From gemini
Run an adversarial code review using Gemini to stress-test and challenge the code. Use when the user wants to find subtle bugs, security issues, or stress-test specific assumptions.
npx claudepluginhub szetty/gemini-cli-plugin-cc --plugin geminiThis skill uses the workspace's default tool permissions.
Use the `gemini_adversarial_review` MCP tool to get Gemini to adversarially challenge the code.
Guides Next.js Cache Components and Partial Prerendering (PPR) with cacheComponents enabled. Implements 'use cache', cacheLife(), cacheTag(), revalidateTag(), static/dynamic optimization, and cache debugging.
Migrates code, prompts, and API calls from Claude Sonnet 4.0/4.5 or Opus 4.1 to Opus 4.5, updating model strings on Anthropic, AWS, GCP, Azure platforms.
Performs token-optimized structural code search using tree-sitter AST parsing to discover symbols, outline files, and unfold code without reading full files.
Use the gemini_adversarial_review MCP tool to get Gemini to adversarially challenge the code.
The user's challenge focus: $ARGUMENTS
If no specific challenge was provided, ask the user what aspect they want to stress-test (e.g. "find race conditions", "break the auth flow", "find data loss scenarios").
After receiving Gemini's adversarial review, present the findings clearly. For each issue found, include the severity and whether you agree with Gemini's assessment.