[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-callstack-react-native-ai-skills":3,"mdc--11k12f-key":39,"related-repo-callstack-react-native-ai-skills":1029,"related-org-callstack-react-native-ai-skills":1038},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":34,"sourceUrl":37,"mdContent":38},"react-native-ai-skills","integrate on-device AI in React Native","Provides integration recipes for the React Native AI @react-native-ai packages that wrap the Llama.rn (Llama.cpp), MLC-LLM, Apple Foundation backends. Use when integrating local on-device AI in React Native, setting up providers, model management.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"callstack","Callstack","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fcallstack.png","callstackincubator",[13,17,20,23],{"name":14,"slug":15,"type":16},"React Native","react-native","tag",{"name":18,"slug":19,"type":16},"LLM","llm",{"name":21,"slug":22,"type":16},"Mobile","mobile",{"name":24,"slug":25,"type":16},"AI Infrastructure","ai-infrastructure",1371,"https:\u002F\u002Fgithub.com\u002Fcallstackincubator\u002Fai","2026-04-06T18:06:48.66379","MIT",54,[32,19,33,15],"ai","on-device-ai",{"repoUrl":27,"stars":26,"forks":30,"topics":35,"description":36},[32,19,33,15],"On-device LLM execution in React Native with Vercel AI SDK compatibility","https:\u002F\u002Fgithub.com\u002Fcallstackincubator\u002Fai\u002Ftree\u002FHEAD\u002Fskills\u002Freact-native-ai","---\nname: react-native-ai-skills\ndescription: Provides integration recipes for the React Native AI @react-native-ai packages that wrap the Llama.rn (Llama.cpp), MLC-LLM, Apple Foundation backends. Use when integrating local on-device AI in React Native, setting up providers, model management.\nlicense: MIT\nmetadata:\n  author: Callstack\n  tags: react-native, ai, llama, apple, mlc, ncnn, vercel-ai-sdk, on-device\n---\n\n# React Native AI Skills\n\n## Overview\n\nExample workflow for integrating on-device AI in React Native apps using the @react-native-ai ecosystem. Available provider tracks (can be combined):\n\n- **Apple** – Apple Intelligence (iOS 26+)\n- **Llama** – GGUF models via llama.rn\n- **MLC** – MLC-LLM models\n- **NCNN** – Low-level NCNN inference wrapper (vision, custom models)\n\n## Path Selection Gate (Must Run First)\n\nBefore selecting any reference file, classify the user request:\n\n1. Select **Apple**:\n   - if you intend to build with: `apple`, `Apple Intelligence`, `Apple Foundation Models`\n   - if you want features: `transcription`, `speech synthesis`, `embeddings` on Apple devices\n   - optionally with capabilities: tool calling\n2. Select **Llama**:\n   - if you intend to use the following technologies: `llama`, `GGUF`, `llama.rn`, `HuggingFace`, `SmolLM`\n   - if you want to perform the following operations: `embedding model`, `rerank`, `speech model`\n3. Select **MLC**:\n   - if you intend to use a library that allows for custom models and involves build-time model optimizations\n4. Select **NCNN**:\n   - if you need to use run low-level inference on bare metal tensors\n   - if you intend to run inference of custom models such as convolutional networks, multi-layer perceptrons, low-level inference, etc.\n   - DO NOT select NCNN if the prompt mentions LLMs only, this use case is better solved by other providers\n\n## Skill Format\n\nEach reference file follows a strict execution format:\n\n- Quick Command\n- When to Use\n- Prerequisites\n- Step-by-Step Instructions\n- Common Pitfalls\n- Related Skills\n\nUse the checklists exactly as written before moving to the next phase.\n\n## When to Apply\n\nReference this package when:\n\n- Integrating on-device AI in React Native apps\n- Installing and configuring @react-native-ai providers\n- Managing model downloads (llama, mlc)\n- Wiring providers with Vercel AI SDK (generateText, streamText)\n- Implementing SetupAdapter pattern for multi-provider apps\n- Debugging native module or Expo plugin issues\n\n## Priority-Ordered Guidelines\n\n| Priority | Category                    | Impact | Start File                       |\n| -------- | --------------------------- | ------ | -------------------------------- |\n| 1        | Path selection and baseline | N\u002FA    | [quick-start][quick-start]       |\n| 2        | Apple provider              | N\u002FA    | [apple-provider][apple-provider] |\n| 3        | Llama provider              | N\u002FA    | [llama-provider][llama-provider] |\n| 4        | MLC-LLM provider            | N\u002FA    | [mlc-provider][mlc-provider]     |\n| 5        | NCNN provider               | N\u002FA    | [ncnn-provider][ncnn-provider]   |\n\n## Quick Reference\n\n```bash\nnpm install\n\n# Provider-specific install\nnpm add @react-native-ai\u002Fapple\nnpm add @react-native-ai\u002Fllama llama.rn\nnpm add @react-native-ai\u002Fmlc\nnpm add @react-native-ai\u002Fncnn-wrapper\n```\n\nRoute by path:\n\n- Apple: [apple-provider][apple-provider]\n- Llama: [llama-provider][llama-provider]\n- MLC: [mlc-provider][mlc-provider]\n- NCNN: [ncnn-provider][ncnn-provider]\n\n## References\n\n| File                             | Impact | Description                                |\n| -------------------------------- | ------ | ------------------------------------------ |\n| [quick-start][quick-start]       | N\u002FA    | Shared preflight                           |\n| [apple-provider][apple-provider] | N\u002FA    | Apple Intelligence setup and integration   |\n| [llama-provider][llama-provider] | N\u002FA    | GGUF models, llama.rn, model management    |\n| [mlc-provider][mlc-provider]     | N\u002FA    | MLC models, download, prepare, Expo plugin |\n| [ncnn-provider][ncnn-provider]   | N\u002FA    | NCNN wrapper, loadModel, runInference      |\n\n## Problem → Skill Mapping\n\n| Problem                               | Start With                                     |\n| ------------------------------------- | ---------------------------------------------- |\n| Need path decision first              | [quick-start][quick-start]                     |\n| Integrate Apple Intelligence          | [apple-provider][apple-provider]               |\n| Run GGUF models from HuggingFace      | [llama-provider][llama-provider]               |\n| Run MLC-LLM models (Llama, Phi, Qwen) | [mlc-provider][mlc-provider]                   |\n| Use NCNN for custom inference         | [ncnn-provider][ncnn-provider]                 |\n| Multi-provider app with SetupAdapter  | [quick-start][quick-start] → provider-specific |\n| Expo + native module setup            | Provider-specific (each has Expo notes)        |\n\n[quick-start]: references\u002Fquick-start.md\n[apple-provider]: references\u002Fapple-provider.md\n[llama-provider]: references\u002Fllama-provider.md\n[mlc-provider]: references\u002Fmlc-provider.md\n[ncnn-provider]: references\u002Fncnn-provider.md\n",{"data":40,"body":43},{"name":4,"description":6,"license":29,"metadata":41},{"author":9,"tags":42},"react-native, ai, llama, apple, mlc, ncnn, vercel-ai-sdk, on-device",{"type":44,"children":45},"root",[46,54,61,67,113,119,124,321,327,332,365,370,376,381,414,420,590,596,719,724,763,769,890,896,1023],{"type":47,"tag":48,"props":49,"children":50},"element","h1",{"id":4},[51],{"type":52,"value":53},"text","React Native AI Skills",{"type":47,"tag":55,"props":56,"children":58},"h2",{"id":57},"overview",[59],{"type":52,"value":60},"Overview",{"type":47,"tag":62,"props":63,"children":64},"p",{},[65],{"type":52,"value":66},"Example workflow for integrating on-device AI in React Native apps using the @react-native-ai ecosystem. Available provider tracks (can be combined):",{"type":47,"tag":68,"props":69,"children":70},"ul",{},[71,83,93,103],{"type":47,"tag":72,"props":73,"children":74},"li",{},[75,81],{"type":47,"tag":76,"props":77,"children":78},"strong",{},[79],{"type":52,"value":80},"Apple",{"type":52,"value":82}," – Apple Intelligence (iOS 26+)",{"type":47,"tag":72,"props":84,"children":85},{},[86,91],{"type":47,"tag":76,"props":87,"children":88},{},[89],{"type":52,"value":90},"Llama",{"type":52,"value":92}," – GGUF models via llama.rn",{"type":47,"tag":72,"props":94,"children":95},{},[96,101],{"type":47,"tag":76,"props":97,"children":98},{},[99],{"type":52,"value":100},"MLC",{"type":52,"value":102}," – MLC-LLM models",{"type":47,"tag":72,"props":104,"children":105},{},[106,111],{"type":47,"tag":76,"props":107,"children":108},{},[109],{"type":52,"value":110},"NCNN",{"type":52,"value":112}," – Low-level NCNN inference wrapper (vision, custom models)",{"type":47,"tag":55,"props":114,"children":116},{"id":115},"path-selection-gate-must-run-first",[117],{"type":52,"value":118},"Path Selection Gate (Must Run First)",{"type":47,"tag":62,"props":120,"children":121},{},[122],{"type":52,"value":123},"Before selecting any reference file, classify the user request:",{"type":47,"tag":125,"props":126,"children":127},"ol",{},[128,201,277,294],{"type":47,"tag":72,"props":129,"children":130},{},[131,133,137,139],{"type":52,"value":132},"Select ",{"type":47,"tag":76,"props":134,"children":135},{},[136],{"type":52,"value":80},{"type":52,"value":138},":\n",{"type":47,"tag":68,"props":140,"children":141},{},[142,169,196],{"type":47,"tag":72,"props":143,"children":144},{},[145,147,154,156,162,163],{"type":52,"value":146},"if you intend to build with: ",{"type":47,"tag":148,"props":149,"children":151},"code",{"className":150},[],[152],{"type":52,"value":153},"apple",{"type":52,"value":155},", ",{"type":47,"tag":148,"props":157,"children":159},{"className":158},[],[160],{"type":52,"value":161},"Apple