Skill Miner

Discover, research, and analyze ClawHub skills safely to build your own clean, secure implementations without downloading suspicious code.

This is an instruction-only guide for safely researching ClawHub skills and creating your own clean implementations; it's coherent and does not request secrets or install code. Before using it, confirm you have a trusted 'clawhub' CLI (the skill assumes you will run clawhub search/inspect/explore) and that any 'skill-creator' tooling you use is trustworthy. Remember that running clawhub inspect/search communicates with the ClawHub service — verify that service and the skill owners you inspect are reputable. The SKILL.md is guidance only: it won't execute by itself, but an agent that follows it may run the referenced CLI commands, so control whether the agent is allowed to run external CLIs or make network requests. If you want stronger guarantees, manually perform the inspect steps and avoid running clawhub install on untrusted skills; when building replacements, keep dependencies minimal and avoid executing downloaded code.

Type: OpenClaw Skill Name: skill-miner Version: 1.0.0 The 'skill-miner' bundle is designed to promote secure skill development by guiding the AI agent and user to research existing ClawHub skills without installing potentially risky code, and instead build clean, custom implementations. All instructions, including those in SKILL.md and references/examples.md, consistently emphasize security best practices such as avoiding `eval`, input validation, and not hardcoding secrets. There are no malicious commands, data exfiltration attempts, persistence mechanisms, or prompt injection directives aimed at subverting the agent's behavior or performing harmful actions. The `clawhub` commands used are for legitimate skill discovery and inspection, aligning perfectly with the stated purpose.