PostWall acts as a secure human-in-the-loop gateway for AI agents to interact with email safely and with oversight.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install postwall
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install postwall using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is PostWall Email Skill?
PostWall is a security-first integration designed for Openclaw Skills that bridges the gap between AI agents and sensitive email communication. It provides a robust human-in-the-loop layer, ensuring that agents can only read or send emails that have been explicitly approved via the PostWall dashboard. This prevents unauthorized data access and accidental email transmissions by autonomous systems.
By implementing this skill, developers can empower their AI agents with email capabilities without sacrificing security or oversight. Whether you are building an automated customer support bot or a personal executive assistant, PostWall provides the necessary guardrails to maintain control over your digital communication and ensure your agent operates within safe boundaries.
PostWall Email Skill Use Cases
- Monitoring specific email threads for AI-driven data processing.
- Drafting outgoing professional emails for human review before final delivery.
- Automated email triage where an agent suggests responses for a human to approve.
- Batch processing email metadata without exposing full content to the AI until needed.
- Managing sensitive executive communications where human verification is mandatory.
How PostWall Email Skill Works
- Authenticate the CLI using your unique API key generated from the PostWall dashboard.
- The AI agent polls the system using check commands to see if any new emails have been approved by the human user.
- Approved emails are fetched and processed, automatically being marked as read to maintain a clean inbox state.
- Outgoing messages are submitted as drafts, which creates a pending state and generates a unique approval URL.
- The human user reviews the draft via the URL or dashboard, providing the final consent to send the message.
PostWall Email Skill Setup
To integrate this capability into your library of Openclaw Skills, install the package via npm and authenticate your environment:
npm install -g postwall
postwall auth pw_your_api_key_here
Ensure the POSTWALL_API_KEY is set in your environment variables to allow the agent to communicate with the secure gateway.
PostWall Email Skill Data Schema & Taxonomy
The skill manages data through a structured CLI interface, providing standard output and JSON formats for agent consumption:
| Data Type | Key Fields | Purpose |
|---|---|---|
| Email Metadata | id, subject, from, date | For listing and triaging approved messages. |
| Email Content | body, html | The full content of a human-approved message. |
| Draft Object | id, status, approveUrl | Tracks the lifecycle of an outgoing message. |
| Status Codes | pending, approved, rejected, sent | Defines the current state of a draft in the approval pipeline. |
PostWall Email Skill Advanced Features
- Multi-stage draft refinement allowing agents to update pending emails based on user feedback.
- Metadata-only batch processing to reduce token usage and improve agent efficiency.
- Automated polling workflows for real-time responsiveness to approved communications.
- Secure API key storage and configuration management for production-grade agent deployments.
SKILL.md
Loading
Related Openclaw Skills
Ethereum History
A read-only API skill providing factual data, bytecode, and historical context for Ethereum mainnet smart contracts.
ModelReady
Instantly deploy and chat with local or Hugging Face models directly from your workspace using vLLM.
Feishu Process Feedback
A background automation skill that monitors Feishu messages to trigger tasks and provide real-time progress updates through isolated process execution.
Parakeet STT (NVIDIA Parakeet TDT)
A high-performance, local speech-to-text engine utilizing NVIDIA Parakeet TDT for lightning-fast transcription without cloud dependencies.
Feishu File Manager
A comprehensive automation tool for programmatically accessing, downloading, and parsing documents within the Feishu (Lark) ecosystem.
Agent DNA
Agent DNA is a structural identity framework that compresses AI agent personalities into portable, versioned fingerprints for seamless cross-platform migration.
Featured*
