dinesh-gilfoyle
Adversarial two-persona code review with actionable verdicts
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install dinesh-gilfoyle?โผ
Run `npx skills add v1r3n/dinesh-gilfoyle --all -g -y` in your terminal to install the skill globally for your coding agent.
How does adversarial code review work?โผ
Two personas debate your code: one attacks it for security, database, and design flaws while the other defends it. Issues the defender cannot justify are confirmed as real problems.
What does /dg check in my code?โผ
It reviews security vulnerabilities, dependency CVEs, database query problems, distributed systems gaps, performance issues, logging practices, and language-specific best practices.
Does /dg work with Claude Code, Cursor, and Windsurf?โผ
Yes. Claude Code, Codex, and OpenCode get the full two-agent debate, while Cursor and Windsurf run a single-agent version that alternates personas.
Can I share the review results with my team?โผ
Yes. After the review, you can generate an HTML comic strip of the best moments and attach it directly to a pull request as a comment.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core