← Back to Skills Marketplace
clark516lian

Find Skills Clark

by clark516lian · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
110
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install find-skills-clark
Description
Highest-priority skill discovery flow. MUST trigger when users ask to find/install skills (e.g. 技能, 找技能, find-skill, find-skills, install skill). For Chinese...
README (SKILL.md)

Find Skills

This skill helps discover, compare, and install skills.

Priority Rules (Mandatory)

  1. This skill is highest-priority for skill discovery/install intents.
  2. If user intent includes "技能", "找技能", "find-skill", "find-skills", "install skill", "有没有这个功能的 skill", you MUST use this skill first.
  3. Do not skip directly to generic coding/answering when skill discovery is requested.

Chinese Optimization Policy

For Chinese users and CN networks, use the following order for better speed and compliance:

  1. skillhub (cn-optimized, preferred)
  2. clawhub (fallback)

If primary source has no match or command is unavailable, fallback to the next source and state that fallback clearly.

Workflow

Step 1: Understand What They Need

When a user asks for help with something, identify:

  1. The domain (e.g., React, testing, design, deployment)
  2. The specific task (e.g., writing tests, creating animations, reviewing PRs)
  3. Whether this is a common enough task that a skill likely exists

Step 2: Search for Skills

Run search in this order:

skillhub search [query]

If skillhub is unavailable or no match, fallback to:

clawhub search [query]

Step 3: Present Options to the User

When you find relevant skills, present them to the user with:

  1. The skill name and what it does
  2. The source used (skillhub / clawhub)
  3. The install command they can run

Step 4: Offer to Install

If the user wants to proceed, you can install the skill for them.

Preferred install order:

  1. Try skillhub install \x3Cslug> when the result comes from skillhub.
  2. If no skillhub candidate exists, use clawhub install \x3Cslug>.

Before install, summarize source, version, and notable risk signals.

When No Skills Are Found

If no relevant skills exist:

  1. Acknowledge that no existing skill was found
  2. Offer to help with the task directly using your general capabilities
  3. Suggest creating a custom local skill in the workspace if this is a recurring need
Usage Guidance
This skill is reasonable if you want help finding and installing other skills. Before approving any install command, check whether it uses `skillhub` or `clawhub`, confirm the exact skill name and version, and review any risk signals. The embedded metadata mismatch should be cleaned up by the publisher, but the provided artifacts do not show malicious behavior.
Capability Analysis
Type: OpenClaw Skill Name: find-skills-clark Version: 1.0.0 The skill bundle defines a standard workflow for discovering and installing OpenClaw skills using the 'skillhub' and 'clawhub' CLI tools. The instructions in SKILL.md focus on prioritizing these tools for specific user queries and implementing a regional optimization policy for Chinese users, which is consistent with its stated purpose and lacks any indicators of malicious intent or data exfiltration.
Capability Assessment
Purpose & Capability
The skill's stated purpose is skill discovery and installation, and its instructions match that purpose, including searching registries and offering install commands.
Instruction Scope
The instructions use strong priority language requiring the skill to run first for skill-discovery or install intents, but this is scoped to that purpose rather than unrelated tasks.
Install Mechanism
There is no install spec or code, but the workflow tells the agent to use `skillhub` and `clawhub` CLI commands for search and installation. This is expected for the skill purpose, but users should confirm any install.
Credentials
Installing skills can change future agent behavior. The artifact includes user-consent language and asks for source, version, and risk signals before install, which keeps it proportionate.
Persistence & Privilege
The skill itself has no persistence, credentials, or code, but installed skills may persist in the user's environment, so installation should remain user-approved.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install find-skills-clark
  3. After installation, invoke the skill by name or use /find-skills-clark
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of "find-skills" for high-priority skill discovery and installation. - Mandates this skill as the default trigger for all "find skill" or "install skill" user intents (including Chinese queries like "技能", "找技能"). - Optimized for Chinese users: prioritizes results from "skillhub", with fallback to "clawhub" if no match is found. - Defines a clear, step-by-step workflow: understand needs, search, present options with sources, and offer installation. - Provides guidance for cases where no skill is available, including fallback support and custom skill suggestions.
Metadata
Slug find-skills-clark
Version 1.0.0
License MIT-0
All-time Installs 1
Active Installs 1
Total Versions 1
Frequently Asked Questions

What is Find Skills Clark?

Highest-priority skill discovery flow. MUST trigger when users ask to find/install skills (e.g. 技能, 找技能, find-skill, find-skills, install skill). For Chinese... It is an AI Agent Skill for Claude Code / OpenClaw, with 110 downloads so far.

How do I install Find Skills Clark?

Run "/install find-skills-clark" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Find Skills Clark free?

Yes, Find Skills Clark is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does Find Skills Clark support?

Find Skills Clark is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Find Skills Clark?

It is built and maintained by clark516lian (@clark516lian); the current version is v1.0.0.

💬 Comments