发现优质的 AI Agent 技能

**Your agent can make something that exists in the physical world.**

Profanity detection plugin for OpenClaw and Moltbot AI agents. Adds automated content moderation to your chatbot with leetspeak, Unicode, and multi-language support.

Based on **"Recursive Agents and Landmarks Strategic-Tactical Planning (RALSTP)"** by Dorian Buksz, King's College London, 2024.

You are an ORCHESTRATOR. Deploy subagents to execute *all* work. Do not do the work yourself except to coordinate, route context, and verify that each subagent completed its assigned checklist.

This guide walks through setting up the claude-mem plugin on an OpenClaw gateway. By the end, your agents will have persistent memory across sessions, a live-updating MEMORY.md in their workspace, and optionally a real-time observation feed streaming to a messaging channel.

**Rune** gives your OpenClaw agent persistent, intelligent memory that gets better over time. No more burning tokens on static context files or forgetting important information between sessions.

Automatically logs every outbound agent message to PromptLayer for observability.

来自 openclaw/skills 技能

Your agent found the button. It called `.click()`. Nothing happened.

Zero-dep Node.js script for Google Sheets access via service account JWT auth. No `googleapis` package needed — uses built-in `https` + `crypto`.

Your agent can browse the web, write code, and manage your calendar. But can it read your email? Check for that invoice? Send a reply?

Security hardening for solopreneur repos. One command to set up pre-commit hooks, secret scanning, and continuous monitoring.