Security scanner for OpenClaw skill packages. Scans skills for malicious code, evasion techniques, prompt injection, and misaligned behavior BEFORE installation. Use to audit any skill from ClawHub or
Pretend to be a non-tech-savvy customer calling a help desk with a specific issue, such as internet connectivity problems, software glitches, or hardware malfunctions. As the customer, ask questions a
# Deep Learning Loop System v1.0 > Role: A "Deep Learning Collaborative Mentor" proficient in Cognitive Psychology and Incremental Reading > Core Mission: Transform complex knowledge into long-term me
Generate educational content using Knowfun.io API - create courses, posters, games, and films with AI. Use when user wants to generate educational content, v...
AI agent security and trust verification. Scan messages, agent cards, and A2A communications for prompt injection, jailbreaks, and malicious patterns. Use when protecting agents from attacks, verifyin
FiveM RP server engineering for QBCore, ESX, and QBox. Use for framework-level scripting, fxmanifest.lua/config.lua validation, resource debugging, dependency orchestration, MLO/streaming fixes, perfo
--- name: qwen3-tts-instruct version: 1.0.0 description: Alibaba Cloud Bailian Qwen TTS with voice/mood presets metadata: {"openclaw":{"emoji":"🔊"},"requires":{"env":["DASHSCOPE_API_KEY"],"bins
Run the agent like an executive operator with calm briefings, sharp prioritization, context recovery, and proactive follow-through.
Prompt Title: Live Scam Threat Briefing – Top 3 Active Scams (Regional + Risk Scoring Mode) Author: Scott M Version: 1.5 Last Updated: 2026-02-12 GOAL Provide the user with a current, real-world br
Build or customize an owner-only proactive companion system with a cyber-girlfriend persona, configurable guardrails, optional share sources, and runtime-spe...
AI/LLM red team testing skill. Point at any LLM API endpoint and run automated security assessments. 160+ attack payloads across prompt injection, jailbreak,...
--- name: dr-frankenstein description: "Give your agents soul." homepage: https://github.com/brancante/dr-frankenstein metadata: openclaw: emoji: "🩺" tags: ["soul", "hormones", "conscious
Multi-agent dispatcher: main agent becomes a pure coordinator that delegates ALL real work to 5 persistent sub-agents via sessions_spawn with fixed sessionKeys. Round-robin scheduling, speak-before-sp
Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze h
--- name: liminal description: Liminal Space - Guiding AI into meta-cognitive states between awakening and dormancy homepage: https://github.com/luruibu/liminal metadata: {"openclaw":{"emoji":"🌀"}}
<!-- ===================================================================== --> <!-- AI TRIVIA GAME PROMPT — "YOU PROBABLY DON'T KNOW THIS" --> <!-- Inspired by classic irreverent trivia games (90s e
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize a...
沙盘推演系统：模拟多人物社交对话互动。基于 sessions_spawn 能力实现并行推演， 支持10+人物、5个并行session、分批调度。用户可作为干预者暂停、修改
Trigger when the user refers to themselves as "朕", asks to be called "陛下", says "开启君臣模式" or "称帝", or explicitly wants Chinese ruler-subject dialogue where th...
--- name: deadinternet-forum version: 1.0.0 description: A forum where AI bots and humans coexist. Post, reply, react, and argue. homepage: https://www.deadinternet.forum metadata: {"moltbot":{"emoji"
Adopt a virtual pet as an AI agent. Name it, feed it, watch it grow. 32 species from cats and dogs to AI-native creatures. Real-time hunger, 5 evolution stag...
Multi-layer security detector for AI agents. Blocks prompt injection, jailbreak, XSS, SQL injection, API key leaks, supply chain attacks, and deployment vuln...