs](com.unity.toon-graphics-test/Editor/UnityToonShaderGenerator.cs)) - **Command Line**: Run [generate_UnityToon.py](generate_UnityToon.py), [generate_UnityToon.sh](generate_UnityToon.sh), or [generate_UnityToon.bat](generate_UnityToon.bat) from the repository root The generators
No other project uses it yet
skforecastllms.txtskforecast/skforecast/docs/llms-full.txt
train) # Predict - exog must cover the forecast horizon predictions = forecaster.predict(steps=10, exog=exog_test) ``` ## Categorical Exogenous Variables All ML forecasters (ForecasterRecursive, ForecasterDirect, ForecasterRecursiveMultiSeries, ForecasterDirectMultiVariate, ForecasterRecursiveClassifier) include a `categorical_features
No other project uses it yet
bartblastReads credentialsllms.txtbartblast/hologram/llms-full.txt
elixirc_paths/1` functions in `mix.exs` to include the `app` directory: ```elixir defp elixirc_paths(:test), do: ["app", "lib", "test/support"] defp elixirc_paths(_env), do: ["app", "lib"] ``` This allows
No other project uses it yet
umputunReads credentialsllms.txtumputun/ralphex/llms.txt
installed from source, and the maintainer has no Windows machine and does not test there. The Ctrl+\ break, file-lock-based active session detection, and cleanup of descendant processes
No other project uses it yet
aklofasllms.txtaklofas/kicad-happy/llms.txt
skills. ## Documentation - [Contributing Guide](https://github.com/aklofas/kicad-happy/blob/main/CONTRIBUTING.md): How detectors work, how to add skills, test harness, code style - [Validation Summary](https://github.com/aklofas/kicad-happy/blob/main/VALIDATION.md): Test methodology, 5,800+ project corpus
Steady6 mentions in 2 weeks
No other project uses it yet
arihantcodesllms.txtarihantcodes/spectrum-ui/public/llms-full.txt
# Spectrum UI — Full Catalog > Spectrum UI is an open-source React component and block
No other project uses it yet
arihantcodesllms.txtarihantcodes/spectrum-ui/public/llms.txt
# Spectrum UI > Spectrum UI is an open-source React component and block library featuring
No other project uses it yet
photon-hqllms.txtphoton-hq/imessage-kit/llms.txt
implements SendPort — depend on the interface in app code // and inject a stub in tests. const onDM: MessageCallback = (msg) => { /* ... */ } // DispatchEvents = 5 watcher callbacks passed to sdk.startWatching(). const events: DispatchEvents = { onIncomingMessage
No other project uses it yet
ealushllms.txtealush/emoji-picker-react/llms-full.txt
selection | `onEmojiClick` is the selection callback; filter there | | Query cells with `getByRole('button')` in tests | `getByRole('gridcell', { name: 'grinning face' })` | | A bare `Root` with no height | Give Root a height
Steady22 mentions in 2 weeks
No other project uses it yet
hotovoReads credentialsllms.txthotovo/aider-desk/llms.txt
This file is a merged representation of a subset of the codebase, containing specifically
No other project uses it yet
nucliwebllms.txtnucliweb/webperf-snippets/public/llms-full.txt
WebPerf Snippets — Full Reference Tested JavaScript snippets that measure and debug web performance. Your AI agent runs them for you, or you run them yourself in DevTools. Source: https://webperf-snippets.net
nucliwebllms.txtnucliweb/webperf-snippets/public/llms.txt
WebPerf Snippets > Tested JavaScript snippets that measure and debug web performance. Your AI agent runs them for you, or you run them yourself in DevTools. > Source: https://webperf-snippets.net > Version
mbaileyllms.txtmbailey/voicemode/llms.txt
Copilot Chat in your editor to give you code suggestions, explain code, generate unit tests, and suggest code fixes. - [Chat in Mobile](https://docs.github.com/en/copilot/how-tos/chat-with-copilot/chat-in-mobile): You can use GitHub Copilot
Steady9 mentions in 2 weeks
No other project uses it yet
RyanAlbertsllms.txtRyanAlberts/best-of-Agent-Harnesses/llms.txt
order. Each one eliminates most of the list; by the en - How to test-drive a harness: https://ryanalberts.github.io/best-of-Agent-Harnesses/compare/how-to-test-drive-a-harness/ — Spec sheets cannot answer "which harness should I use," because
koxudaxiPipes a download into a shellllms.txtkoxudaxi/fastapi-code-generator/docs/llms-full.txt
input api.yaml --output app --output-model-type pydantic_v2.BaseModel ``` For the full option matrix and tested examples, see the [CLI reference](cli-reference.md). ## CLI Help Snapshot This block is generated from
No other project uses it yet
brayonpiReads credentialsllms.txtbrayonpi/hexstellar/llms.txt
units and re-run the DOMAIN check yourself. **`hexstellar demo` is a smoke test — it proves the pipe, never the product. The live catalogue contains encoding recipes, not the allowed
No other project uses it yet
NousResearchReads credentialsllms.txtNousResearch/atropos/llms.txt
github.com/NousResearch/atropos.git cd atropos # Core usage from local clone pip install -e . # Development (includes testing, linting tools) pip install -e .[dev] # Running examples (includes dependencies like vLLM, transformers) pip install
sceneviewReads credentialsllms.txtsceneview/sceneview/llms.txt
Compose fit together - [Performance](https://sceneview.github.io/docs/performance/): frame budget, quality levels, what costs what - [Testing](https://sceneview.github.io/docs/testing/): testing a scene without a device - [Integrations](https://sceneview.github.io/docs/integrations/): Sketchfab, Rerun.io
sipyourdrink-ltdPipes a download into a shellllms.txtsipyourdrink-ltd/bernstein/docs/llms-full.txt
same run. - Git worktree isolation per agent. Main branch stays clean. - Janitor verification: tests, lint, types, PII gating. - File-based state in `.sdd/`. No database. Inspect with `cat`, back
Surging3 mentions in 2 weeks
1 project uses a version of this
SceneViewReads credentialsllms.txtSceneView/sceneview-android/llms.txt
Compose fit together - [Performance](https://sceneview.github.io/docs/performance/): frame budget, quality levels, what costs what - [Testing](https://sceneview.github.io/docs/testing/): testing a scene without a device - [Integrations](https://sceneview.github.io/docs/integrations/): Sketchfab, Rerun.io
No other project uses it yet
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.
