skills.rest
AtaraxiaEpiphany
AtaraxiaEpiphanyCOMMUNITY
Explore all skills by this author →
GitHub

review

Orchestrate adversarial multi-lens code reviews against project specifications.

Updated May 7, 2026
Search Tags:#automation#tdd#software engineering#quality assurance#code review#conductor
One-click install
npx skills add https://github.com/AtaraxiaEpiphany/conductor --skill review-ataraxiaepiphany
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/AtaraxiaEpiphany/conductor/tree/main/skills/review
Command: npx skills add https://github.com/AtaraxiaEpiphany/conductor --skill review-ataraxiaepiphany

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the limitations of single-pass AI code reviews by implementing an adversarial, multi-lens verification process that ensures high-quality, compliant, and test-verified code.

Core Features & Use Cases

  • Adversarial Review: Uses a fanned-out approach with specialized lenses (bugs, security, spec-compliance, tests) and a completeness critic to catch issues missed by standard reviews.
  • State-Aware Verification: Integrates directly with Conductor's track-state system to ensure reviews are contextually accurate to the specific development track.
  • Automated Remediation: Provides a structured path to apply fixes and archive completed work, maintaining project integrity.

Quick Start

Use the review skill to perform a comprehensive quality audit on the current implementation track.

Frequently Asked Questions about review

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

FAQPage Schema
How does adversarial code review improve software quality assurance?▼

Adversarial code review improves quality assurance by using a fanned-out approach with specialized lenses for bugs, security, spec-compliance, and tests, alongside a completeness critic to catch issues missed by standard reviews.

How do I verify test coverage and spec compliance for a new implementation track?▼

You can verify test coverage and spec compliance by orchestrating a multi-lens review process that analyzes diffs and validates the implementation directly against project specifications and quality standards.

Do I need the Conductor subagent ecosystem to automate track-based code reviews?▼

Yes, automating track-based code reviews requires integration with the Conductor subagent ecosystem and the track-state CLI to execute concurrent analysis and iterative refinement loops.

What is the best way to automate remediation after an adversarial code review?▼

The best way to automate remediation is using a structured path to apply fixes and archive completed work, which maintains project integrity after the multi-lens review identifies issues.

Why does single-pass AI code review miss spec-compliance and security issues?▼

Single-pass AI code review misses issues because it lacks an adversarial verification process, meaning it cannot concurrently analyze specialized dimensions like security and spec-compliance with a completeness critic.

Related Skills

Explore More Software Engineering Skills→
AtaraxiaEpiphanyAtaraxiaEpiphany

implement

Orchestrate software development tasks through a state-machine-driven subagent loop.

Community
Advanced
SimplifyMyCloudSimplifyMyCloud

openspec-bulk-archive-change

Batch-archive multiple completed OpenSpec changes with conflict resolution and status checks.

Official
Advanced
HomericIntelligenceHomericIntelligence
18

quality-run-linters

Run Mojo format, markdownlint, and pre-commit hooks for code quality checks.

Official
Intermediate
roderikroderik

adversarial-review

Spawn opposite-model reviewers via CLI to critique code changes and output a synthesized verdict.

Community
Advanced