AI Agent Skills

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating s…

VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech

A tool to convert a Wallpaper's color scheme / palette, OCR with VLM's Traditional & Hybrid, Image Compression ,color palette extraction, image upsacling with Adversaria…

An adversarial example library for constructing attacks, building defenses, and benchmarking both

[CVPR2020] Adversarial Latent Autoencoders

Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when correctness matters more than speed, when working in unfamiliar code…

Image Deblurring using Generative Adversarial Networks

Create or refine promptfoo redteam setup configs: purpose, targets, plugins, strategies, frameworks, multi-input target inputs, policy text, grader guidance, contexts, a…

Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS…

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfa…

Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adve…

AI-powered adversarial UI testing via the browse CLI. Analyzes git diffs to test only what changed, or explores the full app to find bugs. Tests functional correctness,…

Run an SEO page observation-action-review loop with persistent Memory by coordinating demand research, page creation, adversarial review, image generation, IndexNow subm…

针对方案或设计的高强度追问式面试（adversarial design review / grill session），暴露假设漏洞与缺失约束，过程中同步维护领域模型（术语表和 ADR）。手动调用 /grill-me。

Adversarial verification of finished work. Treats any "done" as a set of claims, then re-runs the claimed verifications, diffs what actually changed, detects weakened te…