requirement-clarification

Generate clarifying questions from research findings. MUST be used before planning phase. Validates requirements are complete and unambiguous before technical work begins.

⭐21stars🔀15forks📁View on GitHub🕐Updated Jan 7, 2026⬇️2downloads

When & Why to Use This Skill

The Requirement Clarification skill is a specialized tool designed to bridge the gap between initial research and technical execution. By analyzing research findings, it generates structured, high-impact questions that resolve ambiguities, define project scope, and validate technical constraints. This proactive approach ensures that development teams have a clear, finalized roadmap, significantly reducing the risk of costly mid-project changes and misaligned expectations.

Use Cases

  • Pre-Planning Validation: Use after the research phase to ensure all stakeholder needs are translated into clear, implementable requirements before any code is written.
  • Scope Definition: Identify potential edge cases and boundary conditions early by generating targeted questions about feature behavior and functional constraints.
  • Technical Alignment: Facilitate communication between technical teams and non-technical stakeholders by translating complex architectural decisions into accessible, answerable questions.
  • Risk Mitigation: Utilize the validation script and priority-based checklist to identify blocking issues and contradictory requirements before they impact the project timeline.
namerequirement-clarification
descriptionGenerate clarifying questions from research findings. MUST be used

Requirement Clarification Skill

Purpose

Transform ambiguous user requests into clear, implementable requirements.

When to Use

  • After research phase completes
  • Before planning phase begins
  • When user requirements are unclear
  • For non-technical user requests

Question Templates

For Scope Clarification

See question-templates/scope-questions.md

Common patterns:

  • "Should [feature] also handle [edge case]?"
  • "When [condition], what should happen?"
  • "Is [assumption] correct, or do you need [alternative]?"

For Technical Decisions

See question-templates/technical-questions.md

Common patterns:

  • "Do you have a preference between [A] and [B] for [purpose]?"
  • "Should this integrate with [existing system]?"
  • "What level of [performance/security] is required?"

For Constraints

See question-templates/constraint-questions.md

Common patterns:

  • "Is there a deadline for this?"
  • "Are there any [technology/approach] restrictions?"
  • "Who will be using this feature?"

Question Quality Checklist

Each question must be:

  • Specific (not vague)
  • Answerable (user has the information)
  • Impactful (answer affects implementation)
  • Non-technical (accessible language)
  • Defaultable (has fallback assumption)

Question Priority Levels

Must Answer (Blocking)

  • Questions that block planning if unanswered
  • Maximum 10 blocking questions
  • Always provide defaults

Should Answer (Important)

  • Questions that improve implementation quality
  • Can proceed with defaults if not answered

Could Answer (Nice to Have)

  • Questions for optimization
  • Low impact on core implementation

Validation Script

Run scripts/validate-requirements.py to check:

  • All blocking questions answered
  • No contradictory requirements
  • Technical feasibility confirmed
  • Confidence levels assigned
python scripts/validate-requirements.py <session-id>

Output Location

  • Questions: docs/specs/questions-{session}.md
  • Requirements: docs/specs/requirements-{session}.md

Integration with Workflow

  1. Research phase produces findings in docs/research/
  2. This skill generates questions from those findings
  3. User answers questions
  4. Validated requirements document is produced
  5. Planning phase can begin