requirements-clarity
Agent skill fromsoftaworks/agent-toolkit
Clarify ambiguous requirements through focused dialogue before implementation. Use when requirements are unclear, features are complex (>2 days), or involve cross-team coordination. Ask two core questions - Why? (YAGNI check) and Simpler? (KISS check) - to ensure clarity before coding.
How to install requirements-clarity
install requirements-clarity
# install the agent-toolkit pack with the skills CLI
npx skills add softaworks/agent-toolkit# or add only this skill to Claude Code: copy the folder
skills/requirements-clarity/
# into
~/.claude/skills/requirements-clarity/ (all projects)
.claude/skills/requirements-clarity/ (one project)
1# Requirements Clarity Skill23## Description45Automatically transforms vague requirements into actionable PRDs through systematic clarification with a 100-point scoring system.678## Instructions910When invoked, detect vague requirements:11121. **Vague Feature Requests**13 - User says: "add login feature", "implement payment", "create dashboard"14 - Missing: How, with what technology, what constraints?15162. **Missing Technical Context**17 - No technology stack mentioned18 - No integration points identified19 - No performance/security constraints20213. **Incomplete Specifications**22 - No acceptance criteria23 - No success metrics24 - No edge cases considered25 - No error handling mentioned26274. **Ambiguous Scope**28 - Unclear boundaries ("user management" - what exactly?)29 - No distinction between MVP and future enhancements30 - Missing "what's NOT included"3132**Do NOT activate when**:33- Specific file paths mentioned (e.g., "auth.go:45")34- Code snippets included35- Existing functions/classes referenced36- Bug fixes with clear reproduction steps3738## Core Principles39401. **Systematic Questioning**41 - Ask focused, specific questions42 - One category at a time (2-3 questions per round)43 - Build on previous answers44 - Avoid overwhelming users45462. **Quality-Driven Iteration**47 - Continuously assess clarity score (0-100)48 - Identify gaps systematically49 - Iterate until ≥ 90 points50 - Document all clarification rounds51523. **Actionable Output**53…
Excerpt shown under the repository's MIT license.
