cook

Automate end-to-end feature implementation with research, planning, coding, testing, and review phases.

Updated Jan 27, 2026
One-click install
npx skills add https://github.com/Hoang130203/Emgu_CV_automation --skill cook-hoang130203
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: cook
Source: https://github.com/Hoang130203/Emgu_CV_automation/tree/main/.opencode/skills/cook
Command: npx skills add https://github.com/Hoang130203/Emgu_CV_automation --skill cook-hoang130203

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill streamlines the entire feature implementation process, from initial research and planning to coding, testing, and finalization, by intelligently automating workflows and detecting user intent.

Core Features & Use Cases

  • Smart Intent Detection: Automatically determines the best workflow mode (interactive, auto, fast, parallel, no-test, code) based on user input.
  • End-to-End Automation: Manages research, planning, implementation, testing, and review phases with minimal human intervention when desired.
  • Use Case: A developer needs to add a new payment gateway to an application. They can simply tell the AI /cook implement payment gateway, and the skill will handle researching existing solutions, planning the integration, writing the code, testing it, and preparing it for merge.

Quick Start

Use the cook skill to implement user authentication for the application.

Frequently Asked Questions about cook

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automate end-to-end feature implementation from planning to code review?

End-to-end feature implementation automation works by orchestrating research, planning, coding, testing, and review phases. It intelligently detects user intent and uses subagents to handle specialized tasks, minimizing manual intervention across the entire workflow.

What is the best way to add a new feature using a coding assistant without writing tests manually?

Using a coding assistant with a no-test execution mode allows you to implement features while skipping the testing phase. The workflow still orchestrates research, planning, coding, and review, but omits automated test generation based on detected intent.

Does workflow orchestration support parallel execution modes for coding and testing?

Workflow orchestration supports multiple execution modes including parallel, auto, fast, and interactive. This allows the feature implementation process to run specialized subagents concurrently for research, coding, testing, and review tasks.

Can I execute code for an existing implementation plan without restarting the research phase?

You can execute code for existing plans using the code-execution mode. This skips initial research and planning phases, directly applying the orchestration workflow to implement code based on the predefined plan.

How does intelligent intent detection determine the correct workflow mode for feature implementation?

Intelligent intent detection analyzes user input to automatically select the most suitable workflow mode, such as interactive, auto, fast, or parallel. It evaluates the request context to orchestrate the appropriate research, coding, testing, and review phases.