Loading...
Loading...
Found 10 Skills
Use when working with error debugging multi agent review
Use when working with performance testing review multi agent review
Comprehensive multi-perspective review using specialized judges with debate and consensus building
Orchestrates design workflows by routing work through brainstorming, multi-agent review, and execution readiness in the correct order. Prevents premature implementation, skipped validation, and unreviewed high-risk designs.
After the task execution is completed, prompt the user to open a new Agent to review the uncommitted git code. Athletes should not act as referees; proceed with the wrap-up only after the review is approved.
Comprehensive code review workflow - parallel specialized reviews → synthesis
Validates optimization plan via parallel multi-agent review (Codex + Gemini) before execution. GO/NO-GO verdict.
Multi-agent review of implementation plans. Use after creating a plan but before implementing, especially for complex or risky changes.
Multi-agent quality improvement review with constructive feedback. Provides suggestions for best practices, code quality, alternatives, and performance optimization.
Initialize a long-running project with a structured docs workflow, or update an existing project (new features, bug fixes, refactors, requirement changes). Use this skill whenever the user wants to start a new project, kick off a long-running build task, set up project documentation structure, or says things like "new project", "start a project", "init project", "project setup", or "I want to build something from scratch". Also use when the user mentions wanting a milestone-based plan, structured execution workflow, or asks to scaffold documentation for a complex multi-step build. Additionally, use this skill when the user wants to modify an existing project that already has a `docs/` directory — e.g., "add a new feature", "fix this bug", "refactor X", "I want to change how Y works", "new feature request".