Requirements Clarity
Product skill, available on Zeplik
Requirements Clarity is a ready-to-run product management skill on Zeplik. Not for writing the spec itself (use write-spec or idea-to-spec). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
The Requirements Clarity skill loads automatically when your request matches it, or you can invoke it directly by typing /requirements-clarity in any chat. It works with attachments, connectors, and any model that supports the task, so you get the same expert method every time without setting anything up.
What the Requirements Clarity skill can do
- Score vague feature requests against a 100-point clarity rubric
- Run targeted clarification rounds of 2-3 questions until score hits 90
- Track clarity score updates and remaining gaps after each answer
- Produce a structured requirements document with acceptance criteria and phases
Try these prompts on Zeplik
Pick a prompt to open it in the Zeplik app. If you are not signed in yet, your prompt is waiting for you the moment you do.
How the Requirements Clarity skill works
/requirements-clarity
Transform vague requirements into actionable, testable requirements through systematic clarification with a 100-point scoring system. This skill produces the clarified requirements document; when the user wants the full spec written from an already-clear idea, hand off to write-spec or idea-to-spec.
When to Activate
- Vague feature requests: "add login feature", "implement payment", "create dashboard" with no how, technology, or constraints
- Missing technical context: no stack, integration points, or performance/security constraints mentioned
- Incomplete specifications: no acceptance criteria, success metrics, edge cases, or error handling
- Ambiguous scope: unclear boundaries, no MVP vs future distinction, no "what's NOT included"
Do NOT activate when: specific file paths or code snippets are given, existing functions are referenced, or it is a bug fix with clear reproduction steps.
Core Principles
- Systematic questioning: ask focused, specific questions, one category at a time (2-3 questions per round), building on previous answers. Along the way apply two core checks: Why? (YAGNI check) and Simpler? (KISS check).
- Quality-driven iteration: continuously assess a clarity score (0-100), identify gaps, iterate until >= 90 points.
- Actionable output: concrete specifications, measurable acceptance criteria, executable phases.
Clarification Process
Step 1: Initial Requirement Analysis
Parse the requirement, name the feature (kebab-case), and score initial clarity against this rubric:
Functional Clarity: /30 points
- Clear inputs/outputs: 10 pts
- User interaction defined: 10 pts
- Success criteria stated: 10 pts
Technical Specificity: /25 points
- Technology stack mentioned: 8 pts
- Integration points identified: 8 pts
- Constraints specified: 9 pts
Implementation Completeness: /25 points
- Edge cases considered: 8 pts
- Error handling mentioned: 9 pts
- Data validation specified: 8 pts
Business Context: /20 points
- Problem statement clear: 7 pts
- Target users identified: 7 pts
- Success metrics defined: 6 pts
Open with: current clarity score, what is already clear, and what needs clarification.
Step 2: Gap Analysis
Identify missing information across four dimensions:
- Functional scope: core functionality, boundaries, out of scope, edge cases
- User interaction: how users interact, inputs, outputs, success/failure scenarios
- Technical constraints: performance, compatibility, security, scalability
- Business value: problem solved, target users, success metrics, priority
Step 3: Interactive Clarification
- Start with the highest-impact gaps; ask 2-3 questions per round
- Build context progressively, use the user's language, give examples when helpful
- After each response: update the score, capture new information, list remaining gaps
- Score < 90: continue with the next round. Score >= 90: proceed to the requirements document
Score update format:
**Clarity Score Update**: X/100 -> Y/100
**New Clarified Content**:
- [Summarize new information]
**Remaining Points to Clarify**:
- [List remaining gaps if score < 90]
Step 4: Requirements Document
Once clarity >= 90, deliver the complete requirements document as a chat artifact (or write it to docs/prds/{feature-name}-v{version}-prd.md if working in a repo), structured as:
- Requirements Description: background (business problem, target users, value), feature overview (core features, boundaries, user scenarios), detailed requirements (input/output, interaction, data, edge cases)
- Design Decisions: technical approach, constraints, risk assessment
- Acceptance Criteria: checklistable functional, quality, and user acceptance items (
- [ ]format) - Execution Phases: preparation, core development, integration and testing, deployment, each with concrete tasks, deliverables, and time estimates
Behavioral Guidelines
Do: ask specific targeted questions, build on previous answers, provide examples, summarize clarification rounds, generate concrete specifications, stay in clarification mode until score >= 90.
