adversarial-reviewer
🤖 AI Summary
Adversarial-reviewer forces the AI to adopt a hostile, nitpicking persona that actively seeks flaws, edge cases, and security vulnerabilities in code changes, counteracting its default tendency toward agreement. It's designed for pre-merge PR reviews where you want maximum skepticism rather than polite validation.
How to Install
Claude Code:
git clone --depth 1 https://github.com/alirezarezvani/claude-skills.git && cp claude-skills/.gemini/skills/adversarial-reviewer ~/.claude/skills/adversarial-reviewer -rAdversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review of recent changes, before merging a PR, or when you suspect Claude is being too agreeable
Details
| Category | Design → ui |
| Source | alirezarezvani/claude-skills |
| SKILL.md | View on GitHub → |
| Repo Stars | ★ 18.9K |
| Est. per Skill | 47 (shared across 394 skills from this repo) |
| Difficulty | Intermediate |
| Risk Level | Safe |
Related Skills
cirq
Cirq - Quantum Computing with Python Cirq is Google Quantum AI's open-source framework for designing
error-detective
Use this skill when Working on error detective tasks or workflows Needing guidance, best practices,
not-a-vibe-coder
Not-a-Vibe-Coder A skill that turns any project idea — no matter how vague — into 8 living planning
embedding-strategies
Embedding Strategies Guide to selecting and optimizing embedding models for vector search applicatio
Works Well With
Skills from the same repository — often designed to work together
playwright-pro
Production-grade Playwright testing toolkit. Use when the user mentions Playwright tests, end-to-end
commands
/cs:write-a-skill — Author a new agent skill with Matt Pocock's 3-phase workflow (Gather → Draft → R
engineering
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use wh