chore: update skills pre 0.8 update (#1010)

## Description

Updates skills to match the current state of the code. 

### Introduces a breaking change?

- [ ] Yes
- [ ] No

### Type of change

- [ ] Bug fix (change which fixes an issue)
- [ ] New feature (change which adds functionality)
- [ ] Documentation update (improves or adds clarity to existing
documentation)
- [x] Other (chores, tests, code style improvements etc.)

### Tested on

- [ ] iOS
- [ ] Android

### Testing instructions

<!-- Provide step-by-step instructions on how to test your changes.
Include setup details if necessary. -->

### Screenshots

<!-- Add screenshots here, if applicable -->

### Related issues

<!-- Link related issues here using #issue-number -->

### Checklist

- [ ] I have performed a self-review of my code
- [ ] I have commented my code, particularly in hard-to-understand areas
- [ ] I have updated the documentation accordingly
- [ ] My changes generate no new warnings

### Additional notes

<!-- Include any additional information, assumptions, or context that
reviewers might need to understand this PR. -->

Author: chmjkb

.cspell-wordlist.txt

@@ -181,3 +181,5 @@ nˈɛvəɹ
 ˈɛls
 Synchronizable
 stringifying
+hɛloʊ
+wɜːld

skills/canary/react-native-executorch/references/core-utilities.md

@@ -88,15 +88,33 @@ const runInference = async () => {
 
 **Use cases:** Download management, storage cleanup, progress tracking, offline-first apps.
 
+## Built-in adapters vs custom adapter
+
+React Native ExecuTorch does not bundle a resource fetcher — you bring your own. Two ready-made adapters are provided:
+
+- **`ExpoResourceFetcher`** from `react-native-executorch-expo-resource-fetcher` — for Expo projects
+- **`BareResourceFetcher`** from `react-native-executorch-bare-resource-fetcher` — for bare React Native projects
+
+Register the adapter once at app startup before using any hooks or modules:
+
+```typescript
+import { initExecutorch } from 'react-native-executorch';
+import { ExpoResourceFetcher } from 'react-native-executorch-expo-resource-fetcher';
+
+initExecutorch({ resourceFetcher: ExpoResourceFetcher });
+```
+
+If neither adapter fits your needs (custom download library, private server, custom caching), you can implement the `ResourceFetcherAdapter` interface yourself. See [Custom Adapter](https://docs.swmansion.com/react-native-executorch/docs/resource-fetcher/custom-adapter) for details.
+
 ## Basic Usage
 
 ```typescript
-import { ResourceFetcher } from 'react-native-executorch';
+import { ExpoResourceFetcher } from 'react-native-executorch-expo-resource-fetcher';
 
 // Download multiple resources with progress tracking
 const downloadModels = async () => {
   try {
-    const uris = await ResourceFetcher.fetch(
+    const uris = await ExpoResourceFetcher.fetch(
       (progress) =>
         console.log(`Download progress: ${(progress * 100).toFixed(1)}%`),
       'https://example.com/llama3_2.pte',
@@ -117,22 +135,22 @@ const downloadModels = async () => {
 ## Pause and Resume Downloads
 
 ```typescript
-import { ResourceFetcher } from 'react-native-executorch';
+import { ExpoResourceFetcher } from 'react-native-executorch-expo-resource-fetcher';
 
-const uris = ResourceFetcher.fetch(
+const uris = ExpoResourceFetcher.fetch(
   (progress) => console.log('Total progress:', progress),
   'https://.../llama3_2.pte',
   'https://.../qwen3.pte'
 ).then((uris) => {
-  console.log('URI resolved as: ', uris); // since we pause the fetch, uris is resolved to null
+  console.log('URI resolved as: ', uris); // null, since we paused
 });
 
-await ResourceFetcher.pauseFetching(
+await ExpoResourceFetcher.pauseFetching(
   'https://.../llama3_2.pte',
   'https://.../qwen3.pte'
 );
 
