- Home
- Skills
- Product Management
- PRD Architect
Works with the AI Agents you already use
PRD Architect
Standardized PRD generator using ISO 29148, MoSCoW, and INVEST to create review-ready software requirements.
$9
PRD Architect
Example session with this skill installed
Draft a PRD for a mobile pet-health app. Features: vaccine reminders, health records, vet chat. Target users: young pet owners. Include prioritization and NFRs.
- Read your context and instructions
- Compiled the prd architect
I have generated a complete PRD for the pet-health app, including 5 functional requirements with business rules, ISO 25010 non-functional requirements, and a quality self-audit.
PetHealth Mobile App Product Requirements Document (PRD)
Document Information
- Title: PetHealth Mobile App PRD
- Version: v1.0
- Status: Draft for Review
1. Functional Requirements
FR-001: Vaccine Reminders
- Priority: M (Must)
- Kano: Must-be
User Story: As a pet owner, I want to receive push notifications for upcoming vaccinations so that my pet stays healthy and compliant with local laws.
-
Deep Description:
Business Rules: Reminders trigger 7 days, 3 days, and 24 hours before the due date. Users must be able to mark a vaccine as "Completed" which auto-schedules the next dose based on frequency data.
- Error Flows: If notification permissions are denied, show an in-app banner on the dashboard.
- Boundary Conditions: Support up to 20 pets per account; reminder titles max 50 characters.
- Acceptance Criteria:
- Given a vaccine is due in 7 days, When the system clock reaches 09:00 local time, Then a push notification is sent to the user.
- Given a user taps "Completed", When the vaccine type is "Rabies (1-yr)", Then a new reminder is created for 365 days from the completion date.
FR-002: Real-time Vet Chat
- Priority: S (Should)
- Kano: Attractive
User Story: As a pet owner, I want to chat with a verified vet, so that I can get immediate advice for non-emergency issues.
-
Deep Description:
Business Rules: Session starts only after user accepts the "Not for emergencies" disclaimer. Chats are archived after 24 hours of inactivity.
Error Flows: If no vet is available, show "Average wait time: X mins" and allow user to leave an offline message.
- Acceptance Criteria:
- Given an active session, When a vet sends a message, Then the user receives a real-time notification and the message appears in the thread within <1s.
2. Non-Functional Requirements
| ID | Characteristic | Metric | Test Method |
|---|---|---|---|
| NFR-001 | Performance | Chat message delivery < 500ms | WebSocket latency test |
| NFR-002 | Security | All health data encrypted at rest (AES-256) | Security audit / DB inspect |
| NFR-003 | Availability | 99.5% uptime | Monthly status monitor |
3. SRS Quality Self-Audit
- Structural Completeness: 20/20
- Requirement Clarity: 23/25 (-2 for vague "real-time" definition in chat)
- Prioritization: 20/20
- Verifiability: 20/20
- Traceability: 15/15
- Total Score: 98/100 (Pass)
Next steps
- Review the Open Questions regarding the vet verification process.
- Approve the MoSCoW priorities for the initial sprint.
- Pass the NFR metrics to the DevOps team for infrastructure calibration.
Connects securely to your tools. The creator never sees your data.
About this skill
Requirement gathering is often messy, vague, and inconsistent. This skill converts raw product ideas into review-ready PRDs compliant with ISO/IEC/IEEE 29148:2018 standards.
What it does
- ISO Standard Structuring generates complete document metadata, glossaries, and requirement matrices following ISO 29148.
- Functional Requirements creates numbered FR-XXX entries including INVEST user stories, MoSCoW priorities, and Kano classifications.
- Deep Logic Definitions specifies business rules, explicit error flows, and boundary conditions for every feature.
- Acceptance Criteria writes testable Given-When-Then (BDD) scenarios for all functional requirements.
- NFR Benchmarking provides quantified non-functional requirements based on ISO 25010 quality characteristics.
- Quality Auditing executes a five-dimension weighted self-audit to score the document on clarity and verifiability.
How it works
- Provide the product name, target users, and core problem or feature list.
- The agent identifies missing information and uses industry-default fallbacks marked for confirmation.
- It generates the full PRD including ASCII or Mermaid flow diagrams for complex logic.
- Review the Requirements Traceability Matrix (RTM) and the quality self-audit report.
Frameworks & tools
This skill implements ISO/IEC/IEEE 29148:2018 for systems engineering, ISO 25010 for software quality, MoSCoW for prioritization, Kano for satisfaction modeling, and INVEST for user story validation.
Why this beats prompting it yourself
Standard prompts often miss critical edge cases like error flows and boundary conditions. This skill enforces strict industry standards and produces a traceability matrix, ensuring every requirement is actually testable and aligned with business value.
Use cases
- Product Kickoff turning a one-sentence pitch into a full MVP requirements document.
- Feature Iteration drafting detailed logic for a new module within an existing app.
- Requirement Cleanup standardizing vague stakeholder requests into structured technical specifications.
- Audit & Review scoring existing PRDs against ISO standards to identify gaps in logic or verifiability.
Known limitations
Does not produce visual wireframes or UI designs. Technical architecture, database schemas, and API specs are out of scope. Performance metrics are reference baselines and require engineering validation.
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Product Management.
No visual wireframes or architecture diagrams. No live market research or API specs. NFR metrics are reference baselines only. Requires user to provide at least product name and target users.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed today
Nothing to install. It runs in your AI agent.
Output is a Markdown PRD document. Copy it into Notion, Confluence, or Google Docs for review.
Permissions
No special permissions declared or detected