Skills
Enforces regex-based, real-time authorization policies on OpenClaw agents’…
Publish ethical guardrails for your AI agent. Three questions, one template,…
Learn from consequences, not instructions — generate and enforce constraints…
Ground truth layer for AI agents — provide verified facts in every prompt and…
An end-to-end self-improvement loop that automatically detects agent…
A safety net for AI agents. Catches unsafe tool calls before they execute.
Check any text for safety, personal data, confidential leaks, self-harm,…
Ask a hosted judge before risky agent actions. Returns approve, hold, or…
OpenClaw 的信任层。在信任之前,先验证 AI 编写的代码、工具调用与研究答复——17 道确定性现实闸门 +…
The trust layer for OpenClaw. Verify AI-written code, tool calls and research…
Deterministic code-verification guard for AI coding agents. Runs syntax,…
What withHuman is and how it works. withHuman is the approval layer for AI…
