# Critic Attack

> Attack an advocate's case with multiple arguments rated by severity.

- Skill: `yogsoth-ai/critic-attack` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add yogsoth-ai/critic-attack`
- Raw SKILL.md: https://api.skillmd.com/api/skills/yogsoth-ai/critic-attack/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: yogsoth-ai (https://skillmd.com/u/yogsoth-ai)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/yogsoth-ai/critic-attack

---


# Critic Attack

Attacks an advocate's case from multiple angles, producing rated arguments that expose weaknesses, logical gaps, and unsupported claims. The critic's job is to find every legitimate vulnerability.

## Execution

Spawns a subagent with the critic role. The subagent receives the winner context and the advocate's case, then attacks the case systematically.

## Why Subagent

- Role isolation prevents sympathy with the advocate's position
- Critic must attack without mercy or compromise
- Separation ensures the attack is genuine, not performative

## HARD-GATE

Output must include:
- >= 3 distinct attack arguments
- Severity rating for each (HIGH/MEDIUM/LOW)
- Evidence or reasoning for each attack
- At least 1 attack targeting the advocate's strongest point

<!-- BEGIN available-tables (generated) -->

## Available SOPs

Optional, no fixed order; the final leaf is always a sop.

| SOP | When to use |
| --- | --- |
| spawn-agent | Spawn a customized CC subagent with full MCP tool access. Used by SOPs that declare execution: subagent. |

<!-- END available-tables (generated) -->