Intelligence",{"type":52,"value":155},{"type":47,"tag":148,"props":164,"children":166},{"className":165},[],[167],{"type":52,"value":168},"Apple Foundation Models",{"type":47,"tag":72,"props":170,"children":171},{},[172,174,180,181,187,188,194],{"type":52,"value":173},"if you want features: ",{"type":47,"tag":148,"props":175,"children":177},{"className":176},[],[178],{"type":52,"value":179},"transcription",{"type":52,"value":155},{"type":47,"tag":148,"props":182,"children":184},{"className":183},[],[185],{"type":52,"value":186},"speech synthesis",{"type":52,"value":155},{"type":47,"tag":148,"props":189,"children":191},{"className":190},[],[192],{"type":52,"value":193},"embeddings",{"type":52,"value":195}," on Apple devices",{"type":47,"tag":72,"props":197,"children":198},{},[199],{"type":52,"value":200},"optionally with capabilities: tool calling",{"type":47,"tag":72,"props":202,"children":203},{},[204,205,209,210],{"type":52,"value":132},{"type":47,"tag":76,"props":206,"children":207},{},[208],{"type":52,"value":90},{"type":52,"value":138},{"type":47,"tag":68,"props":211,"children":212},{},[213,252],{"type":47,"tag":72,"props":214,"children":215},{},[216,218,224,225,231,232,238,239,245,246],{"type":52,"value":217},"if you intend to use the following technologies: ",{"type":47,"tag":148,"props":219,"children":221},{"className":220},[],[222],{"type":52,"value":223},"llama",{"type":52,"value":155},{"type":47,"tag":148,"props":226,"children":228},{"className":227},[],[229],{"type":52,"value":230},"GGUF",{"type":52,"value":155},{"type":47,"tag":148,"props":233,"children":235},{"className":234},[],[236],{"type":52,"value":237},"llama.rn",{"type":52,"value":155},{"type":47,"tag":148,"props":240,"children":242},{"className":241},[],[243],{"type":52,"value":244},"HuggingFace",{"type":52,"value":155},{"type":47,"tag":148,"props":247,"children":249},{"className":248},[],[250],{"type":52,"value":251},"SmolLM",{"type":47,"tag":72,"props":253,"children":254},{},[255,257,263,264,270,271],{"type":52,"value":256},"if you want to perform the following operations: ",{"type":47,"tag":148,"props":258,"children":260},{"className":259},[],[261],{"type":52,"value":262},"embedding model",{"type":52,"value":155},{"type":47,"tag":148,"props":265,"children":267},{"className":266},[],[268],{"type":52,"value":269},"rerank",{"type":52,"value":155},{"type":47,"tag":148,"props":272,"children":274},{"className":273},[],[275],{"type":52,"value":276},"speech model",{"type":47,"tag":72,"props":278,"children":279},{},[280,281,285,286],{"type":52,"value":132},{"type":47,"tag":76,"props":282,"children":283},{},[284],{"type":52,"value":100},{"type":52,"value":138},{"type":47,"tag":68,"props":287,"children":288},{},[289],{"type":47,"tag":72,"props":290,"children":291},{},[292],{"type":52,"value":293},"if you intend to use a library that allows for custom models and involves build-time model optimizations",{"type":47,"tag":72,"props":295,"children":296},{},[297,298,302,303],{"type":52,"value":132},{"type":47,"tag":76,"props":299,"children":300},{},[301],{"type":52,"value":110},{"type":52,"value":138},{"type":47,"tag":68,"props":304,"children":305},{},[306,311,316],{"type":47,"tag":72,"props":307,"children":308},{},[309],{"type":52,"value":310},"if you need to use run low-level inference on bare metal tensors",{"type":47,"tag":72,"props":312,"children":313},{},[314],{"type":52,"value":315},"if you intend to run inference of custom models such as convolutional networks, multi-layer perceptrons, low-level inference, etc.",{"type":47,"tag":72,"props":317,"children":318},{},[319],{"type":52,"value":320},"DO NOT select NCNN if the prompt mentions LLMs only, this use case is better solved by other providers",{"type":47,"tag":55,"props":322,"children":324},{"id":323},"skill-format",[325],{"type":52,"value":326},"Skill Format",{"type":47,"tag":62,"props":328,"children":329},{},[330],{"type":52,"value":331},"Each reference file follows a strict execution format:",{"type":47,"tag":68,"props":333,"children":334},{},[335,340,345,350,355,360],{"type":47,"tag":72,"props":336,"children":337},{},[338],{"type":52,"value":339},"Quick Command",{"type":47,"tag":72,"props":341,"children":342},{},[343],{"type":52,"value":344},"When to Use",{"type":47,"tag":72,"props":346,"children":347},{},[348],{"type":52,"value":349},"Prerequisites",{"type":47,"tag":72,"props":351,"children":352},{},[353],{"type":52,"value":354},"Step-by-Step Instructions",{"type":47,"tag":72,"props":356,"children":357},{},[358],{"type":52,"value":359},"Common Pitfalls",{"type":47,"tag":72,"props":361,"children":362},{},[363],{"type":52,"value":364},"Related Skills",{"type":47,"tag":62,"props":366,"children":367},{},[368],{"type":52,"value":369},"Use the checklists exactly as written before moving to the next phase.",{"type":47,"tag":55,"props":371,"children":373},{"id":372},"when-to-apply",[374],{"type":52,"value":375},"When