google-ai-edgeSkillcalculate-hash
google-ai-edge/gallery/skills/built-in/calculate-hash/SKILL.md
Calculate the hash of a given text.
2 projects use a version of this
Find the best CLAUDE.md, AGENTS.md and Claude skills
One search for your own team's files and the public ecosystem. See how real projects write their agent instructions, and bring the good ideas home.
Your trail
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.
Worked for most · soon
google-ai-edgeSkillgoogle-ai-edgeSkillinteractive-map
google-ai-edge/gallery/skills/built-in/interactive-map/SKILL.md
Show an interactive map view for the given location.
2 projects use a version of this
google-ai-edgeSkillkitchen-adventure
google-ai-edge/gallery/skills/built-in/kitchen-adventure/SKILL.md
Act as a dungeon master for a text-based adventure set in a world where everyone is a sentient kitchen appliance. Trigger when user says "start kitchen adventure".
2 projects use a version of this
google-ai-edgeSkillmood-tracker
google-ai-edge/gallery/skills/built-in/mood-tracker/SKILL.md
A simple mood tracking skill that stores your daily mood and comments. Use this when the user wants to log their mood, track how they feel, or see their mood history.
2 projects use a version of this
google-ai-edgeSkillqr-code
google-ai-edge/gallery/skills/built-in/qr-code/SKILL.md
Generates a QR code for the given url.
6 projects use a version of this
google-ai-edgeSkillquery-wikipedia
google-ai-edge/gallery/skills/built-in/query-wikipedia/SKILL.md
Query summary from Wikipedia for a given topic.
2 projects use a version of this
google-ai-edgeSkillsend-email
google-ai-edge/gallery/skills/built-in/send-email/SKILL.md
Send an email.
27 projects use a version of this
google-ai-edgeSkilltext-spinner
google-ai-edge/gallery/skills/built-in/text-spinner/SKILL.md
Spin the given text on my head.
2 projects use a version of this
google-ai-edgeSkillmood-music
google-ai-edge/gallery/skills/featured/mood-music/SKILL.md
A skill to suggest or play music based on the user's mood, including analyzing images or audio, by querying available genres and generating music via the Loudly API.
3 projects use a version of this
google-ai-edgeSkillrestaurant-roulette
google-ai-edge/gallery/skills/featured/restaurant-roulette/SKILL.md
Show a roulette wheel to allow user to randomly select a restaurant based on location and cuisine.
3 projects use a version of this
google-ai-edgeSkillvirtual-piano
google-ai-edge/gallery/skills/featured/virtual-piano/SKILL.md
Show a virtual piano to play music
2 projects use a version of this
google-ai-edgeAGENTS.mdLiteRT / tensor
google-ai-edge/LiteRT/tensor/AGENTS.md
This directory contains the C++ LiteRT Tensor API: a lightweight, backend-agnostic graph construction and execution framework for on-device generative AI and ML models across XNNPACK (CPU), ML Drift (OpenCL/Metal/WebGPU GPU), TFLite FlatBuffer export, and multi-backend ModelChain runners. - GPU tests on Forge (ML Drift over OpenCL): Tag cc_test targets that require an OpenCL GPU with tags = ["requires-gpu-sm90"]. - Large checkpoint tests: Do not check multi-GB .safetensors or .gguf weights into Piper. Keep unit tests in TAP fast and hermetic…
google-ai-edgeSkillconverting-pytorch-to-litert
google-ai-edge/ai-edge-torch/SKILL.md
Converts PyTorch models (e.g. ResNet, timm, HuggingFace transformers) directly to LiteRT (.tflite) flatbuffer format. Use when converting PyTorch models to TFLite, setting up export environments, or troubleshooting torch-to-litert conversion bugs. Don't use for ONNX exports or converting existing TensorFlow models.
google-ai-edgeSkillaccuracy-safe-quantization
google-ai-edge/litert-samples/skills/accuracy-safe-quantization/SKILL.md
Shrink a converted LiteRT model with ai-edge-quantizer (fp16 / int8 / int4) without losing accuracy, verifying parity against the float source after every step. Use when choosing a quantization recipe for a new model, when a quantized model fails to load, degrades on a task benchmark, or degenerates over long generations, or when deciding between dynamic-range, weight-only, and blockwise variants.
google-ai-edgeSkilllitert-lm
google-ai-edge/litert-samples/skills/android/litert-lm/SKILL.md
Builds an Android app that runs an open text LLM on the device, on the
Surging1 mention in 2 weeks
1 project uses a version of this
google-ai-edgeSkilllitert-runtime
google-ai-edge/litert-samples/skills/android/litert-runtime/SKILL.md
Configures and implements LiteRT (.tflite) on-device inference on Android
google-ai-edgeSkillbenchmark-on-ddp
google-ai-edge/litert-samples/skills/benchmark-on-ddp/SKILL.md
Measure a LiteRT .tflite model with `benchmark_model` on Developer Device Platform (DDP) lab phones through `litert benchmark --ddp`, or on the Mac you run it from, and turn the session into rows of the performance leaderboard under benchmark/leaderboard - one matrix entry per model, one session per accelerator, collect results.pb and runtime_info.pb, rebuild board.json, check the page, commit the data. Use when a model needs latency and memory numbers per platform, device and accelerator, or when a new benchmark_model release means re-measuring the board.
google-ai-edgeSkillcompiled-model-app-scaffolding
google-ai-edge/litert-samples/skills/compiled-model-app-scaffolding/SKILL.md
Build a new Android app (Kotlin, Compose) around a verified LiteRT model using the CompiledModel API - the app architecture, the inference-layer lifecycle rules, model delivery, and the UI traps that masquerade as model bugs. Use when turning a converted and device-verified model into a demo or product app, when an app's inference layer leaks memory or blocks the UI, or when a model that verified clean looks wrong inside an app.
google-ai-edgeSkillgpu-clean-conversion
google-ai-edge/litert-samples/skills/gpu-clean-conversion/SKILL.md
Convert a PyTorch or Hugging Face model into a LiteRT model that runs fully on the GPU via the CompiledModel API with verified-correct output, and lay it out as a model recipe. Use when converting a new model, or when a converted model is rejected by the GPU, falls back to CPU, or returns wrong numbers on device.
google-ai-edgeSkilllitert-compiled-model-migration
google-ai-edge/litert-samples/skills/litert-compiled-model-migration/SKILL.md
Rapidly migrate an Android application from legacy TensorFlow Lite (TFLite) to the modern LiteRT CompiledModel API (2.x) in Open Source GitHub repositories, keeping the TensorFlow Lite Support Library as LiteRT Support (litert-support 2.3.0). Covers buffer reuse, NPU JIT compilation, a reference implementation, and a two-stage verification gate (compile check, then an on-device parity test against a golden output).
Agent instruction files
What are agent instruction files?
Plain text files in a repository that tell a coding agent how the project works: commands to run, conventions to follow and things to avoid. CLAUDE.md, AGENTS.md, cursor rules and skills are the common kinds.
CLAUDE.md or AGENTS.md?
CLAUDE.md is read by Claude Code. AGENTS.md is an open format that Codex, Cursor and other agents read. Many projects keep one and point the other at it.
What is a skill?
A folder with a SKILL.md that describes one capability, such as filling PDFs or reviewing code. The agent loads it only when the task calls for it.
Can I search my own team's files too?
Your agents already can, over MCP, limited to the files you're allowed to read. Searching them from this page is coming.