Is the Adversarial Reviewer skill free?

Yes. The skill itself is free from mhylle/claude-skills-collection. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Adversarial Reviewer SkillProof Score?

8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.

How do I install Adversarial Reviewer?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Adversarial Reviewer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Adversarial Reviewer

Three isolated subagent personas (Saboteur, New Hire, Security Auditor) hostile-review your diff in parallel.

by mhylle · mhylle/claude-skills-collection

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.8/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 43a56ee

Applied its three persona lenses (Saboteur/New Hire/Security) to a deliberately buggy TTLCache and it surfaced a real stale-value-after-expiry bug plus an API-contract ambiguity my plain baseline review missed — but I couldn't verify its actual differentiator (true parallel-subagent isolation) since this benchmark run forbade spawning subagents, which is exactly the anti-pattern the skill's own doc warns against.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 5/5

What Adversarial Reviewer does

Dispatches three independent Agent subagents — each with only the diff and a persona brief, no shared context — to find production bugs, comprehension gaps, and security holes that a single self-review pass tends to miss. Triggers on requests for a hostile/harsh/adversarial/critical review, pre-merge checks, or a whole-codebase audit via --codebase.

How to install Adversarial Reviewer

git clone https://github.com/mhylle/claude-skills-collection
mkdir -p ~/.claude/skills
cp -r claude-skills-collection/skills/adversarial-reviewer ~/.claude/skills/adversarial-reviewer

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Adversarial Reviewer

/adversarial-reviewer Three isolated subagent personas (Saboteur, New Hire, Security Auditor) hostile-review your diff in parallel.

It also activates on plain-language prompts like these:

Can you do a hostile review of this pull request before I merge it?
I need someone to poke holes in this code from a security angle.
Give me a brutal review of this diff, assume it's full of bugs.

Frequently asked questions

Is the Adversarial Reviewer skill free?: Yes. The skill itself is free from mhylle/claude-skills-collection. SkillProof publishes the install command and an independent test verdict at no cost.
Does Adversarial Reviewer work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Tested · Works. Applied its three persona lenses (Saboteur/New Hire/Security) to a deliberately buggy TTLCache and it surfaced a real stale-value-after-expiry bug plus an API-contract ambiguity my plain baseline review missed — but I couldn't verify its actual differentiator (true parallel-subagent isolation) since this benchmark run forbade spawning subagents, which is exactly the anti-pattern the skill's own doc warns against.
What is the Adversarial Reviewer SkillProof Score?: 8.8/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 5/5.
How do I install Adversarial Reviewer?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Adversarial Reviewer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.