Devil's advocate skill/plugin for Claude Code and Cowork: turns Claude against you to harshly critique an idea or whole project across 8 angles and return a blunt verdict. Bilingual ES/EN. Made by tododeia.

An AI-powered Fund Manager & Chief Investment Officer app that stress-tests your Stock & Funds thesis against House views, custom rules and data-backed facts

Critical thinking plugin for Claude Code. Three specialized agents (advocate, adversary, judge) argue, stress-test, and judge any idea using a shared argument graph, 10 reasoning traditions, and persistent memory.

A council of AI agents deliberates your hardest decision — and shows its work. 一个公开审议你最难决定的 AI 议事会。

A rule-based foundational ontology and applied physics framework exploring definition discipline, spacetime resistance, gravity, cognition, and field-first engineering.

red-team-challenge: adversarial fact-check / red-team skill for Claude Code (with upgrade dogfood)

Claude skill for legal stress-testing — адвокат дьявола для правовой позиции

系统拆解 colleague-skill（赛博永生/AI同事克隆）概念缺陷的 Skill。基于心理学偏差、第一性原理和历史教训的反驳武器。

Claude Code plugin for second opinions: iterative adversarial debates between Claude and Codex over any subject, from specs, designs, and code to non-technical positions, ending in genuine agreement or a documented dispute.

War-game your hard calls. A council of non-colluding officers plus a mandated dissenter returns the strategy that wins — and what would make it lose. Claude Code plugin.

Multi-persona evaluation skill for Claude Code — T1 quick council, T2 deep analysis, T3 sub-agent dispatch

A reusable, framework-agnostic AI Engineering Operating System for autonomous coding agents with contract-driven verification, adversarial review, and multi-project support.

A devil's-advocate skill for Claude — pushes back on your own ideas with evidence. 4 modes, grounded in 7 decision frameworks.

A multi-stage verification tool for improving quality and reliability in demanding engineering tasks.

Adversarial critique loop for stress-testing a new idea before you build it - with a filter layer that separates real risks from over-worry. Agent skill for Claude Code / OpenCode.

A Claude Code session mode that pushes back. Challenges your decisions and your codebase when warranted, stays silent when the code is fine. Levels: lite, full, ultra.

🏛️ An AI agent swarm that argues like the Roman Senate — five conflicting senators deliberate your decision in parallel, a cross-family envoy attacks their consensus, and the Legions are sent to do the work /senate for Claude Code. SPQR.

Red-team your decisions. ATHENA runs a wise war council with a Sun Tzu terrain read: five adversaries, one GO/RESHAPE/KILL verdict on the record. Adversarial decision intelligence for Claude Code.