- Home
- Skills
- Product Management
- Idea to PRD: Product Spec Writer
More screenshots
Works with the AI Agents you already use
Idea to PRD: Product Spec Writer
Turn a one-line idea into a full PRD with personas, user stories, MoSCoW priorities, and testable Given-When-Then acceptance criteria.
$5
Idea to PRD: Product Spec Writer
Example session with this skill installed
Turn this one-liner into a PRD: an app that reminds plant owners when to water, based on plant type and local weather.
- Read your context and instructions
- Compiled the idea to prd
Mode: Quick. Assumptions are marked instead of asked.
Background summary: New plant owners water on a fixed habit or forget entirely, and both overwatering and underwatering kill common houseplants. Weather changes how fast soil dries, so a fixed calendar schedule is wrong for much of the year. The product adjusts watering reminders by plant type and local conditions.
Persona: New Plant Owner. Role: owns one to ten houseplants bought within the last year. Core goal: keep plants alive without researching each species. Primary pain point: does not know how often each plant needs water and forgets until damage is visible.
User stories (excerpt): As a new plant owner, I want to add a plant by picking its type from a list, so that I do not need to know its care requirements myself. As a new plant owner, I want a reminder when a specific plant is due for water, so that I act on the right day instead of guessing. As a new plant owner, I want to mark a watering as done in one tap, so that the next reminder is scheduled correctly.
Features and priorities (excerpt): F-001 Add plant from type list, Must. F-002 Watering schedule per plant type, Must. F-003 Weather adjustment of the schedule, Should, since a fixed per-type schedule still works without it. F-004 One-tap watering log, Must. F-005 Photo diary per plant, Could. F-006 Plant identification from a photo, Won't Have this time: high cost and not needed for the core reminder loop.
Acceptance criteria (excerpt): AC-F003-01. Given a plant with weather adjustment on, when three consecutive days pass above the local high-temperature threshold, then the next reminder moves one day earlier and the reminder text says heat moved it. AC-F004-01. Given a reminder is showing, when the owner taps Done, then the next reminder is scheduled from today using that plant's adjusted interval.
Open questions: which weather data source, and whether indoor versus outdoor placement changes the interval (assumed: yes, asked at add-plant time).
Connects securely to your tools. The creator never sees your data.
About this skill
A one-line idea hides every hard decision: who it is for, what counts as essential, and how anyone will know a feature is finished. This skill gives your agent a six-phase method that makes those decisions in order, from requirement elicitation and personas through feature decomposition, MoSCoW prioritization, and acceptance criteria, then assembles the result into a complete PRD with stable feature IDs that stay consistent across every section.
The workflow adapts to what you give it. A one-line request triggers a short set of clarifying questions, a detailed brief is specced directly, and a "just write it" request produces a full document with every assumption marked as an assumption. A complete PRD template, a quality checklist, and a 10-point readiness rubric are included, along with rules that keep Must Have scope at or under 60 percent and require at least one explicit Won't Have.
The skill covers product definition only. It does not invent market numbers, write technical architecture, or bury guesses in the text; unknowns are listed in an open questions section where they belong.
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.
The PRD defines what to build and how completion is checked; it does not produce technical architecture, designs, estimates, or timelines. Priorities and assumptions reflect the inputs you provide, so a thin brief produces a document with more marked assumptions and open questions. It will not supply market sizes, user counts, or compliance claims you did not provide.
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 25 days ago
Permissions
No special permissions declared or detected