Add downloadable image extraction skill

.agents/skills/extract-image-data/SKILL.md

@@ -0,0 +1,261 @@
+---
+name: extract-image-data
+description: Extract structured data from document images through the electblake/image-data-extractor Gradio Space API. Use when calling its template selection, template generation, or image extraction endpoints from Python, JavaScript, or cURL.
+---
+
+# Extract Image Data (API)
+
+This skill describes how to use the electblake/image-data-extractor Gradio Space programmatically.
+
+## API Endpoints
+
+### `/select_structured_json_template`
+
+**Parameters:**
+
+- `key` [Dropdown]: `Literal['Basic receipt', 'Advanced receipt', 'Basic bank statement', 'Advanced bank statement', 'Invoice with line items', 'Advanced global record']`, default: `Invoice with line items`
+
+**Returns:**
+
+- `Structured JSON template` [Textbox]: `str`
+
+**Python:**
+
+```python
+from gradio_client import Client
+
+client = Client("electblake/image-data-extractor")
+result = client.predict(
+	key="Invoice with line items",
+	api_name="/select_structured_json_template",
+)
+print(result)
+```
+
+**JavaScript:**
+
+```javascript
+import { Client } from "@gradio/client";
+
+const client = await Client.connect("electblake/image-data-extractor");
+const result = await client.predict("/select_structured_json_template", {
+		key: "Invoice with line items",
+});
+
+console.log(result.data);
+```
+
+**cURL:**
+
+```bash
+curl -X POST https://electblake-image-data-extractor.hf.space/call/v2/select_structured_json_template -s -H "Content-Type: application/json" \
+  -d '{"key": "Invoice with line items"}' \
+  | awk -F'"' '{ print $4}' \
+  | read EVENT_ID; curl -N https://electblake-image-data-extractor.hf.space/call/select_structured_json_template/$EVENT_ID
+```
+
+### `/generate_template`
+
+**Parameters:**
+
+- `image` [Image]: `filepath` (required)
+
+**Returns:**
+
+- `Structured JSON template` [Textbox]: `str`
+
+**Python:**
+
+```python
+from gradio_client import Client, handle_file
+
+client = Client("electblake/image-data-extractor")
+result = client.predict(
+	image=handle_file('https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png'),
+	api_name="/generate_template",
+)
+print(result)
+```
+
+**JavaScript:**
+
+```javascript
+import { Client } from "@gradio/client";
+
+const response_0 = await fetch("https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png");
+const exampleImage = await response_0.blob();
+
+const client = await Client.connect("electblake/image-data-extractor");
+const result = await client.predict("/generate_template", {
+		image: exampleImage,
+});
+
+console.log(result.data);
+```
+
+**cURL:**
+
+```bash
+FILE_PATH=$(curl -s -X POST https://electblake-image-data-extractor.hf.space/upload -F 'files=@/path/to/your/file' | tr -d '[]" ')
+
+curl -X POST https://electblake-image-data-extractor.hf.space/call/v2/generate_template -s -H "Content-Type: application/json" \
+  -d '{"image": {"path": "'$FILE_PATH'", "meta": {"_type": "gradio.FileData"}}}' \
+  | awk -F'"' '{ print $4}' \
+  | read EVENT_ID; curl -N https://electblake-image-data-extractor.hf.space/call/generate_template/$EVENT_ID
+```
+
+### `/extract`
+
+**Parameters:**
+
+- `image` [Image]: `filepath` (required)
+- `text` [Textbox]: `str` (required)
+- `template` [Textbox]: `str`, default: `{
+  "document_type": "verbatim-string",
+  "vendor": {
+    "name": "verbatim-string",
+    "address": "verbatim-string",
+    "email": "email-address",
+    "phone": "phone-number"
+  },
+  "invoice_number": "verbatim-string",
+  "invoice_date": "verbatim-string",
+  "line_items": [
+    {
+      "description": "verbatim-string",
+      "category": ["product", "service", "shipping", "tax", "other"],
+      "quantity": "integer",
+      "unit_price": "number",
+      "unit": "unit-code",
