Crucible
Bambushu
Codebase-level adversarial review by a panel of frontier models. A Claude Code skill that runs every file through DeepSeek + Gemini + Kimi + MiniMax in sequence, then ha…
48GitHub
OPENAGENTSKILL / DIRECTORY
AI Agent Skills
Find a skill for your next task. Explore tools for Codex, Claude Code, Cursor and more.
Search retrieves candidates across the registry and ranks a bounded shortlist by task fit. This count is matching candidates, not the registry total. No suitable match? Try a specific tool or task.
Results · “adversarial-attacks”
1–9 / 9
More filters · 1
Results: 9
Agent Review Panel
wan-huiyan
Claude Code skill: Multi-agent adversarial review panel — 4-6 AI reviewers debate your code/plans, then a supreme judge delivers the verdict. 9 auto-detected signal grou…
30GitHub
Raptor
gadievron
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…
3KGitHub
strategy-red-team
phuryn
Red-team a PRD, roadmap, or strategy by attacking its load-bearing assumptions before reality does. Steelmans then attacks each claim, ranks failure modes by impact × li…
CodingClaude Code
26.3KGitHub
Cc Tree
skymanbp
Claude Code plugin: universal radial-tree exploration engine. One tree skill + swappable presets (brainstorm / attack / design / code-audit) for divergent ideation, adve…
161GitHub
Arcjet Js
arcjet
Arcjet JavaScript (JS) / TypeScript SDK. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building…
CodingReview before use
683GitHub
Packj
ossillate-inc
Packj stops :zap: Solarwinds-, ESLint-, and PyTorch-like attacks by flagging malicious/vulnerable open-source dependencies ("weak links") in your software supply-chain
CodingReview before use
687GitHub
Opc
iamtouchskyer
OPC — One Person Company. A full team in a single Claude Code skill. Adaptive agent orchestrator with 11 built-in roles, 4 modes, and adversarial quality control.
CodingClaude Code
194GitHub
Pristine Skill
newbanser
First-Time Principle agent skill — no patching, no residue, single source of truth, adversarial verification, memory drift scan, source map index.
33GitHub
External platform skills
Browse external directory →Owner-curated external sources. Not filtered by the scores or compatibility controls above; excluded from GitHub rankings and automatic installation.
No external entries match this query.