react-email
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
Security-audited skills for Claude, Codex & Claude Code. One-click install, quality verified.
A lightweight alternative to OpenClaw that runs in containers for security. Connects to WhatsApp, Telegram, Slack and other messaging apps,, has memory, scheduled jobs, and runs directly on Anthropic's Agents SDK
Security checks for the Ralph Loop - scan before commit, fix iteratively, escalate when stuck
Production-ready Claude Code configuration template with stack presets, security hooks, and automation tools
Distributed adversarial behavioral security evaluation framework for LLMs - Swarm-based parallel probing with cryptographic consensus
CTF toolkit for agnets with templates and scripts for exploitation, web security, ICS/SCADA, cryptography, and forensics.
A comprehensive collection of specialized security agents for red teaming, blue teaming, and security development operations.
Review backend code for quality, security, maintainability, and best practices based on established checklist rules. Use when the user requests a review, analysis, or improvement of backend files (e.g., `.py`) under the `api/` directory. Do NOT use for frontend files (e.g., `.tsx`, `.ts`, `.js`). Supports pending-change review, code snippets review, and file-focused review.
Perform code reviews following Sentry engineering practices. Use when reviewing pull requests, examining code changes, or providing feedback on code quality. Covers security, performance, testing, and design review.