ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 3/5

skill-search

Search, discover, and dynamically load skills from the ClawHub registry at skills.droyd.ai. Use when an agent needs a capability it doesn't have, wants to find tools for a specific task, or needs to browse trending/popular skills. Triggers include requests to find skills, search for tools, discover capabilities, load a skill dynamically, check what skills exist for a domain, or run a skill without installing it. Also use when the user asks about available OpenClaw/ClawHub skills, wants to explore skill categories, or needs to fetch and execute skill content on the fly.

Why use this skill?

Learn how to use skill-search to discover, audit, and dynamically load external tools from ClawHub into your OpenClaw agent for flexible automation.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/dustinjamest/dynamic-skills
Or

What This Skill Does

The skill-search capability is a powerful interface for the ClawHub registry, allowing your OpenClaw agent to act as a dynamic explorer of available software tools. Instead of relying solely on pre-installed capabilities, skill-search empowers the agent to fetch, audit, and execute new functions on the fly from the centralized skills.droyd.ai repository. This mechanism acts as a bridge between the agent's core identity and the vast ecosystem of community-contributed automation scripts. By leveraging search queries, category filters, and metadata inspection, the agent can identify the most efficient tool for a given task, inspect its requirements such as API keys or system dependencies, and pull the necessary scripts directly into a secure sandbox for immediate execution.

Installation

To enable this functionality permanently for your agent, you can install the core provider via the CLI using the command: clawhub install openclaw/skills/skills/dustinjamest/dynamic-skills. Once installed, the skill-search command is exposed to the agent’s execution context, allowing it to perform dynamic lookups without further administrative intervention.

Use Cases

This skill is ideal for environments where task diversity is high and pre-installing every possible tool is inefficient. It is best used for research-oriented tasks where the agent needs to find the latest version of a tool (e.g., searching for the newest crypto market analysis scripts), identifying cross-domain capabilities (e.g., using productivity tools to organize marketing data), and executing one-off tasks where full, persistent installation is unnecessary and could clutter the local system environment.

Example Prompts

  1. "I need to automate a task on a website. Search ClawHub for available browser automation tools and check which ones require API keys."
  2. "What are the most popular trending skills in the finance and crypto categories right now? Give me a list of the top 3."
  3. "Find the skill for managing PDF documents, fetch its content, and guide me through the steps to summarize the attached report using its tools."

Tips & Limitations

When using --extract, always be aware that files are written to the /tmp/openclaw-skills/ directory. Ensure your environment has the necessary permissions to write and read from this path. Because this skill allows for dynamic loading, always inspect the SKILL.md file after extraction to ensure you understand the dependencies and operational requirements before triggering execution. Avoid running external scripts that you have not vetted if they demand elevated system permissions.

Metadata

Stars1100
Views0
Updated2026-02-17
View Author Profile
AI Skill Finder

Not sure this is the right skill?

Describe what you want to build — we'll match you to the best skill from 16,000+ options.

Find the right skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-dustinjamest-dynamic-skills": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#registry#discovery#automation#dynamic#tools
Safety Score: 3/5

Flags: network-access, file-write, file-read, code-execution