added github link of app

README.md

@@ -20,9 +20,10 @@ tags:
 
 **Build Small Hackathon — Backyard AI.**
 
-Turn everyday phone requests into structured Android automation skills. A fine-tuned **Qwen2.5-3B-Instruct** model (≤4B params) classifies natural language into one of 15 skills — alarms, Spotify, WhatsApp, Slack, Uber, and more — then loads the matching **UI automation trajectory** recorded on a real Android device.
+Turn everyday phone requests into structured Android automation skills. A fine-tuned **Qwen2.5-3B-Instruct** model (≤4B params) classifies natural language into one of 15 skills — alarms, Spotify, WhatsApp, Slack, Uber, and more — then loads the matching **UI automation trajectory** recorded on a real Android device. Classifier demo for the **[Pocket Automator](https://github.com/kriyanshii/pocket-automator)** stack.
 
 - **Demo video:** [YouTube Short](https://youtube.com/shorts/IQRHf7HfTDA?si=9kEoZKRus6FzHYbB)
+- **Android recorder:** [Pocket Automator](https://github.com/kriyanshii/pocket-automator)
 - **Social post:** _add your post link here_
 - **Space:** [android-skill-router](https://huggingface.co/spaces/build-small-hackathon/android-skill-router)
 
@@ -36,6 +37,10 @@ Voice assistants route to cloud APIs. This project shows a **small, local-first
 
 Each trajectory is a step-by-step UI tree capture (app package, taps, screens) ready for an accessibility or agent runtime.
 
+## Recording trajectories
+
+UI traces in `trajectories/` were captured with **[Pocket Automator](https://github.com/kriyanshii/pocket-automator)** — an Android accessibility recorder that exports JSON for training and replay. Record a flow on device → export → map to a skill via `scripts/generate_skill_dataset.py`.
+
 ## Tech stack
 
 | Piece | What |
@@ -44,6 +49,7 @@ Each trajectory is a step-by-step UI tree capture (app package, taps, screens) r
 | **Fine-tune** | 4-bit QLoRA + SFT with [Unsloth](https://github.com/unslothai/unsloth) on Modal (`modal_apps/train_modal.py`) |
 | **Inference** | Modal GPU API (`modal_apps/predict_api.py`) — keeps the Gradio Space lightweight |
 | **Demo UI** | Gradio (`app.py`) |
+| **Recorder** | [Pocket Automator](https://github.com/kriyanshii/pocket-automator) — Android accessibility capture & replay |
 | **Data** | 15 Android trajectories → `data/skills.jsonl` → ~510 prompt variations in `data/train.jsonl` |
 
 ## Hackathon entry
@@ -102,7 +108,7 @@ scripts/
   generate_skill_dataset.py
   generate_training_data.py
   train.py                  # Local GPU training (optional)
-trajectories/               # Recorded Android UI automation traces
+trajectories/               # Pocket Automator exports (Android UI automation traces)
 trained_model/              # Local model weights (gitignored)
 ```