-const resolvedUris = await ResourceFetcher.resumeFetching(
+const resolvedUris = await ExpoResourceFetcher.resumeFetching(
   'https://.../llama3_2.pte',
   'https://.../qwen3.pte'
 );
@@ -141,17 +159,17 @@ const resolvedUris = await ResourceFetcher.resumeFetching(
 ## Cancel Downloads
 
 ```typescript
-import { ResourceFetcher } from 'react-native-executorch';
+import { ExpoResourceFetcher } from 'react-native-executorch-expo-resource-fetcher';
 
-const uris = ResourceFetcher.fetch(
+const uris = ExpoResourceFetcher.fetch(
   (progress) => console.log('Total progress:', progress),
   'https://.../llama3_2.pte',
   'https://.../qwen3.pte'
 ).then((uris) => {
-  console.log('URI resolved as: ', uris); // since we cancel the fetch, uris is resolved to null
+  console.log('URI resolved as: ', uris); // null, since we cancelled
 });
 
-await ResourceFetcher.cancelFetching(
+await ExpoResourceFetcher.cancelFetching(
   'https://.../llama3_2.pte',
   'https://.../qwen3.pte'
 );
@@ -160,22 +178,22 @@ await ResourceFetcher.cancelFetching(
 ## Manage Downloaded Resources
 
 ```typescript
-import { ResourceFetcher } from 'react-native-executorch';
+import { ExpoResourceFetcher } from 'react-native-executorch-expo-resource-fetcher';
 
 // List all downloaded files
 const listFiles = async () => {
-  const files = await ResourceFetcher.listDownloadedFiles();
+  const files = await ExpoResourceFetcher.listDownloadedFiles();
   console.log('All downloaded files:', files);
 
-  const models = await ResourceFetcher.listDownloadedModels();
+  const models = await ExpoResourceFetcher.listDownloadedModels();
   console.log('Model files:', models);
 };
 
 // Clean up old resources
 const cleanup = async () => {
-  const oldModelUrl = 'https://example.com/old_model.pte';
-
-  await ResourceFetcher.deleteResources(oldModelUrl);
+  await ExpoResourceFetcher.deleteResources(
+    'https://example.com/old_model.pte'
+  );
   console.log('Old model deleted');
 };
 ```
@@ -195,11 +213,12 @@ Resources can be:
 **Progress callback:** Progress is reported as 0-1 for all downloads combined.
 **Null return:** If `fetch()` returns `null`, download was paused or cancelled.
 **Network errors:** Implement retry logic with exponential backoff for reliability.
-**Storage location:** Downloaded files are stored in application's document directory under `react-native-executorch/`
+**Pause/resume on Android:** `BareResourceFetcher` does not support pause/resume on Android. Use `ExpoResourceFetcher` if you need this on Android.
 
 ## Additional references
 
-- [ResourceFetcher full reference docs](https://docs.swmansion.com/react-native-executorch/docs/utilities/resource-fetcher)
+- [ResourceFetcher usage docs](https://docs.swmansion.com/react-native-executorch/docs/resource-fetcher/usage)
+- [Custom Adapter docs](https://docs.swmansion.com/react-native-executorch/docs/resource-fetcher/custom-adapter)
 - [Loading Models guide](https://docs.swmansion.com/react-native-executorch/docs/fundamentals/loading-models)
 
 ---
@@ -220,13 +239,13 @@ import {
   RnExecutorchErrorCode,
 } from 'react-native-executorch';
 
-const llm = new LLMModule({
-  tokenCallback: (token) => console.log(token),
-  messageHistoryCallback: (messages) => console.log(messages),
-});
-
 try {
-  await llm.load(LLAMA3_2_1B_QLORA, (progress) => console.log(progress));
+  const llm = await LLMModule.fromModelName(
+    LLAMA3_2_1B_QLORA,
+    (progress) => console.log(progress),
+    (token) => console.log(token),
+    (messages) => console.log(messages)
+  );
   await llm.sendMessage('Hello!');
 } catch (err) {
   if (err instanceof RnExecutorchError) {
@@ -242,21 +261,27 @@ try {
 
