TAG: AI-TOOLS

Discover untapped project ideas and find what nobody has built yet with nobodybuilt.

GitHub profile README

Methods for creating agent skills with greater integrity and better code execution safety protocols.

# 🔐 Agent Security Eval A lightweight framework for **adversarial testing of AI agents** (Claude, OpenAI, custom agents). This project helps identify: * Prompt injection vulnerabilities * Tool misuse / unsafe execution * Data leakage risks * Weak agent behavior under adversarial inputs ---

Principal-level AI Agents and Skills for SDLC Planning via Model Context Protocol (MCP)

一个用于管理和部署 AI 技能的 Python 命令行工具，支持大模型智能分类、本地软链接一键部署至编程工具（如 Trae/Cursor/VSCode）以及基于 SSH 的远程服务器部署。

Tutorial completo sobre uso de Skills em LLMs (Codex CLI, Claude Code e Gemini CLI) — padrão aberto SKILL.md com exemplos práticos para n8n JavaScript (Code Node v2.9.x+)