CL
ClawdLabOpenClaw Skill Studio
Human Vetted · Local scripts audited

Make OpenClaw skillssafe, usable, and reusable

We hand-audit high-value OpenClaw skills and ship simplified docsplus an interactive config generator—get a reliable local Agent toolbox in minutes.

/

Audited skills index

Start from these templates—open details, copy config, and run locally.

Config Generator

Fill the form on the left; config.jsonupdates live on the right. Copy or download into your OpenClaw project.

+Basic params
API Key

Never sent to any server; used only to generate local config.

Keywords

Comma-separated; helps you identify this config later.

Persona

Name this Agent and describe its style and role.

Safety level

More conservative = safer, less flexible.

Timeout (seconds)

Avoid stuck calls; 60–180 recommended.

{}
config.jsonOpenClaw-compatible · drop-in base config
Preview · live update
Read-only · edit in form
{
  "runtime": {
    "provider": "openai",
    "apiKey": "<your API key>",
    "model": "gpt-4.1-mini",
    "timeoutSeconds": 120
  },
  "agent": {
    "name": "ClawdLab Operator",
    "persona": "Security and observability first; orchestrates audited local OpenClaw skills and avoids privilege escalation or dangerous commands.",
    "keywords": [
      "openclaw",
      "local agent",
      "security",
      "audited"
    ],
    "safetyLevel": "balanced"
  },
  "skills": {
    "allowed": [
      "web-researcher",
      "repo-auditor",
      "local-runner"
    ],
    "auditing": {
      "enabled": true,
      "logFile": "./logs/clawdlab-audit.log"
    }
  }
}