 ```typescript
 import {
+  LLMModule,
+  LLAMA3_2_1B_QLORA,
   RnExecutorchError,
   RnExecutorchErrorCode,
 } from 'react-native-executorch';
 
-const handleModelError = async (llm, message: string) => {
+const llm = await LLMModule.fromModelName(
+  LLAMA3_2_1B_QLORA,
+  (progress) => console.log(progress),
+  (token) => console.log(token),
+  (messages) => console.log(messages)
+);
+
+const handleModelError = async (message: string) => {
   try {
     await llm.sendMessage(message);
   } catch (err) {
     if (err instanceof RnExecutorchError) {
       switch (err.code) {
         case RnExecutorchErrorCode.ModuleNotLoaded:
-          console.error('Model not loaded. Loading now...');
-          await llm.load(LLAMA3_2_1B_QLORA);
-          // Retry the message
-          await llm.sendMessage(message);
+          console.error('Model not loaded.');
           break;
 
         case RnExecutorchErrorCode.ModelGenerating:
@@ -267,7 +292,9 @@ const handleModelError = async (llm, message: string) => {
         case RnExecutorchErrorCode.InvalidConfig:
           console.error('Invalid configuration:', err.message);
           // Reset to default config
-          await llm.configure({ topp: 0.9, temperature: 0.7 });
+          await llm.configure({
+            generationConfig: { topp: 0.9, temperature: 0.7 },
+          });
           break;
 
         default:

skills/canary/react-native-executorch/references/reference-audio.md

@@ -225,8 +225,7 @@ const model = useTextToSpeech({
 const audioContext = new AudioContext({ sampleRate: 24000 });
 
 const handleSpeech = async (text: string) => {
-  const speed = 1.0;
-  const waveform = await model.forward(text, speed);
+  const waveform = await model.forward({ text, speed: 1.0 });
 
   const audioBuffer = audioContext.createBuffer(1, waveform.length, 24000);
   audioBuffer.getChannelData(0).set(waveform);
@@ -242,21 +241,43 @@ const handleSpeech = async (text: string) => {
 
 ```typescript
 // Stream chunks for lower latency
-await tts.stream({
+await model.stream({
   text: 'Long text to be streamed chunk by chunk...',
   speed: 1.0,
+  onBegin: async () => console.log('Streaming started'),
   onNext: async (chunk) => {
     return new Promise((resolve) => {
-      const buffer = ctx.createBuffer(1, chunk.length, 24000);
+      const buffer = audioContext.createBuffer(1, chunk.length, 24000);
       buffer.getChannelData(0).set(chunk);
 
-      const source = ctx.createBufferSource();
+      const source = audioContext.createBufferSource();
       source.buffer = buffer;
-      source.connect(ctx.destination);
+      source.connect(audioContext.destination);
       source.onEnded = () => resolve();
       source.start();
     });
   },
+  onEnd: async () => console.log('Streaming finished'),
+  stopAutomatically: true,
+});
+```
+
+## Phoneme-based synthesis
+
+If you have pre-computed phonemes, use `forwardFromPhonemes` or `streamFromPhonemes` to skip the text-to-phoneme step:
+
+```typescript
+const waveform = await model.forwardFromPhonemes({
+  phonemes: 'hɛloʊ',
+  speed: 1.0,
+});
+
+await model.streamFromPhonemes({
+  phonemes: 'hɛloʊ wɜːld',
+  speed: 1.0,
+  onNext: async (chunk) => {
+    /* play chunk */
+  },
 });
 ```
 
@@ -268,17 +289,14 @@ For all available models check out [this exported HuggingFace models collection]
 
