dg-skill
OfficialAdversarial code review with two sub-agents.
Software Engineering#git#multi-agent#convergence#quality-assurance#code-review#adversarial-review#template-output
Authoragentspan-ai
Version1.0.0
Installs0
System Documentation
What problem does it solve?
Adversarial code review with two sub-agents helps teams automatically critique and defend code, reducing review time and increasing coverage.
Core Features & Use Cases
- Two-agent adversarial review rounds (Gilfoyle and Dinesh) that iterate until convergence.
- Template-driven output generation using comic-template.html to present findings.
- Suitable for reviewing pull requests, security-sensitive changes, and complex refactors.
Quick Start
Dispatch Gilfoyle to review the code, then Dinesh to respond, and iterate until convergence using comic-template.html as the output template.
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: dg-skill Download link: https://github.com/agentspan-ai/agentspan/archive/main.zip#dg-skill Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.