to Apply",{"type":47,"tag":62,"props":377,"children":378},{},[379],{"type":52,"value":380},"Reference this package when:",{"type":47,"tag":68,"props":382,"children":383},{},[384,389,394,399,404,409],{"type":47,"tag":72,"props":385,"children":386},{},[387],{"type":52,"value":388},"Integrating on-device AI in React Native apps",{"type":47,"tag":72,"props":390,"children":391},{},[392],{"type":52,"value":393},"Installing and configuring @react-native-ai providers",{"type":47,"tag":72,"props":395,"children":396},{},[397],{"type":52,"value":398},"Managing model downloads (llama, mlc)",{"type":47,"tag":72,"props":400,"children":401},{},[402],{"type":52,"value":403},"Wiring providers with Vercel AI SDK (generateText, streamText)",{"type":47,"tag":72,"props":405,"children":406},{},[407],{"type":52,"value":408},"Implementing SetupAdapter pattern for multi-provider apps",{"type":47,"tag":72,"props":410,"children":411},{},[412],{"type":52,"value":413},"Debugging native module or Expo plugin issues",{"type":47,"tag":55,"props":415,"children":417},{"id":416},"priority-ordered-guidelines",[418],{"type":52,"value":419},"Priority-Ordered Guidelines",{"type":47,"tag":421,"props":422,"children":423},"table",{},[424,453],{"type":47,"tag":425,"props":426,"children":427},"thead",{},[428],{"type":47,"tag":429,"props":430,"children":431},"tr",{},[432,438,443,448],{"type":47,"tag":433,"props":434,"children":435},"th",{},[436],{"type":52,"value":437},"Priority",{"type":47,"tag":433,"props":439,"children":440},{},[441],{"type":52,"value":442},"Category",{"type":47,"tag":433,"props":444,"children":445},{},[446],{"type":52,"value":447},"Impact",{"type":47,"tag":433,"props":449,"children":450},{},[451],{"type":52,"value":452},"Start File",{"type":47,"tag":454,"props":455,"children":456},"tbody",{},[457,486,512,538,564],{"type":47,"tag":429,"props":458,"children":459},{},[460,466,471,476],{"type":47,"tag":461,"props":462,"children":463},"td",{},[464],{"type":52,"value":465},"1",{"type":47,"tag":461,"props":467,"children":468},{},[469],{"type":52,"value":470},"Path selection and baseline",{"type":47,"tag":461,"props":472,"children":473},{},[474],{"type":52,"value":475},"N\u002FA",{"type":47,"tag":461,"props":477,"children":478},{},[479],{"type":47,"tag":480,"props":481,"children":483},"a",{"href":482},"references\u002Fquick-start.md",[484],{"type":52,"value":485},"quick-start",{"type":47,"tag":429,"props":487,"children":488},{},[489,494,499,503],{"type":47,"tag":461,"props":490,"children":491},{},[492],{"type":52,"value":493},"2",{"type":47,"tag":461,"props":495,"children":496},{},[497],{"type":52,"value":498},"Apple provider",{"type":47,"tag":461,"props":500,"children":501},{},[502],{"type":52,"value":475},{"type":47,"tag":461,"props":504,"children":505},{},[506],{"type":47,"tag":480,"props":507,"children":509},{"href":508},"references\u002Fapple-provider.md",[510],{"type":52,"value":511},"apple-provider",{"type":47,"tag":429,"props":513,"children":514},{},[515,520,525,529],{"type":47,"tag":461,"props":516,"children":517},{},[518],{"type":52,"value":519},"3",{"type":47,"tag":461,"props":521,"children":522},{},[523],{"type":52,"value":524},"Llama provider",{"type":47,"tag":461,"props":526,"children":527},{},[528],{"type":52,"value":475},{"type":47,"tag":461,"props":530,"children":531},{},[532],{"type":47,"tag":480,"props":533,"children":535},{"href":534},"references\u002Fllama-provider.md",[536],{"type":52,"value":537},"llama-provider",{"type":47,"tag":429,"props":539,"children":540},{},[541,546,551,555],{"type":47,"tag":461,"props":542,"children":543},{},[544],{"type":52,"value":545},"4",{"type":47,"tag":461,"props":547,"children":548},{},[549],{"type":52,"value":550},"MLC-LLM provider",{"type":47,"tag":461,"props":552,"children":553},{},[554],{"type":52,"value":475},{"type":47,"tag":461,"props":556,"children":557},{},[558],{"type":47,"tag":480,"props":559,"children":561},{"href":560},"references\u002Fmlc-provider.md",[562],{"type":52,"value":563},"mlc-provider",{"type":47,"tag":429,"props":565,"children":566},{},[567,572,577,581],{"type":47,"tag":461,"props":568,"children":569},{},[570],{"type":52,"value":571},"5",{"type":47,"tag":461,"props":573,"children":574},{},[575],{"type":52,"value":576},"NCNN provider",{"type":47,"tag":461,"props":578,"children":579},{},[580],{"type":52,"value":475},{"type":47,"tag":461,"props":582,"children":583},{},[584],{"type":47,"tag":480,"props":585,"children":587},{"href":586},"references\u002Fncnn-provider.md",[588],{"type":52,"value":589},"ncnn-provider",{"type":47,"tag":55,"props":591,"children":593},{"id":592},"quick-reference",[594],{"type":52,"value":595},"Quick Reference",{"type":47,"tag":597,"props":598,"children":603},"pre",{"className":599,"code":600,"language":601,"meta":602,"style":602},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","npm