[AI-297] Expand docs for standardise plugin generation (#221)

* Add section for standard README format

* Update OpenRouter plugin description

Author: Nash0x7E2

docs/ai/instructions/ai-plugin.md

@@ -70,3 +70,40 @@ members = [
 ## PCM / Audio management
 
 Use `PcmData` and other utils available from the `getstream.video.rtc.track_util` module. Do not write code that directly manipulates PCM, use the audio utilities instead.
+
+## Plugin README.MD Format
+The README.md of the plugin should contain a standardise format which includes an intro briefly describing the functionality of the plugin and what it allows developers to build when paired with Vision Agents. See example below: 
+```md 
+# Plugin Name 
+ "Name of plugin"
+
+## Features 
+- Few bullet points calling attention to the main functionality of the plugins
+
+## Installation 
+Installation instructions in the format of a command using uv add. As an example:
+```
+    uv add vision-agents[PLUGIN-NAME]
+```
+
+## Usage
+Basic code snippet showing the usage in code. Example: 
+```python
+from vision_agents.plugins import ultralytics # Plugin import 
+
+# Create a YOLO pose processor
+processor = ultralytics.YOLOPoseProcessor(
+    model_path="yolo11n-pose.pt",
+    conf_threshold=0.5,
+    device="cpu",
+    enable_hand_tracking=True,
+    enable_wrist_highlights=True
+)
+```
+
+## Configuration
+Parameters developers can specify to adjust the plugin behaviour. This should be shown as a table with the parameter name, a short description derived from the code docs and the accepted values (either data type or default value)
+
+## Dependencies
+Bullet point list of dependencies the plugin requires to work correctly
+```

plugins/openrouter/README.md

@@ -1,33 +1,50 @@
 # OpenRouter Plugin
 
-OpenRouter plugin for vision agents. This plugin provides LLM capabilities using OpenRouter's API, which is compatible with the OpenAI API format.
+This plugin provides LLM capabilities using OpenRouter's API, which offers access to multiple LLM providers through a unified OpenAI-compatible interface. It enables developers to easily switch between different models from various providers (Anthropic, Google, OpenAI, etc.) without changing their code.
 
-## Note/ Issues
+## Features
 
-Instruction following doesn't always work with openrouter atm.
+- Access to multiple LLM providers through a single API
+- OpenAI-compatible interface for easy integration
+- Support for various models including Claude, Gemini, GPT, and more
+- Automatic conversion of instructions to system messages
+- Manual conversation history management
 
 ## Installation
 
 ```bash
-uv pip install vision-agents-plugins-openrouter
+uv add vision-agents[openrouter]
 ```
 
 ## Usage
 
 ```python
-from vision_agents.plugins import openrouter, getstream, elevenlabs, cartesia, deepgram, smart_turn
+from vision_agents.core import User, Agent
+from vision_agents.plugins import openrouter, getstream, elevenlabs, deepgram, smart_turn
 
 agent = Agent(
     edge=getstream.Edge(),
     agent_user=User(name="OpenRouter AI"),
     instructions="Be helpful and friendly to the user",
     llm=openrouter.LLM(
-        model="anthropic/claude-haiku-4.5",  # Can also use other models like anthropic/claude-3-opus
+        model="anthropic/claude-haiku-4.5",
     ),
     tts=elevenlabs.TTS(),
     stt=deepgram.STT(),
-    turn_detection=smart_turn.TurnDetection(
-        buffer_in_seconds=2.0, confidence_threshold=0.5
-    )
+    turn_detection=smart_turn.TurnDetection(),
 )
 ```
+
+## Configuration
+
+| Parameter | Description | Accepted Values |
+|-----------|-------------|----------------|
+| `api_key` | OpenRouter API key | `str \| None`. If not provided, uses `OPENROUTER_API_KEY` environment variable |
+| `base_url` | OpenRouter API base URL | `str`. Default: `"https://openrouter.ai/api/v1"` |
+| `model` | Model identifier to use | `str`. Default: `"openrouter/andromeda-alpha"`. Examples: `"anthropic/claude-haiku-4.5"`, `"google/gemini-2.5-flash"`, `"openai/gpt-4o"` |
+| `**kwargs` | Additional arguments passed to OpenAI LLM | Any additional parameters supported by the underlying OpenAI LLM implementation |
+
+## Dependencies
+
+- vision-agents
+- vision-agents-plugins-openai