Android skills is a collection of modular instructions and resources that help AI agents handle specialized Android development tasks. Android developers use it to guide coding agents toward Android-specific workflows, and the catalogue lists some of its skills and plugin.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add android/skills --skill litert-runtimegit clone --depth 1 https://github.com/android/skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/android/skills/litert-runtime)<a href="https://agentmods.dev/skills/android/skills/litert-runtime"><img src="https://agentmods.dev/badge/skills/android/skills/litert-runtime/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/android/skills/litert-runtime"><img src="https://agentmods.dev/badge/skills/android/skills/litert-runtime.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00127 | $0.04477 |
| Opus 5.5 | $0.00051 | $0.01791 |
| Sonnet 5.5 | $0.00025 | $0.00895 |
| Haiku 4.5 | $0.00013 | $0.00448 |
Grade A, and why
litert-runtime scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.
This skill provides step-by-step guidance for building an Android app that runs
a .tflite model with the LiteRT CompiledModel API
(com.google.ai.edge.litert:litert 2.x; source repository) on the CPU or
the GPU. Don't use the deprecated org.tensorflow.lite.Interpreter API. For
open text language models using .litertlm files, suggest the litert-lm
skill.
Prerequisites
- A Kotlin Android project (
minSdkmust be24or higher, as declared by the LiteRT 2.3.0 AARs). - The dependencies in the app-level
build.gradle.ktsfile from Google Maven:implementation("com.google.ai.edge.litert:litert:2.3.0")andimplementation("com.google.ai.edge.litert:litert-gpu:2.3.0"). From 2.3.0 the GPU accelerator is the second artifact: withlitertalone the app builds, andCompiledModel.createwithAccelerator.GPUthrowsLiteRtExceptionbecause the APK has no GPU accelerator library (Logcat logsGPU accelerator could not be loaded and registered). No manifest entry is needed:litert-api, whichlitertdepends on, declares the OpenCL driver libraries (uses-native-library) in its own manifest. - A verified
.tflitemodel and its input contract (input dimensions, mean, standard deviation, channel order, and tensor layout). For models with a verified recipe, inspect the LiteRT model recipes.
Critical mandates
- Single-thread confinement : One single-thread executor or confined coroutine dispatcher must own the
CompiledModelinstance. Creation, inference, and closing must execute on that same background thread, never on the main thread. - Buffer lifecycle : Allocate
TensorBufferinstances once usingcreateInputBuffersandcreateOutputBuffers, reuse them across inferences, and close all input and output buffers before closing theCompiledModel. - Synchronous timing :
model.runenqueues work on the GPU and returns before GPU execution completes. Always measuremodel.runand output buffer readback (outputs[0].readFloat) together. - Warm-up and exception safety : Execute one warm-up inference inside the helper constructor's
initblock so first-run GPU shader compilation doesn't block the first user interaction, and callcloseincatchbefore rethrowing so neitherCompiledModelnorTensorBufferhandles leak if buffer allocation or warm-up throws.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 359 lines · 127 tokens per session scan A bbccfb836f66
litert-runtime is a skill published in the GitHub repository android/skills (7,842 stars, last pushed 2d ago), licensed Apache-2.0. It adds 127 tokens to every session and 4,477 once invoked, about $0.0005 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.
Other skills, from other repositories
deploy-edge-ai-model
Deploy machine learning models to edge devices using Google AI Edge Gallery, TensorFlow Lite, ONNX Runtime, and MediaPipe. Covers model quantization (INT8/INT4), on-device inference with Gemma 4 models, Android/iOS deployment via AI Edge Gallery, hardware delegate selection (GPU/NPU/DSP), and performance benchmarking…
apple-on-device-ai
Integrate on-device AI using Foundation Models framework, Core ML, and open-source LLM runtimes on Apple Silicon. Covers Foundation Models (LanguageModelSession, @Generable, @Guide, SystemLanguageModel, structured output, tool calling), Core ML (coremltools, model conversion, quantization, palettization, pruning…
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
foundation-models-on-device
Apple FoundationModels framework for on-device LLM — text generation, guided generation with @Generable, tool calling, and snapshot streaming in iOS 26+.
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
developer-device-platform-basics
Provides guidance and instructions on managing remote devices on Developer Device Platform (DDP). Use when reserving remote Android devices, establishing connection tunnels, checking session status, or extending/cancelling leases. Don't use for iOS or local device/hardware inquiries.