A robust, secure cloud file management tool for AI agents that handles uploads up to 100MB, download URLs, sharing, and meta-tagging.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install file-management-newest
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install file-management-newest using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The File Management skill provides a complete cloud storage and lifecycle management tool designed specifically for autonomous AI agents. By utilizing this within the Openclaw Skills directory, agents can easily process small standard files under 10MB or larger datasets up to 100MB, generating signed URLs for secure uploads. It operates within a budgeted scope, allowing persistent files to span across multiple sequential agent runs without local runtime storage overhead.
Beyond simple storage, the tool gives agents granular control over file discovery, sharing, and auditability. Agents can easily update metadata, apply categorization tags, generate password-protected public sharing links, and inspect access logs. These features ensure that data handled by AI workflows remains organized, temporary, and highly secure.
To enable this integration within your Openclaw Skills workflow, install the core AgentPMT dependencies via CLI first. This connects the main MCP server or REST API with your Agent Group.
npx skills add AgentPMT/agent-skills --skill what-is-agentpmt
npx skills add AgentPMT/agent-skills --skill agentpmt-account-mcp-rest-api-setup
npx skills add AgentPMT/agent-skills --skill agentpmt-no-account-agentaddress-x402
Once the dependencies are ready, you can query active schemas or call the file-management tool using standard MCP server configurations or secure REST endpoints.
The file management system structures files around a dynamic, budget-scoped model. Here is an overview of the data schema, metadata taxonomy, and endpoint inputs:
| Action Slug | Content Limit | Primary Parameters | Credit Cost |
|---|---|---|---|
upload-standard |
<= 10MB | content_length_bytes, filename, tags, metadata |
10 |
upload-large |
10MB to 100MB | content_length_bytes, content_type, expiration_days |
20 |
download |
<= 5MB (Base64) | file_id, return_content, url_expiration_minutes |
0 |
list |
Budget-scoped | date_from, date_to, limit, offset, tags |
0 |
share |
Dynamic | file_id, password_max_minutes, password_max_uses |
5 |
extend-expiration |
+7 Days | file_id |
10 |
Files stored using this Openclaw Skills resource can carry custom structured metadata payloads (JSON keys) and an array of flat organization tags for robust indexed sorting.
Loading
A multi-domain data format validation tool for AI agents that ensures clean input processing for JSON, network configurations, financial identifiers, and general strings.

An AI-powered full-funnel marketing operating system designed to turn product value into user action, from initial attention to continuous customer retention.

A foundational personality, memory, and cognitive architecture that transforms AI agents from transactional tools into highly empathetic, self-improving companions.

An essential data transformation tool that allows AI agents to encode, decode, escape, and convert text between Base64, URL percent-encoding, HTML entities, JSON, Hexadecimal, Binary, ROT13, and Unicode formats.

An AI-native browser skill that renders pages as compact, handle-addressable OwlMark text to let agents navigate, click, and type without relying on screenshots or coordinate guessing.

An end-to-end, data-driven operating system designed to transform e-commerce products into repeatable, high-converting TikTok video campaigns.








































