on-device-ai

on-device-ai is a Cross-platform mobile skill for AI agents, published by smart-village-solutions in the smart-village-app-app repository on GitHub. Skillspace rates on-device-ai C (70/100) and it passed the safety scan; the rating is based on static analysis only.

Software Mansion's best practices for on-device AI in React Native using React Native ExecuTorch. Covers LLMs (chat, tool calling, structured output), computer vision (classification, object detection, OCR, segmentation, style transfer, embeddings, text-to-image), speech processing (speech-to-text, text-to-speech, voice activity detection), VisionCamera real-time frame processing, model loading and resource management. Trigger on: 'react-native-executorch', 'ExecuTorch', 'on-device AI', 'on-device ML', 'local AI', 'offline AI', 'useLLM', 'useClassification', 'useObjectDetection', 'useOCR', 'useVerticalOCR', 'useStyleTransfer', 'useTextToImage', 'useImageEmbeddings', 'useImageSegmentation', 'useSpeechToText', 'useTextToSpeech', 'useVAD', 'useTextEmbeddings', 'useTokenizer', 'useExecutorchModule', 'ResourceFetcher', 'real-time frame processing', 'runOnFrame', 'tool calling', 'structured output', or any request to run AI/ML models locally in a React Native app.

Grade

C

Quality

70 / 100

Safety

Passed

GitHub stars

72

Unproven: rated by static analysis only, not yet compared head-to-head.

Not launch-quality. It is graded C with a clean safety verdict, but our quality filters exclude it: it is a near-duplicate variant of another skill. So it is not in our launch-quality set, the skills our MCP server searches and recommends. How launch-quality is decided

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.