+      "amount": "number"
+    }
+  ],
+  "subtotal": "number",
+  "tax": "number",
+  "total": "number",
+  "currency": "currency"
+}`
+- `enable_thinking` [Checkbox]: `bool`, default: `False`
+
+**Returns:**
+
+- `Structured JSON` [Json]: `str | float | bool | list | dict`
+
+**Python:**
+
+```python
+from gradio_client import Client, handle_file
+
+client = Client("electblake/image-data-extractor")
+result = client.predict(
+	image=handle_file('https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png'),
+	text="Hello!!",
+	template="{
+  "document_type": "verbatim-string",
+  "vendor": {
+    "name": "verbatim-string",
+    "address": "verbatim-string",
+    "email": "email-address",
+    "phone": "phone-number"
+  },
+  "invoice_number": "verbatim-string",
+  "invoice_date": "verbatim-string",
+  "line_items": [
+    {
+      "description": "verbatim-string",
+      "category": ["product", "service", "shipping", "tax", "other"],
+      "quantity": "integer",
+      "unit_price": "number",
+      "unit": "unit-code",
+      "amount": "number"
+    }
+  ],
+  "subtotal": "number",
+  "tax": "number",
+  "total": "number",
+  "currency": "currency"
+}",
+	enable_thinking=False,
+	api_name="/extract",
+)
+print(result)
+```
+
+**JavaScript:**
+
+```javascript
+import { Client } from "@gradio/client";
+
+const response_0 = await fetch("https://raw.githubusercontent.com/gradio-app/gradio/main/test/test_files/bus.png");
+const exampleImage = await response_0.blob();
+
+const client = await Client.connect("electblake/image-data-extractor");
+const result = await client.predict("/extract", {
+		image: exampleImage,
+		text: "Hello!!",
+		template: "{
+  "document_type": "verbatim-string",
+  "vendor": {
+    "name": "verbatim-string",
+    "address": "verbatim-string",
+    "email": "email-address",
+    "phone": "phone-number"
+  },
+  "invoice_number": "verbatim-string",
+  "invoice_date": "verbatim-string",
+  "line_items": [
+    {
+      "description": "verbatim-string",
+      "category": ["product", "service", "shipping", "tax", "other"],
+      "quantity": "integer",
+      "unit_price": "number",
+      "unit": "unit-code",
+      "amount": "number"
+    }
+  ],
+  "subtotal": "number",
+  "tax": "number",
+  "total": "number",
+  "currency": "currency"
+}",
+		enable_thinking: false,
+});
+
+console.log(result.data);
+```
+
+**cURL:**
+
+```bash
+FILE_PATH=$(curl -s -X POST https://electblake-image-data-extractor.hf.space/upload -F 'files=@/path/to/your/file' | tr -d '[]" ')
+
+curl -X POST https://electblake-image-data-extractor.hf.space/call/v2/extract -s -H "Content-Type: application/json" \
+  -d '{"image": {"path": "'$FILE_PATH'", "meta": {"_type": "gradio.FileData"}}, "text": "Hello!!", "template": "{
+  "document_type": "verbatim-string",
+  "vendor": {
+    "name": "verbatim-string",
+    "address": "verbatim-string",
+    "email": "email-address",
+    "phone": "phone-number"
+  },
+  "invoice_number": "verbatim-string",
+  "invoice_date": "verbatim-string",
+  "line_items": [
+    {
+      "description": "verbatim-string",
+      "category": ["product", "service", "shipping", "tax", "other"],
+      "quantity": "integer",
+      "unit_price": "number",
+      "unit": "unit-code",
+      "amount": "number"
+    }
+  ],
+  "subtotal": "number",
+  "tax": "number",
+  "total": "number",
+  "currency": "currency"
+}", "enable_thinking": false}' \
+  | awk -F'"' '{ print $4}' \
+  | read EVENT_ID; curl -N https://electblake-image-data-extractor.hf.space/call/extract/$EVENT_ID
+```
+

.agents/skills/extract-image-data/agents/openai.yaml

@@ -0,0 +1,4 @@
+interface:
+  display_name: "Extract Image Data (API)"
+  short_description: "Extract structured data from document images"
+  default_prompt: "Use $extract-image-data to extract structured data from a document image through the API."