kimchi:clarify

Extract feature requirements through structured clarification questions and produce CONTEXT.md.

8|Updated Jan 31, 2026
One-click install
npx skills add https://github.com/Tromml/kimchi --skill kimchi-clarify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: kimchi:clarify
Source: https://github.com/Tromml/kimchi/tree/main/plugins/kimchi/skills/clarify
Command: npx skills add https://github.com/Tromml/kimchi --skill kimchi-clarify

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps users clearly define and understand their feature ideas by asking targeted clarification questions, ensuring all ambiguities are resolved before planning begins.

Core Features & Use Cases

  • Iterative Questioning: Engages in a structured dialogue to probe for details about functionality, data, integrations, and constraints.
  • Ambiguity Resolution: Identifies and resolves unclear aspects of a feature idea.
  • Use Case: A product manager has a vague idea for a new user profile feature. They use kimchi:clarify to systematically ask questions about required fields, privacy settings, and integration with existing systems, resulting in a well-defined scope.

Quick Start

Use the kimchi:clarify skill to clarify the feature idea "Implement a dark mode toggle".

Frequently Asked Questions about kimchi:clarify

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

FAQPage Schema
How do I clarify feature ideas and resolve ambiguities before planning begins?

To clarify feature ideas, you engage in structured, iterative questioning across functional, data, integration, constraint, and scope categories. This resolves ambiguities by probing for details, ensuring all specifics are defined before downstream planning begins.

What is the best way to define feature scope and gather requirements for a vague product idea?

Defining feature scope involves targeted dialogue to identify required functionality, data structures, and system constraints. It systematically resolves unclear aspects of a product idea, resulting in a well-defined scope and a detailed context file for planning.

How does iterative questioning work for extracting complete feature definitions?

Iterative questioning works by asking targeted questions across five categories: functional, data, integration, constraint, and scope. This structured dialogue probes for missing details, systematically resolving ambiguities to capture all decisions and specifics.

Can I use this to define integration points and data constraints for a new user profile feature?

Yes, you can use it to define integration points and data constraints. It systematically asks targeted questions about required fields, privacy settings, and existing system integrations, ensuring every aspect of a feature is fully understood and scoped.

What output do I get after resolving feature idea ambiguities?

After resolving ambiguities, you get a detailed CONTEXT.md file. This file captures all decisions and specifics extracted during the clarification process, providing a complete understanding of the feature idea for downstream planning stages.