Expanso Text Summarize

# text-summarize

Summarize text into 3-5 bullet points using AI

## Requirements

- Expanso Edge installed (`expanso-edge` binary in PATH)
- Install via: `clawhub install expanso-edge`

## Usage

### CLI Pipeline
```bash
# Run standalone
echo '<input>' | expanso-edge run pipeline-cli.yaml
```

### MCP Pipeline
```bash
# Start as MCP server
expanso-edge run pipeline-mcp.yaml
```

### Deploy to Expanso Cloud
```bash
expanso-cli job deploy https://skills.expanso.io/text-summarize/pipeline-cli.yaml
```

## Files

| File | Purpose |
|------|---------|
| `skill.yaml` | Skill metadata (inputs, outputs, credentials) |
| `pipeline-cli.yaml` | Standalone CLI pipeline |
| `pipeline-mcp.yaml` | MCP server pipeline |

# text-summarize

> Summarize any text into 3-5 bullet points while keeping your API keys local.

This is the "Hello World" of Expanso + OpenClaw skills. It demonstrates the core value proposition:

- **Your API keys stay local** - `${OPENAI_API_KEY}` is resolved on your machine
- **Validated pipelines** - This skill passes `expanso-cli job validate`
- **Full audit trail** - Every invocation is logged with input hash and trace ID
- **Backend flexibility** - Use OpenAI or Ollama without code changes

## Quick Start

### CLI Mode (for shell scripting)

```bash
# Set your API key
export OPENAI_API_KEY=sk-...

# Summarize text from stdin
echo "Your long article or document text here..." | \
  expanso-edge run pipeline-cli.yaml

# Or pipe a file
cat my-article.txt | expanso-edge run pipeline-cli.yaml
```

### MCP Mode (for OpenClaw integration)

```bash
# Start the skill server
PORT=8080 expanso-edge run pipeline-mcp.yaml &

# Call from curl (or OpenClaw MCP)
curl -X POST http://localhost:8080/summarize \
  -H "Content-Type: application/json" \
  -d '{"text": "Your long article or document text here..."}'
```

## Configuration

| Environment Variable | Required | Description |
|---------------------|----------|-------------|
| `OPENAI_API_KEY` | Yes* | OpenAI API key |
| `PORT` | No | HTTP port for MCP mode (default: 8080) |

*Not required if using Ollama backend locally.

## Example Output

```json
{
  "summary": "• Key insight from the text\n• Another important point\n• Action item or recommendation\n• Supporting detail\n• Conclusion or next steps",
  "metadata": {
    "skill": "text-summarize",
    "mode": "cli",
    "model": "gpt-4o-mini",
    "input_hash": "a1b2c3d4e5f6...",
    "input_length": 2847,
    "trace_id": "550e8400-e29b-41d4-a716-446655440000",
    "timestamp": "2026-01-31T12:00:00Z"
  }
}
```

## Using with Ollama (Local, No API Key)

For complete privacy, you can use Ollama instead of OpenAI. Edit the pipeline to replace `openai_chat_completion` with `o...