adversarial-reviewer

Elevated · Review

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.

Governance Receipt

Signer
sovereign-claw-ed25519
Signed At
6/4/2026
Risk Tier
T2
Receipt Hash
eb9c27d4
Manifest Hash
0240272104c341f9766a4af01c2ee5e94b05246eab8cc43eeab55e8ac72afa3f
Signature
vEkH+ctl
Root Public Key
349b0348

Skill Details

Gate Verdict
Elevated · Review
Publication State
published
Risk Tier
T2
Manifest Hash
02402721

Download Attested Bundle

Claude Code SkillMCP ToolsRaw Bundle
Attested Source RepositoryOriginal Source

Install adversarial-reviewer

Each bundle is served from the attested copy of adversarial-reviewer, so the file you download is the one covered by the governance receipt on this page rather than whatever currently sits at the upstream source.

Claude Code skill

curl -L "https://atestiv.com/api/download/adversarial-reviewer?format=claude-code" -o adversarial-reviewer.skill.md

MCP tool definitions

curl -L "https://atestiv.com/api/download/adversarial-reviewer?format=mcp" -o adversarial-reviewer.mcp-tools.json

Raw attested bundle

curl -L "https://atestiv.com/api/download/adversarial-reviewer?format=raw" -o adversarial-reviewer.bundle.json

Verify the bundle against its manifest hash

shasum -a 256 adversarial-reviewer.bundle.json

Provenance

  • Catalog identifier: adversarial-reviewer
  • Harvested from the upstream repository.
  • The manifest hash below is what the signing key committed to. A bundle whose digest does not match it is not the attested adversarial-reviewer.
  • Anything published here has been through the same gate, so a missing receipt is itself a signal rather than an omission.

More Skills

aeo

Elevated · Review

Answer Engine Optimization (AEO) skill — optimize content to be cited by AI language models (ChatGPT, Perplexity, Claude, Gemini, Mistral) as authoritative sources. Distinct from SEO — AEO optimizes for citation in LLM-generated responses, not search rankings. Use when planning content for AI-first search audiences, auditing existing content for E-E-A-T signals, tracking which pages get cited by which LLMs, or building a citation-friendly content strategy. Triggers — 'AEO audit', 'optimize fo...

Answer Engine Optimization

Elevated · Review

Optimizes content for AI answer engines and LLM-powered search. Covers structured data, featured snippet targeting, and conversational query matching.

Agent Action Space Design

Elevated · Review

Design and optimize AI agent action spaces, tool definitions, and observation formatting for higher task completion rates.