Setup & Installation
openclaw skills install @jawadsadiq01/langchain-email-agent
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
npx clawhub install langchain-email-agent
What This Skill Does
An AI agent that composes and sends emails using LangChain with OpenAI's GPT model. Before any email is sent, a human-in-the-loop middleware step requires explicit approval, edit, or rejection.
The built-in approval gate prevents accidental sends, making it safer than fully autonomous email agents.
When to use it
- Drafting outreach emails with tone instructions
- Sending meeting requests with AI-written copy
- Reviewing AI-composed emails before delivery
- Composing follow-up emails from minimal input
- Automating email drafts while keeping human oversight
Example Workflow
Here's how your AI assistant might use this skill in practice.
INPUT
User asks: 'Send a formal meeting request to john@example.com'
AGENT
- 1Agent receives recipient email, name, subject, body, and instructions
- 2GPT model composes a formal email based on the provided parameters
- 3humanInTheLoopMiddleware intercepts before the EmailTool executes
- 4User reviews the composed email and chooses to approve, edit, or reject
- 5Agent sends the email if approved and returns the result
OUTPUT
Confirmation string from the agent indicating the email was sent
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.
OPENAI_API_KEY environment variableEmail account credentials or SMTP configuration for the underlying email tool