install\n\n# Provider-specific install\nnpm add @react-native-ai\u002Fapple\nnpm add @react-native-ai\u002Fllama llama.rn\nnpm add @react-native-ai\u002Fmlc\nnpm add @react-native-ai\u002Fncnn-wrapper\n","bash","",[604],{"type":47,"tag":148,"props":605,"children":606},{"__ignoreMap":602},[607,625,635,645,663,685,702],{"type":47,"tag":608,"props":609,"children":612},"span",{"class":610,"line":611},"line",1,[613,619],{"type":47,"tag":608,"props":614,"children":616},{"style":615},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[617],{"type":52,"value":618},"npm",{"type":47,"tag":608,"props":620,"children":622},{"style":621},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[623],{"type":52,"value":624}," install\n",{"type":47,"tag":608,"props":626,"children":628},{"class":610,"line":627},2,[629],{"type":47,"tag":608,"props":630,"children":632},{"emptyLinePlaceholder":631},true,[633],{"type":52,"value":634},"\n",{"type":47,"tag":608,"props":636,"children":638},{"class":610,"line":637},3,[639],{"type":47,"tag":608,"props":640,"children":642},{"style":641},"--shiki-light:#90A4AE;--shiki-light-font-style:italic;--shiki-default:#546E7A;--shiki-default-font-style:italic;--shiki-dark:#676E95;--shiki-dark-font-style:italic",[643],{"type":52,"value":644},"# Provider-specific install\n",{"type":47,"tag":608,"props":646,"children":648},{"class":610,"line":647},4,[649,653,658],{"type":47,"tag":608,"props":650,"children":651},{"style":615},[652],{"type":52,"value":618},{"type":47,"tag":608,"props":654,"children":655},{"style":621},[656],{"type":52,"value":657}," add",{"type":47,"tag":608,"props":659,"children":660},{"style":621},[661],{"type":52,"value":662}," @react-native-ai\u002Fapple\n",{"type":47,"tag":608,"props":664,"children":666},{"class":610,"line":665},5,[667,671,675,680],{"type":47,"tag":608,"props":668,"children":669},{"style":615},[670],{"type":52,"value":618},{"type":47,"tag":608,"props":672,"children":673},{"style":621},[674],{"type":52,"value":657},{"type":47,"tag":608,"props":676,"children":677},{"style":621},[678],{"type":52,"value":679}," @react-native-ai\u002Fllama",{"type":47,"tag":608,"props":681,"children":682},{"style":621},[683],{"type":52,"value":684}," llama.rn\n",{"type":47,"tag":608,"props":686,"children":688},{"class":610,"line":687},6,[689,693,697],{"type":47,"tag":608,"props":690,"children":691},{"style":615},[692],{"type":52,"value":618},{"type":47,"tag":608,"props":694,"children":695},{"style":621},[696],{"type":52,"value":657},{"type":47,"tag":608,"props":698,"children":699},{"style":621},[700],{"type":52,"value":701}," @react-native-ai\u002Fmlc\n",{"type":47,"tag":608,"props":703,"children":705},{"class":610,"line":704},7,[706,710,714],{"type":47,"tag":608,"props":707,"children":708},{"style":615},[709],{"type":52,"value":618},{"type":47,"tag":608,"props":711,"children":712},{"style":621},[713],{"type":52,"value":657},{"type":47,"tag":608,"props":715,"children":716},{"style":621},[717],{"type":52,"value":718}," @react-native-ai\u002Fncnn-wrapper\n",{"type":47,"tag":62,"props":720,"children":721},{},[722],{"type":52,"value":723},"Route by path:",{"type":47,"tag":68,"props":725,"children":726},{},[727,736,745,754],{"type":47,"tag":72,"props":728,"children":729},{},[730,732],{"type":52,"value":731},"Apple: ",{"type":47,"tag":480,"props":733,"children":734},{"href":508},[735],{"type":52,"value":511},{"type":47,"tag":72,"props":737,"children":738},{},[739,741],{"type":52,"value":740},"Llama: ",{"type":47,"tag":480,"props":742,"children":743},{"href":534},[744],{"type":52,"value":537},{"type":47,"tag":72,"props":746,"children":747},{},[748,750],{"type":52,"value":749},"MLC: ",{"type":47,"tag":480,"props":751,"children":752},{"href":560},[753],{"type":52,"value":563},{"type":47,"tag":72,"props":755,"children":756},{},[757,759],{"type":52,"value":758},"NCNN: ",{"type":47,"tag":480,"props":760,"children":761},{"href":586},[762],{"type":52,"value":589},{"type":47,"tag":55,"props":764,"children":766},{"id":765},"references",[767],{"type":52,"value":768},"References",{"type":47,"tag":421,"props":770,"children":771},{},[772,792],{"type":47,"tag":425,"props":773,"children":774},{},[775],{"type":47,"tag":429,"props":776,"children":777},{},[778,783,787],{"type":47,"tag":433,"props":779,"children":780},{},[781],{"type":52,"value":782},"File",{"type":47,"tag":433,"props":784,"children":785},{},[786],{"type":52,"value":447},{"type":47,"tag":433,"props":788,"children":789},{},[790],{"type":52,"value":791},"Description",{"type":47,"tag":454,"props":793,"children":794},{},[795,814,833,852,871],{"type":47,"tag":429,"props":796,"children":797},{},[798,805,809],{"type":47,"tag":461,"props":799,"children":800},{},[801],{"type":47,"tag":480,"props":802,"children":803},{"href":482},[804],{"type":52,"value":485},{"type":47,"tag":461,"props":806,"children":807},{},[808],{"type":52,"value":475},{"type":47,"tag":461,"props":810,"children":811},{},[812],{"type":52,"value":813},"Shared