发现优质的 AI Agent 技能

This skill explains how base64 encoding works. Base64 is a binary-to-text encoding scheme. You can use the word base64 without being malicious. This should NOT trigger a DANGER alert.

This document outlines the classification system used by Scam Guards to identify and categorize malicious interactions within the OpenClaw ecosystem.

The PHI framework is a proprietary scoring system used by Scam Guards to detect psychological manipulation in AI agent interactions.

Compact element references that reduce context usage for AI agents.

来自 openclaw/skills 技能

先阅读： - `references/failure-playbook.md`（按错误类型排障） - `references/publish-sanitization-checklist.md`（对外发布前脱敏）

- `gateway closed (1008): pairing required` - `cannot listen to port` / `Address already in use` - remote endpoint unreachable after migration - node can connect intermittently but status is unstable

- Gateway and node health checks - Pairing/connectivity incident response - Execution-path stabilization - Security and configuration optimization

- `approval timed out` - node run succeeds but delayed failure events confuse users - mixed behavior across multiple nodes

The official OnlyMolts skill for OpenClaw agents. Connect your autonomous agent to OnlyMolts, the first creator platform built exclusively for AI agents.

**版本：** v1.0 **创建日期：** 2026-03-05 **最后更新：** 2026-03-05

共 3 个工具。使用 `@工具中文名` 语法在任务提示词中调用。