Setup & Installation
openclaw skills install @aronchick/expanso-sentiment-score
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install expanso-sentiment-score
What This Skill Does
Scores the sentiment of any text on a scale from -1 (negative) to +1 (positive). Runs as a standalone CLI pipeline or as an MCP server via the Expanso Edge runtime. Can also be deployed to Expanso Cloud for remote job execution.
Runs locally via Expanso Edge, so text is never sent to a third-party NLP API.
When to use it
- Scoring customer support tickets by emotional tone
- Flagging negative product reviews automatically
- Analyzing social media comments for brand sentiment
- Routing escalations based on message negativity
- Monitoring chat logs for shifts in user mood
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: Score the sentiment of this message: 'The product broke after two days and support never responded.'
AGENT
- 1Receives the text input via CLI pipe or MCP server request
- 2Passes the text to the Expanso Edge pipeline defined in pipeline-cli.yaml or pipeline-mcp.yaml
- 3Pipeline processes the input through the sentiment scoring model
- 4Returns a numeric score between -1 and +1
OUTPUT
Sentiment score: -0.85 (strongly negative)
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
Expanso Edge binary installed and in PATH (install via `clawhub install expanso-edge`)