cascade-code-testing-code-review

Systematic workflow for processing CodeRabbit code review feedback with MCP-powered analysis and fixes

Audit Anthropic cookbook notebooks against structured rubrics to ensure quality, clarity, and best practices.

Independent code review using a different, larger model for fresh perspective

Computer Use MCP app testing with scenario execution and feedback reporting

call another agent to perform a task.

Useful slash commands for managing pull requests

pair-review app integration — Open PRs and local changes in the pair-review web UI, run server-side AI analysis, and address review feedback. Requires the pair-review MCP server.

Symmetric two-AI peer review using OpenAI Codex CLI. Both AIs review independently in a blind pass, then debate per-issue with terminal states until convergence. Catches significantly more issues than single-pass validation.

Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.

Rust development skill with strict coding standards, FAIL FAST error handling, and build/review agents

Code review, compare, and debate tools using multiple AI models

Comprehensive feature development workflow with spec-driven implementation, atomic phasing, and multi-agent collaboration

Verify code, architecture, and bug fixes through factored multi-agent verification

Comprehensive code review skills with an orchestrator for triage/routing and 11 specialist sub-skills for security, correctness, API, data, concurrency, performance, observability, testing, style, and configuration analysis.

Multi-AI orchestration pipeline with Task-based enforcement and Codex final gate