All skills
38,472 Skills
Search uses this published catalog; rankings and counts are snapshots.
accuracy-safe-quantization
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 bench
benchmark-on-ddp
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 mo
compiled-model-app-scaffolding
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
gpu-clean-conversion
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, o
litert-lm
Creates an Android app that runs an open text LLM on the device, on the CPU or the GPU, with the LiteRT-LM Kotlin API. Use this skill to build a new chat, summarization or extraction app with a .litertlm model from Hugging Face litert-community (Gemma, Qwen, Llama, Phi) - the dep
litert-runtime
Creates an Android app that runs a .tflite model on the CPU or the GPU with the LiteRT CompiledModel API in Kotlin. Use this skill to build a new app around a vision, audio or embedding model, or to add on-device inference to an existing app - the dependency, where the model file
Open Quadtree Mapping
This is a monocular dense mapping system corresponding to IROS 2018 "Quadtree-accelerated Real-time Monocular Dense Mapping"
Artificial Nose
Instructions, source code, and misc. resources needed for building a Tiny ML-powered artificial nose.
deep-research
Use only when the user explicitly requests comprehensive multi-source research, such as "research X", "deep dive into X", "comprehensive review of X", "systematic comparison between X and Y", "investigate the landscape of X", or Chinese equivalents like "调研一下X", "深入研究X", "全面对比X与Y
systematic-document-and-literature-review
Use this skill when the user wants a systematic review, thematic synthesis, or cross-document analysis across multiple academic papers OR provided general documents (reports, internal memos, web articles). Retrieves sources via arXiv, internal Knowledge Base (KB), or direct URLs.
ROS Behavior Tree
Behavior Trees Library for ROS (Robot Operating System). In C++ and python
Motion Sense
MotionSense Dataset for Human Activity and Attribute Recognition ( time-series data generated by smartphone's sensors: accelerometer and gyroscope) (PMC Journal) (IoTDI'19)
Create Dapp Solana Nextjs
Scaffolding for a Solana dapp using TS, Next.JS, Tailwinds CSS, and Daisy UI
vietnamese-landing-copy
Writes and reviews native-quality Vietnamese (vi-VN) marketing copy for landing pages — especially real-estate (bất động sản) project pages, plus SaaS and e-commerce. Use whenever generating, translating, or reviewing Vietnamese website copy, headlines, CTAs, section labels, lead
Catalog captured:2026-11-21