deep-clarify

Clarify vague project requests through guided Socratic questioning into structured spec documents.

7|Updated May 26, 2026
One-click install
npx skills add https://github.com/chrono-meta/forge-harness --skill deep-clarify
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-clarify
Source: https://github.com/chrono-meta/forge-harness/tree/main/plugins/fh-meta/skills/deep-clarify
Command: npx skills add https://github.com/chrono-meta/forge-harness --skill deep-clarify

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill eliminates wasted effort and misalignment caused by vague, undefined project requests by using guided Socratic dialogue to extract clear goals, completion criteria, scope, and constraints from users.

Core Features & Use Cases

  • Guided Socratic Questioning: Asks a maximum of 3 rounds of targeted questions (2 per round) to pull out critical details only the user can provide, while inferring obvious implementation details automatically to avoid unnecessary back-and-forth.
  • Structured Spec Generation: Compiles conversation results into a standardized, actionable spec document saved to .claude/specs/ for use by downstream agents and development tools.
  • Workflow Integration: Automatically suggests the next appropriate skill or agent (such as agent-composer for orchestration or the plan agent for design review) based on the clarified requirements.
  • Use Case: If you have a rough idea like "build a customer onboarding flow" but no clear requirements, this skill will walk you through simple, focused questions to define success metrics, excluded features, and priority, then output a ready-to-use spec for your implementation team.

Quick Start

Invoke the deep-clarify skill with your vague project idea to receive a structured specification document ready for implementation.

Frequently Asked Questions about deep-clarify

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

FAQPage Schema
How do I turn vague project ideas into clear specs for AI coding agents?

To turn vague project ideas into clear specs, guided Socratic dialogue extracts goals, completion criteria, scope, and constraints, generating a structured specification document for downstream implementation. It asks up to 3 rounds of targeted questions while inferring obvious details automatically.

What is the best way to clarify requirements before dispatching an AI agent?

The best way to clarify requirements for pre-dispatch validation is using a structured questioning workflow that defines success metrics, excluded features, and priorities, outputting a ready-to-use specification document saved to .claude/specs/ for your implementation team.

How does Socratic dialogue work for project scoping and requirement clarification?

Socratic dialogue for project scoping works by asking a maximum of 3 rounds of 2 targeted questions per round to pull critical details from the user, while automatically inferring obvious implementation details to minimize unnecessary back-and-forth during requirement clarification.

Can I use generated spec documents with downstream orchestration and planning tools?

Yes, you can use generated spec documents with downstream orchestration and planning tools. The workflow automatically suggests the next appropriate skill or agent, such as agent-composer for orchestration or the plan agent for design review, based on the clarified requirements.

Do I need defined project scope before starting requirement clarification workflows?

No, you do not need a defined project scope before starting requirement clarification. This workflow is specifically designed for ambiguous, underdefined project requests, taking rough ideas like a customer onboarding flow and walking you through focused questions to define the complete scope.

What are the limitations of automated spec generation for feature development?

A limitation of automated spec generation is that it requires user input for critical details only the user can provide, capping questioning at 3 rounds to avoid friction, meaning highly complex feature development may still need manual refinement beyond the generated specification document.