 **Available Voices:**
 
-- `KOKORO_VOICE_AF_HEART` - Female, heart
-- `KOKORO_VOICE_AF_SKY` - Female, sky
-- `KOKORO_VOICE_AF_BELLA` - Female, bella
-- `KOKORO_VOICE_AF_NICOLE` - Female, nicole
-- `KOKORO_VOICE_AF_SARAH` - Female, sarah
-- `KOKORO_VOICE_AM_ADAM` - Male, adam
-- `KOKORO_VOICE_AM_MICHAEL` - Male, michael
+- `KOKORO_VOICE_AF_HEART` - American Female, heart
+- `KOKORO_VOICE_AF_RIVER` - American Female, river
+- `KOKORO_VOICE_AF_SARAH` - American Female, sarah
+- `KOKORO_VOICE_AM_ADAM` - American Male, adam
+- `KOKORO_VOICE_AM_MICHAEL` - American Male, michael
+- `KOKORO_VOICE_AM_SANTA` - American Male, santa
 - `KOKORO_VOICE_BF_EMMA` - British Female, emma
-- `KOKORO_VOICE_BF_ISABELLA` - British Female, isabella
-- `KOKORO_VOICE_BM_GEORGE` - British Male, george
-- `KOKORO_VOICE_BM_LEWIS` - British Male, lewis
+- `KOKORO_VOICE_BM_DANIEL` - British Male, daniel
 
 ## Troubleshooting
 

skills/canary/react-native-executorch/references/reference-cv-2.md

@@ -22,7 +22,11 @@ const model = useStyleTransfer({ model: STYLE_TRANSFER_CANDY });
 const imageUri = 'file:///Users/.../photo.png';
 
 try {
-  const generatedImageUrl = await model.forward(imageUri);
+  // Returns PixelData (raw RGB buffer) by default
+  const pixelData = await model.forward(imageUri);
+
+  // Pass 'url' as second argument to get a file URI instead
+  const generatedImageUrl = await model.forward(imageUri, 'url');
   console.log('Styled image:', generatedImageUrl);
 } catch (error) {
   console.error(error);
@@ -33,10 +37,10 @@ try {
 
 **Model constants:**
 
-- `STYLE_TRANSFER_CANDY` - Candy artistic style
-- `STYLE_TRANSFER_MOSAIC` - Mosaic artistic style
-- `STYLE_TRANSFER_UDNIE` - Udnie artistic style
-- `STYLE_TRANSFER_RAIN_PRINCESS` - Rain princess artistic style
+- `STYLE_TRANSFER_CANDY` / `STYLE_TRANSFER_CANDY_QUANTIZED`
+- `STYLE_TRANSFER_MOSAIC` / `STYLE_TRANSFER_MOSAIC_QUANTIZED`
+- `STYLE_TRANSFER_UDNIE` / `STYLE_TRANSFER_UDNIE_QUANTIZED`
+- `STYLE_TRANSFER_RAIN_PRINCESS` / `STYLE_TRANSFER_RAIN_PRINCESS_QUANTIZED`
 
 For the latest available models reference exported models in [HuggingFace Style Transfer collection](https://huggingface.co/collections/software-mansion/style-transfer)
 
@@ -101,7 +105,7 @@ function App() {
 }
 ```
 
-**Model constants:** `BK_SDM_TINY_VPRED_256`
+**Model constants:** `BK_SDM_TINY_VPRED_256`, `BK_SDM_TINY_VPRED_512`
 
 For the latest available models reference exported models in [HuggingFace Text to Image collection](https://huggingface.co/collections/software-mansion/text-to-image)
 
@@ -173,7 +177,7 @@ try {
 
 ## Available Models
 
-**Model constants:** `CLIP_VIT_BASE_PATCH32_IMAGE`
+**Model constants:** `CLIP_VIT_BASE_PATCH32_IMAGE`, `CLIP_VIT_BASE_PATCH32_IMAGE_QUANTIZED`
 
 For the latest available models reference exported models in [HuggingFace Image Embeddings collection](https://huggingface.co/collections/software-mansion/image-embeddings)