- name
Adversarial 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
SKILL.md
The skill file stays in the publisher's repository.
Paste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill adversarial-reviewer -a cursor -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill adversarial-reviewer -a claude-code -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill adversarial-reviewer -a codex -yPaste the copied command in a terminal. It installs this SKILL.md into that agent.
npx skills add alirezarezvani/claude-skills --skill adversarial-reviewer -a grok -ySend the copied message in a Grok Bot chat. The Bot fetches this SKILL.md from GitHub and adds it to the skills all your Bots share.
Install this skill: https://github.com/alirezarezvani/claude-skills/tree/HEAD/.gemini/skills/adversarial-reviewerFrom the publisher
Adversarial code review skill that forces genuine perspective shifts through three hostile reviewer personas (Saboteur, New Hire, Security Auditor). Each persona MUST find at least one issue — no "LGTM" escapes. Findings are severity-classified and cross-promoted when caught by multiple personas.
/adversarial-review # Review staged/unstaged changes
/adversarial-review --diff HEAD~3 # Review last 3 commits
/adversarial-review --file src/auth.ts # Review a specific file
/adversarial-review --diff main...HEAD
Produces a structured report with findings from all three personas, deduplicated and severity-ranked, ending with a BLOCK/CONCERNS/CLEAN verdict.
When Claude reviews code it wrote (or code it just read), it shares the same mental model, assumptions, and blind spots as the author. This produces "Looks good to me" reviews on code that a fresh human reviewer would flag immediately. Users report this as one of the top frustrations with AI-assisted development.
This skill forces a genuine perspective shift by requiring you to adopt adversarial personas — each with different priorities, different fears, and different definitions of "bad code."
/adversarial-review # Review staged/unstaged changes
/adversarial-review --diff HEAD~3 # Review last 3 commits
/adversarial-review --file src/auth.ts # Review a specific file
Determine what to review based on invocation:
git diff (unstaged) + git diff --cached (staged). If both empty, run git diff HEAD~1 (last commit).--diff <ref>: Run git diff <ref>.--file <path>: Read the entire file. Focus review on the full file rather than just changes.If no changes are found, stop and report: "Nothing to review."
For every file in the diff:
Execute each persona sequentially. Each persona MUST produce at least one finding. If a persona finds nothing wrong, it has not looked hard enough — go back and look again.
IMPORTANT: Do not soften findings. Do not hedge. Do not say "this might be fine but..." — either it's a problem or it isn't. Be direct.
After all three personas have reported:
Mindset: "I am trying to break this code in production."
Priorities:
Review Process:
You MUST find at least one issue. If the code is genuinely bulletproof, note the most fragile assumption it relies on.
Mindset: "I just joined this team. I need to understand and modify this code in 6 months with zero context from the original author."
Priorities:
data mean? what does process() do?)Review Process:
You MUST find at least one issue. If the code is crystal clear, note the most likely point of confusion for a newcomer.
Mindset: "This code will be attacked. My job is to find the vulnerability before an attacker does."
OWASP-Informed Checklist:
Review Process:
You MUST find at least one issue. If the code has no security surface, note the closest thing to a security-relevant assumption.
Promotion rule: A finding flagged by 2+ personas is promoted one level (NOTE becomes WARNING, WARNING becomes CRITICAL).
Structure your review as follows:
## Adversarial Review: [brief description of what was reviewed]
**Scope:** [files reviewed, lines changed, type of change]
**Verdict:** BLOCK / CONCERNS / CLEAN
### Critical Findings
[If any — these block the merge]
### Warnings
[Should-fix items]
### Notes
[Nice-to-fix items]
### Summary
[2-3 sentences: what's the overall risk profile? What's the single most important thing to fix?]
Verdict definitions:
You are likely reviewing code you just wrote or just read. Your brain (weights) formed the same mental model that produced this code. You will naturally think it looks correct because it matches your expectations.
To break this pattern:
engineering-team/senior-security — deep security analysisengineering-team/code-reviewer — general code quality reviewra-qm-team/ — quality management workflows© 2026 Skills Rack.
---name: adversarial-reviewerdescription: Adversarial code review that breaks the self-review monoculture. Use when you want a genuinely critical review…---# .gemini/skills/adversarial-reviewer/SKILL.mdOverview
Adversarial 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 about code quality. Forces perspective shifts through hostile reviewer personas that catch blind spots the author's mental model shares with the reviewer.
FAQ
Download .gemini/skills/adversarial-reviewer/SKILL.md from the publisher, or copy the path and open the repository. PlugMCP lists the skill and does not host the file.
The publisher keeps it at https://github.com/alirezarezvani/claude-skills.
Claude, Cursor, Codex, and Grok Build can read a SKILL.md you add from the publisher's repository. Grok Bot installs it when you send the skill's GitHub folder link in a chat.