---
name: adverse-review
description: "Use when you want adversarial multi-agent review — 3 reviewers (Auditor, Adversary, Pragmatist) for high-stakes changes."
adverse-review
Multi-agent adversarial review.
When to use
See description.
Workflow
Understand the task and check project context.
Follow the source skill steps for this domain.
Verify output and commit.
Verification
Task completed per source skill checklist
Tests pass and no regressions
References
Source: upstream composite
1---2name: adverse-review3description: ---4---5---6name: adverse-review7description: "Use when you want adversarial multi-agent review — 3 reviewers (Auditor, Adversary, Pragmatist) for high-stakes changes."8---910# adverse-review1112Multi-agent adversarial review.1314## When to use1516See description.1718## Workflow19201. Understand the task and check project context.212. Follow the source skill steps for this domain.223. Verify output and commit.2324## Verification2526- [ ] Task completed per source skill checklist27- [ ] Tests pass and no regressions2829## References3031- Source: upstream composite
Run npx skillmds@latest add viasrijan/adverse-review in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
--- It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
viasrijan (@viasrijan) published this skill. Their other Agent Skills are listed on their SkillMD profile.
viasrijan