Bug Hunter
codexstar69
Adversarial AI bug hunter with auto-fix skill for Claude Code, Cursor, Codex CLI, GitHub Copilot CLI, Kiro CLI, Opencode, Pi Coding Agent, and more. Multi-agent pipeline…
502GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Results · “adversarial”
1–8 / 8
More filters · 1
Candidates in this shortlist, not the full registry. GitHub stars belong to repositories, not individual skills.
Results: 8
doubt-driven-development
addyosmani
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…
91.4KGitHub
ai-security
alirezarezvani
Use when assessing AI/ML systems for prompt injection, jailbreak vulnerabilities, model inversion risk, data poisoning exposure, or agent tool abuse. Covers MITRE ATLAS…
25.1KGitHub
ui-test
browserbase
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,…
3.7KGitHub
redteam
agentscope-ai
Use when the user wants to test their LLM/agent application for safety and security vulnerabilities — jailbreaks, prompt injection, PII extraction, harmful content gener…
816GitHub
oracle-prism
Soul-Brews-Studio
Multi-perspective analysis — one agent transforms through 5 lenses (Archaeologist, Bug Hunter, Skeptic, Architect, Auditor) inline, no subagents. Use when user says "pri…
121GitHub
verbalized-sampling
gnurio
Generate diverse outputs by prompting for a probability distribution instead of a single response. Implements Verbalized Sampling (VS) from Zhang et al. 2025 — a trainin…
104GitHub
tree
skymanbp
Universal radial-tree exploration engine. Loads a preset, builds a §2 baseline, then recursively applies 12 framing passes per node until stable convergence (no new high…
107GitHub