adversarial-reviewer

Reviews code adversarially to find bugs across logic, security, concurrency, and error handling categories.

Updated Aug 14, 2026
One-click install
npx skills add https://github.com/tatran0195/emdash-with-docs --skill adversarial-reviewer-tatran0195
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: adversarial-reviewer
Source: https://github.com/tatran0195/emdash-with-docs/tree/main/skills/adversarial-reviewer
Command: npx skills add https://github.com/tatran0195/emdash-with-docs --skill adversarial-reviewer-tatran0195

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Standard code reviews often miss subtle bugs because reviewers give code the benefit of the doubt. This Skill forces a hostile review posture that assumes bugs exist and hunts for them with concrete triggers, catching defects before they reach production. ## Core Features & Use Cases - Systematic Bug Hunting: Works through seven ordered categories — logic errors, edge cases, error handling, state and concurrency, security, data integrity, and resource management. - Structured Findings: Outputs each bug with file location, category, severity rating (CRITICAL to LOW), a concrete trigger scenario, and a minimal fix. - Use Case: Before merging a pull request that touches payment logic, run an adversarial review to surface race conditions, missing authorization checks, and swallowed errors with proof-of-concept inputs for each finding. ## Quick Start Review the code in this pull request adversarially and tell me every bug you can find with severity and a concrete trigger.

Frequently Asked Questions about adversarial-reviewer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I get a thorough code review that finds real bugs?▼

Ask for an adversarial review of your code or pull request. The reviewer assumes every line is guilty until proven innocent, works through seven bug categories systematically, and reports each finding with a concrete trigger scenario and severity rating.

What kinds of bugs does adversarial code review catch?▼

It covers logic errors, edge cases and boundaries, error handling failures, state and concurrency races, security vulnerabilities, data integrity issues, and resource management problems like leaks and missing timeouts.

How are code review findings reported and prioritized?▼

Each bug is reported with a title, file and line number, category, and severity from CRITICAL to LOW, plus a trigger scenario and minimal fix. Findings are ordered by severity with CRITICAL first.

Does adversarial review comment on code style or suggest refactors?▼

No. It explicitly excludes style feedback, feature suggestions, refactoring advice, and test coverage commentary. It only reports demonstrable bugs, and if none are found it says so rather than manufacturing issues.

When should I use adversarial review instead of a normal code review?▼

Use it for high-risk changes such as payment logic, authentication, concurrency-heavy code, or pre-merge PR audits where missed defects are costly. It is less suited for early drafts where design feedback matters more than bug hunting.