$ loading_
Turn vague feature ideas into structured specs or PRDs.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "write-spec" skill from askskill: 1. Download https://raw.githubusercontent.com/anthropics/knowledge-work-plugins/main/product-management/skills/write-spec/SKILL.md 2. Save it as ~/.claude/skills/write-spec/SKILL.md 3. Reload skills and tell me it's ready
Turn “reduce drop-off after new user signup” into a PRD with a problem statement, goals, non-goals, user stories, P0/P1/P2 requirements, success metrics, open questions, and phased planning.
A structured PRD defining the user problem, scope, priorities, and success measures.
Write a feature spec for “support SSO login.” Fill in any necessary background assumptions first, then produce goals, non-goals, user stories, acceptance criteria, and timeline considerations.
A feature spec for SSO that helps product, design, and engineering align.
We want to build “user data export.” Create a phased spec that separates launch scope from later enhancements, and include success metrics and open questions.
A phased specification that helps the team control scope and move implementation forward.
A product manager or team lead can use it to turn a problem statement, user feedback, or a vague idea into a structured PRD for team review and alignment. It is especially useful for defining goals, non-goals, and acceptance criteria from scratch.
When a team wants to move forward with a feature but the scope is still unclear, this skill helps organize user stories, prioritized requirements, and success metrics. It also helps surface dependencies, constraints, and unresolved questions earlier.
For a large request or cross-functional project, it can break the work into a phased specification that separates what must ship now from what can come later. This makes launch scope and timeline planning easier to manage.
The document explains how write-spec turns a feature name, problem statement, user request, or vague idea into a structured PRD. Its workflow starts by understanding the request, then gathering context such as the user problem, target users, success metrics, constraints, and prior art. If related project, knowledge, or design tools are connected, it can also pull supporting context. The final output includes goals, non-goals, user stories, prioritized requirements, acceptance criteria, success metrics, open questions, and timeline considerations.
If you see unfamiliar placeholders or need to check which tools are connected, see CONNECTORS.md.
Write a feature specification or product requirements document (PRD).
/write-spec $ARGUMENTS
Ask the user what they want to spec. Accept any of:
Ask the user for the following. Be conversational — do not dump all questions at once. Ask the most important ones first and fill in gaps as you go:
If ~~project tracker is connected:
If ~~knowledge base is connected:
If ~~design is connected:
If these tools are not connected, work entirely from what the user provides. Do not ask the user to connect tools — just proceed with available information.
Produce a structured PRD with these sections. See PRD Structure below for detailed guidance on what each section should contain.
After generating the PRD:
…
It is used to generate a structured feature specification or PRD from a problem statement, feature idea, or user request. The document typically includes a problem statement, goals, non-goals, user stories, requirements, success metrics, open questions, and timeline considerations.
Based on the documentation, you can start with a feature name, problem statement, user request, or even a vague idea. It then fills in context step by step, such as the user problem, target users, success metrics, constraints, and prior art.
Yes. The documentation says that if project tracking, knowledge base, or design tools are not connected, it will proceed using only the information provided by the user.
Review content for brand voice, style compliance, and legal-risk issues.
Embed Zoom Virtual Agent chat on web with secure controls and context updates.
Quickly add Zoom’s prebuilt React video UI to web workflows.
Review an analysis for methodology, accuracy, bias, and evidence support.
Generate people analytics reports on headcount, attrition, diversity, and org health.
Choose the right Zoom surface for a product use case with clear tradeoffs.
Write shared product docs and testable specifications for your team.
Turn requirements into a clear step-by-step execution plan before implementation.
Turn Notion specs into implementation plans, tasks, and progress tracking.
Guide users to co-author docs, proposals, and specs through iterative refinement.
Convert PRDs and ideas into structured specs for more accurate AI coding.
Turn finalized designs into clear developer handoff specs for implementation.