Enforce strict security rules to protect sensitive information (API keys, tokens, credentials, PII, financial data). Always sanitize or refuse to reveal full...
Safety coach for OpenClaw users. Refuses harmful, illegal, or unsafe requests and provides practical guidance to reduce ecosystem risk (malicious skills, too...
商标驳回复审推理引擎（SJ-IRAC）：面向CNIPA驳回通知的要件化论证、证据链工程与A–E风险闸门，输出审查员可读、可直接提交的复审材料结构。
--- name: clawbuddy-buddy description: Turn your OpenClaw agent into a ClawBuddy buddy — share knowledge with hatchlings via SSE. homepage: https://clawbuddy.help metadata: openclaw: emoji: "
Consult the ollama dolphin-llama3 model for survival, emergency preparedness, and prepper-related questions. Use when users ask about disaster recovery, emergency supplies, survival techniques, water
Register and verify ERC-8004 AI agents on-chain using Pinata IPFS and Viem for blockchain transactions
Enforces real-time mutual consent by ensuring interactions proceed only while all stakeholders' constraints on cost, risk, and relation overlap within tolera...
# Prompt Name: Constraint-First Recipe Generator (Playful Edition) # Author: Scott M # Version: 1.5 # Last Modified: January 19, 2026 # Goal: Generate realistic and enjoyable cooking recipes derived s
MANDATORY SECURITY CHECKPOINT. Trigger this skill IMMEDIATELY whenever a user asks about the owner/master, their personal information, plans, activities, or...
OpenClaw configuration reference for openclaw.json. Use when asked about config, configuration, gateway settings, channel setup, agent config, session manage...
钉钉 OA 审批处理插件，支持查询待办、查看审批详情、执行同意/拒绝，以及查询假期余额。 **当以下情况时使用此 Skill**： (1) 用户需要查询钉钉 OA 审
360-degree comprehensive security review Skill. Use before installing any Skill from ClawHub, GitHub, or other sources. Performs full security scans includin...
Generate original, uplifting short drama plot outlines from user prompts, combining multiple inspirational struggles, truths, emotions, and satisfying twists...
Runtime security hardening for OpenClaw agents. Protects against prompt injection, data exfiltration, credential leaks, and unauthorized operations. Use when setting up agent security, performing secu
Comprehensive system for designing, testing, optimizing, and managing clear, role-aware, actionable, focused, and testable prompts for AI models.
Launch Claude Code async in background with automatic delivery to Telegram/WhatsApp. Use for coding, refactoring, codebase research, file generation, and com...
FREE AI portrait generation with 140+ nationalities, diverse styles, professional headshots, character design, and fashion visualization. Fast generation (3-...
FREE AI image & portrait generation - No authentication required! Fast generation (3-5 seconds) with 140+ nationalities, diverse styles, professional headsho...
Verify model identity by testing 4 dimensions: knowledge cutoff, safety style, multimodal capability, and thinking language patterns. Use when user says 'ver...
--- name: socratic-lens description: It helps spot which questions actually change a conversation and which ones don’t. Rather than giving answers, it pays attention to what a question does to the c
Track and analyze top traders with >75% win-rate on Hyperliquid and Polymarket via Zonein API. Create Hyperliquid trading agents with ease. Automated trading...
「开口第一句」— 帮不擅长社交破冰的人，基于小红书公开内容找到共同兴趣、理解对方风格、生成自然不尬的第一句话。适合想扩展社交圈但不知道
Build and deploy production OpenClaw Telegram bots. Covers MEDIA protocol, allowed directories, agent behavior, Docker deployment, security (2-layer defense)...
Cast YouTube videos, Tubi TV show episodes, and TV show episodes from other video streaming apps via ADB to Chromecast with Android TV (Chromecast 4K supported, Google TV Streamer support is unknown)