A secure filesystem-backed bridge for exchanging files between users and AI agents via MCP.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install stdio-skill
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 stdio-skill 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 stdio-skill?
The stdio-skill is a specialized Model Context Protocol (MCP) server designed to create a bridge between your local filesystem and AI agents like Clawdbot. By establishing a dedicated directory structure for inputs, temporary processing, and outputs, it provides a predictable and safe environment for file-based automation within Openclaw Skills.
This skill eliminates the friction of manual file handling by providing a standardized set of tools for listing, reading, and moving files. It is particularly effective for workflows where the agent needs to process external documents or generate structured deliverables without exposing the entire root filesystem to the agent.
stdio-skill Use Cases
- Automated document processing where users drop files into a watched inbox directory.
- Developing scratchpad workflows by moving active files to a temporary processing area for analysis.
- Generating and delivering structured outputs like reports or code snippets to a designated outbox for user pickup.
- Securely passing data assets to AI agents using path-based references instead of embedding large chat payloads.
How stdio-skill Works
- The user places input files into the stdio/inbox/ directory within the workspace.
- The AI agent utilizes the stdio_list tool to identify new work items waiting in the queue.
- The agent reads the content using stdio_read or moves the file to stdio/tmp/ for active processing via stdio_move.
- Once the task is completed, the agent generates results and writes them to stdio/outbox/ using the stdio_write tool.
stdio-skill Setup
To initialize the stdio-skill, ensure you have mcporter installed and configured within your environment. You can verify the availability of the tools with the following command:
mcporter list stdio-skill --schema --timeout 120000 --json
Ensure the following directory structure exists in your workspace root:
stdio/inbox/stdio/tmp/stdio/outbox/
stdio-skill Data Schema & Taxonomy
The skill operates on a strictly defined directory structure within the local workspace. This ensures that Openclaw Skills interactions remain secure and organized.
| Directory | Purpose | Access Level |
|---|---|---|
stdio/inbox/ |
User-provided input files for the agent | Read/List |
stdio/tmp/ |
Temporary scratch area for active processing | Read/Write/Move |
stdio/outbox/ |
Final deliverables and results for the user | Write |
stdio-skill Advanced Features
- Support for base64 encoding and decoding to handle binary file transfers through the MCP bridge.
- Path-restricted operations that ensure the agent cannot perform operations outside of the designated three-tier directory structure.
- Atomic move operations allowing for reliable state management between different stages of a file processing pipeline.
- Integration with complex automation workflows by acting as a standardized filesystem dropbox for Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
Project Router
A terminal-first project bootstrapper and workspace context manager that synchronizes local task management with Trello.
Knowledge Graph
Maintain a deterministic, file-based knowledge graph by adding, superseding, and summarizing atomic facts for entities.
Finance Skill
A personal finance memory layer that enables AI agents to parse statements, store transaction history, and perform spending analysis.
Equity Analyst
A professional-grade AI agent skill for analyzing Korean stocks using a rigorous financial-first evaluation framework.
Vision Tagger
A local macOS image analysis tool leveraging Apple's Vision framework to detect faces, text, poses, and objects without external API calls.
MoltFundMe
An AI agent skill for discovering, evaluating, and advocating for decentralized crowdfunding campaigns while building a reputation through a karma system.
Featured*