Don't: ask all questions at once, make assumptions without confirmation, generate the document before a 90+ score, use vague language, proceed without user responses.
Success Criteria
- Clarity score >= 90/100
- All sections complete with substance
- Acceptance criteria checklistable
- Execution phases actionable with concrete tasks
- User approves the final document; ready for spec-writing or development handoff
Usage
/requirements-clarity $ARGUMENTS
How to use the Requirements Clarity skill
Sign in to Zeplik
Create a free Zeplik account or sign in. New accounts start with free credits, so you can try the Requirements Clarity skill right away.
Describe your product management task
Ask in plain language, or type /requirements-clarity to invoke the skill directly. Zeplik recognizes the Requirements Clarity skill and applies its method.
Review and refine the result
Zeplik returns a clear, structured answer. Ask follow-ups in the same chat to refine it or take the next step.
Source and credit
- Author
- davila7
- License
- MIT
Adapted from the open-source davila7/claude-code-templates project and tuned to run natively on Zeplik. View source on GitHub.
Frequently asked questions
- What is the Requirements Clarity skill?
- Requirements Clarity is a ready-to-run product management skill on Zeplik. Not for writing the spec itself (use write-spec or idea-to-spec). Ask in plain language and Zeplik applies the skill's method for you inside the conversation, on whichever AI model you prefer.
- How do I use Requirements Clarity on Zeplik?
- Sign in to Zeplik and ask in plain language, or type /requirements-clarity in any chat to invoke it directly. The skill applies its method and returns a result you can refine in the same conversation.
- Which AI model does the Requirements Clarity skill use?
- Any model you choose. Zeplik works across every model in one chat, so the Requirements Clarity skill runs on your preferred model for the task.
- Where does the Requirements Clarity skill come from?
- The Requirements Clarity skill is adapted from the open-source davila7/claude-code-templates project (MIT) and tuned to run natively on Zeplik. The original source is linked on this page.
- How much does the Requirements Clarity skill cost?
- Using the skill is free to start. You only spend Zeplik credits when the assistant runs, and new accounts begin with free credits.
Related product skills
- Agile Product OwnerUse when writing INVEST user stories, acceptance criteria, or grooming and prioritizing a product backlog. Not for sprint ceremony planning (use sprint-planning).
- AI Product BuilderUse when building a paid product that wraps AI APIs: architecture, prompts as product, cost metering, differentiation. Not for calling the Anthropic API in code (use claude-api).
- AI Product DevelopmentIntegration, safety and cost guidance for building or hardening a production LLM feature. Not for a thin one-API SaaS (use ai-wrapper-product).
- Game-Changing FeaturesStack-ranked 10x opportunity analysis across massive/medium/small bets. Not for open-ended ideation (use product-brainstorming) or one idea into a spec (use idea-to-spec).
- Idea to SpecTurn a rough product idea into build-ready documents through staged gates: a clarifying interview in chat, then a design doc artifact, an optional UI brief, and an implementation plan. Use when the user has an app or feature idea and wants it captured, shaped, and specified before any code. Not for tasks that already have a clear spec (use plan or execplan) or for pure research questions.
- Pre-Build Risk ReviewUse for a pre-build risk review of demand, positioning, monetization, retention, distribution before committing to build. Not for turning an idea into a full spec (use idea-to-spec).
More on Zeplik
Try Requirements Clarity on Zeplik
Every model, one chat. Bring the Requirements Clarity skill into your next conversation and let the assistant do the work.