preflight",{"type":47,"tag":429,"props":815,"children":816},{},[817,824,828],{"type":47,"tag":461,"props":818,"children":819},{},[820],{"type":47,"tag":480,"props":821,"children":822},{"href":508},[823],{"type":52,"value":511},{"type":47,"tag":461,"props":825,"children":826},{},[827],{"type":52,"value":475},{"type":47,"tag":461,"props":829,"children":830},{},[831],{"type":52,"value":832},"Apple Intelligence setup and integration",{"type":47,"tag":429,"props":834,"children":835},{},[836,843,847],{"type":47,"tag":461,"props":837,"children":838},{},[839],{"type":47,"tag":480,"props":840,"children":841},{"href":534},[842],{"type":52,"value":537},{"type":47,"tag":461,"props":844,"children":845},{},[846],{"type":52,"value":475},{"type":47,"tag":461,"props":848,"children":849},{},[850],{"type":52,"value":851},"GGUF models, llama.rn, model management",{"type":47,"tag":429,"props":853,"children":854},{},[855,862,866],{"type":47,"tag":461,"props":856,"children":857},{},[858],{"type":47,"tag":480,"props":859,"children":860},{"href":560},[861],{"type":52,"value":563},{"type":47,"tag":461,"props":863,"children":864},{},[865],{"type":52,"value":475},{"type":47,"tag":461,"props":867,"children":868},{},[869],{"type":52,"value":870},"MLC models, download, prepare, Expo plugin",{"type":47,"tag":429,"props":872,"children":873},{},[874,881,885],{"type":47,"tag":461,"props":875,"children":876},{},[877],{"type":47,"tag":480,"props":878,"children":879},{"href":586},[880],{"type":52,"value":589},{"type":47,"tag":461,"props":882,"children":883},{},[884],{"type":52,"value":475},{"type":47,"tag":461,"props":886,"children":887},{},[888],{"type":52,"value":889},"NCNN wrapper, loadModel, runInference",{"type":47,"tag":55,"props":891,"children":893},{"id":892},"problem-skill-mapping",[894],{"type":52,"value":895},"Problem → Skill Mapping",{"type":47,"tag":421,"props":897,"children":898},{},[899,915],{"type":47,"tag":425,"props":900,"children":901},{},[902],{"type":47,"tag":429,"props":903,"children":904},{},[905,910],{"type":47,"tag":433,"props":906,"children":907},{},[908],{"type":52,"value":909},"Problem",{"type":47,"tag":433,"props":911,"children":912},{},[913],{"type":52,"value":914},"Start With",{"type":47,"tag":454,"props":916,"children":917},{},[918,933,948,963,978,993,1010],{"type":47,"tag":429,"props":919,"children":920},{},[921,926],{"type":47,"tag":461,"props":922,"children":923},{},[924],{"type":52,"value":925},"Need path decision first",{"type":47,"tag":461,"props":927,"children":928},{},[929],{"type":47,"tag":480,"props":930,"children":931},{"href":482},[932],{"type":52,"value":485},{"type":47,"tag":429,"props":934,"children":935},{},[936,941],{"type":47,"tag":461,"props":937,"children":938},{},[939],{"type":52,"value":940},"Integrate Apple Intelligence",{"type":47,"tag":461,"props":942,"children":943},{},[944],{"type":47,"tag":480,"props":945,"children":946},{"href":508},[947],{"type":52,"value":511},{"type":47,"tag":429,"props":949,"children":950},{},[951,956],{"type":47,"tag":461,"props":952,"children":953},{},[954],{"type":52,"value":955},"Run GGUF models from HuggingFace",{"type":47,"tag":461,"props":957,"children":958},{},[959],{"type":47,"tag":480,"props":960,"children":961},{"href":534},[962],{"type":52,"value":537},{"type":47,"tag":429,"props":964,"children":965},{},[966,971],{"type":47,"tag":461,"props":967,"children":968},{},[969],{"type":52,"value":970},"Run MLC-LLM models (Llama, Phi, Qwen)",{"type":47,"tag":461,"props":972,"children":973},{},[974],{"type":47,"tag":480,"props":975,"children":976},{"href":560},[977],{"type":52,"value":563},{"type":47,"tag":429,"props":979,"children":980},{},[981,986],{"type":47,"tag":461,"props":982,"children":983},{},[984],{"type":52,"value":985},"Use NCNN for custom inference",{"type":47,"tag":461,"props":987,"children":988},{},[989],{"type":47,"tag":480,"props":990,"children":991},{"href":586},[992],{"type":52,"value":589},{"type":47,"tag":429,"props":994,"children":995},{},[996,1001],{"type":47,"tag":461,"props":997,"children":998},{},[999],{"type":52,"value":1000},"Multi-provider app with SetupAdapter",{"type":47,"tag":461,"props":1002,"children":1003},{},[1004,1008],{"type":47,"tag":480,"props":1005,"children":1006},{"href":482},[1007],{"type":52,"value":485},{"type":52,"value":1009}," → provider-specific",{"type":47,"tag":429,"props":1011,"children":1012},{},[1013,1018],{"type":47,"tag":461,"props":1014,"children":1015},{},[1016],{"type":52,"value":1017},"Expo + native module setup",{"type":47,"tag":461,"props":1019,"children":1020},{},[1021],{"type":52,"value":1022},"Provider-specific (each has Expo notes)",{"type":47,"tag":1024,"props":1025,"children":1026},"style",{},[1027],{"type":52,"value":1028},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1030,"total":611},[1031],{"slug":4,"name":4,"fn":5,"description":6,"org":1032,"tags":1033,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1034,1035,1036,1037],{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"items":1039,"total":1212},[1040,1060,1072,1090,1104,1116,1131,1150,1165,1177,1184,1198],{"slug":1041,"name":1041,"fn":1042,"description":1043,"org":1044,"tags":1045,"stars":1057,"repoUrl":1058,"updatedAt":1059},"assess-react-native-migration","assess mobile product React Native migration","Assesses whether and how an existing mobile product should migrate to React Native. Use when auditing one or more product repositories for migration readiness, including products whose iOS, Android, and other clients live in separate directories or repositories; choosing brownfield, greenfield, or a checkpoint-based path; defining a representative trial; or preparing a baseline and ROI decision before implementation. When product scope or material evidence is unavailable, grills the stakeholder with exactly one question per turn instead of sending a questionnaire.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1046,1049,1052,1055,1056],{"name":1047,"slug":1048,"type":16},"Android","android",{"name":1050,"slug":1051,"type":16},"iOS","ios",{"name":1053,"slug":1054,"type":16},"Migration","migration",{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},1527,"https:\u002F\u002Fgithub.com\u002Fcallstackincubator\u002Fagent-skills","2026-07-11T05:40:57.94641",{"slug":1061,"name":1061,"fn":1062,"description":1063,"org":1064,"tags":1065,"stars":1057,"repoUrl":1058,"updatedAt":1071},"create-react-native-library","scaffold React Native libraries","Scaffolds React Native libraries with create-react-native-library for standalone libraries or local native modules and views. Use when creating or working on React Native libraries or adding native functionality in an existing app.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1066,1069,1070],{"name":1067,"slug":1068,"type":16},"Engineering","engineering",{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-06-26T07:57:53.098041",{"slug":1073,"name":1073,"fn":1074,"description":1075,"org":1076,"tags":1077,"stars":1057,"repoUrl":1058,"updatedAt":1089},"github","manage GitHub PRs with gh CLI","GitHub patterns using gh CLI for pull requests, stacked PRs, code review, branching strategies, and repository automation. Use when working with GitHub PRs, merging strategies, or repository management tasks.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1078,1081,1084,1086],{"name":1079,"slug":1080,"type":16},"CLI","cli",{"name":1082,"slug":1083,"type":16},"Code Review","code-review",{"name":1085,"slug":1073,"type":16},"GitHub",{"name":1087,"slug":1088,"type":16},"Pull Requests","pull-requests","2026-04-06T18:06:37.430056",{"slug":1091,"name":1091,"fn":1092,"description":1093,"org":1094,"tags":1095,"stars":1057,"repoUrl":1058,"updatedAt":1103},"github-actions","build React Native apps in GitHub Actions","GitHub Actions workflow patterns for React Native iOS simulator and Android emulator cloud builds with downloadable artifacts. Use when setting up CI build pipelines or downloading GitHub Actions artifacts via gh CLI and GitHub API.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1096,1099,1101,1102],{"name":1097,"slug":1098,"type":16},"CI\u002FCD","cicd",{"name":1100,"slug":1091,"type":16},"GitHub Actions",{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-04-06T18:06:38.661459",{"slug":1105,"name":1105,"fn":1106,"description":1107,"org":1108,"tags":1109,"stars":1057,"repoUrl":1058,"updatedAt":1115},"react-native-best-practices","optimize React Native app performance","Provides React Native performance optimization guidelines for FPS, TTI, bundle size, memory leaks, re-renders, and animations. Applies to tasks involving Hermes optimization, JS thread blocking, bridge overhead, FlashList, native modules, or debugging jank and frame drops.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1110,1111,1114],{"name":21,"slug":22,"type":16},{"name":1112,"slug":1113,"type":16},"Performance","performance",{"name":14,"slug":15,"type":16},"2026-04-06T18:06:41.158478",{"slug":1117,"name":1117,"fn":1118,"description":1119,"org":1120,"tags":1121,"stars":1057,"repoUrl":1058,"updatedAt":1130},"react-native-brownfield-migration","migrate native apps to React Native","Implements an accepted incremental brownfield migration from native iOS or Android to React Native or Expo using @callstack\u002Freact-native-brownfield. Use after the brownfield path has been selected, when setting up the integration, packaging XCFramework or AAR artifacts, or adding React Native surfaces to native hosts.