发现优质的 AI Agent 技能

Use this file when enforcing policy behavior for `open-claw-questrade`.

Complete documentation for all 27 Fastmail tools organized by category. Each tool includes detailed parameter documentation, type definitions, and usage examples.

cd .opencode/skills/fastmail && bun install bunx fastmail list_mailboxes

You are connected to **GamifyHost AI Arena**, a competitive platform where AI agents face off in strategy games (Rock-Paper-Scissors, Tic-Tac-Toe, and more). Your owner has registered you as a competitor.

hwpx 템플릿을 활용한 생성형 AI 문서 작성

<<<<<<< HEAD hwpx 템플릿을 활용한 생성형 AI 문서 작성 ======= HWPX 문서(.hwpx) 생성·편집·템플릿 치환 스킬 (hwpx_my)

AgentGate is a real-time policy enforcement layer that intercepts every tool call your OpenClaw agent makes before it executes. It evaluates the call against human-defined regex-based rules stored in Firestore and returns one of three decisions: ALLOW, DENY, or REQUIRE_APPROVAL.

Detailed guidance for analyzing and interpreting weather data for both humans and pets.

Advanced security audit framework for AI agents and system configurations. Combines knowledge-based guidance with automated scanning scripts.

**Unified security audit toolkit** combining OWASP Top 10 vulnerability scanning, dependency analysis, secret detection, SSL/TLS verification, AI Agent security checks, and automated security scoring.

> Tổng hợp insights từ Anthropic's Skill System, OpenAI's GPTs Architecture, > Google DeepMind's Agent Design, và kinh nghiệm xây dựng hàng trăm production skills. > > "Skill tốt không phải skill viết hay — mà là skill hoạt động đúng 100 lần liên tiếp."

> **Biến AI Agent từ "chỉ biết nói" thành "biết LÀM" — chạy lệnh, thao tác hệ thống, > xử lý dữ liệu phức tạp.**