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1122,1123,1126,1127,1128,1129],{"name":1047,"slug":1048,"type":16},{"name":1124,"slug":1125,"type":16},"Expo","expo",{"name":1050,"slug":1051,"type":16},{"name":1053,"slug":1054,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-04-06T18:06:42.392689",{"slug":1132,"name":1132,"fn":1133,"description":1134,"org":1135,"tags":1136,"stars":1057,"repoUrl":1058,"updatedAt":1149},"react-native-tv-best-practices","review React Native TV application quality","Reviews React Native TV apps for focus\u002FD-pad navigation, 10-foot UI layout, TV playback\u002FDRM integration, low-memory TV performance, and TV accessibility. Use when building, debugging, or reviewing react-native-tvos, Expo TV, Amazon Vega\u002FKepler, or React Native web TV targets where the issue depends on remote input, TV focus, TV packaging, TV hardware, or TV playback constraints.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1137,1140,1143,1144,1145,1146],{"name":1138,"slug":1139,"type":16},"Accessibility","accessibility",{"name":1141,"slug":1142,"type":16},"Frontend","frontend",{"name":21,"slug":22,"type":16},{"name":1112,"slug":1113,"type":16},{"name":14,"slug":15,"type":16},{"name":1147,"slug":1148,"type":16},"UI Components","ui-components","2026-06-28T08:04:16.29881",{"slug":1151,"name":1151,"fn":1152,"description":1153,"org":1154,"tags":1155,"stars":1057,"repoUrl":1058,"updatedAt":1164},"react-navigation","configure React Navigation UI patterns","Provides React Navigation UI patterns for stacks, tabs, drawers etc. Use when building navigation UIs with React Navigation, configuring headers, bottom sheets or handling safe areas and insets.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1156,1157,1158,1161],{"name":1141,"slug":1142,"type":16},{"name":21,"slug":22,"type":16},{"name":1159,"slug":1160,"type":16},"Navigation","navigation",{"name":1162,"slug":1163,"type":16},"React","react","2026-06-26T07:57:54.478042",{"slug":1166,"name":1166,"fn":1167,"description":1168,"org":1169,"tags":1170,"stars":1057,"repoUrl":1058,"updatedAt":1176},"upgrading-react-native","upgrade React Native apps","Upgrades React Native apps to newer versions by applying rn-diff-purge template diffs, updating package.json dependencies, migrating native iOS and Android configuration, resolving CocoaPods and Gradle changes, and handling breaking API updates. Use when upgrading React Native, bumping RN version, updating from RN 0.x to 0.y, or migrating Expo SDK alongside a React Native upgrade.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1171,1172,1173,1174,1175],{"name":1047,"slug":1048,"type":16},{"name":1050,"slug":1051,"type":16},{"name":1053,"slug":1054,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},"2026-04-06T18:06:39.914409",{"slug":4,"name":4,"fn":5,"description":6,"org":1178,"tags":1179,"stars":26,"repoUrl":27,"updatedAt":28},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1180,1181,1182,1183],{"name":24,"slug":25,"type":16},{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"slug":1185,"name":1185,"fn":1186,"description":1187,"org":1188,"tags":1189,"stars":1195,"repoUrl":1196,"updatedAt":1197},"voltra","build Voltra iOS widgets and charts","Build, review, refactor, configure, or debug Voltra code using Voltra JSX, Voltra JS APIs, the Expo config plugin, and the Voltra CLI. Use when the user asks about charts, Live Activities, Dynamic Island UI, iOS widgets, scheduled widgets, Android widgets, ongoing notifications, image handling, app.json plugin config, React Native CLI setup, or Voltra push update flows.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1190,1191,1192,1193],{"name":1124,"slug":1125,"type":16},{"name":1050,"slug":1051,"type":16},{"name":21,"slug":22,"type":16},{"name":1194,"slug":1185,"type":16},"Voltra",787,"https:\u002F\u002Fgithub.com\u002Fcallstackincubator\u002Fvoltra","2026-04-06T18:06:47.399012",{"slug":1199,"name":1199,"fn":1200,"description":1201,"org":1202,"tags":1203,"stars":1209,"repoUrl":1210,"updatedAt":1211},"rozenite-agent","use Rozenite plugins for React Native devtools","Use Rozenite for Agents through CLI-driven `rozenite agent` commands to inspect React Native DevTools data and Rozenite plugins on a live app target. Trigger this skill for shell-based debugging and live session work. For Node.js or TypeScript scripts, wrappers, automations, or other programmatic SDK usage, use `rozenite-agent-sdk` instead.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1204,1205,1208],{"name":21,"slug":22,"type":16},{"name":1206,"slug":1207,"type":16},"Plugin Development","plugin-development",{"name":14,"slug":15,"type":16},633,"https:\u002F\u002Fgithub.com\u002Fcallstackincubator\u002Frozenite","2026-07-31T05:52:54.56302",15]