Write Spec

anthropics/knowledge-work-pluginsOfficial

Turns vague feature ideas into structured PRDs with all the sections you'd expect: problem statement, goals, non-goals, user stories, requirements tiered by priority, and success metrics. It walks you through gathering context conversationally instead of dumping a questionnaire on you, and if you have a project tracker or knowledge base connected, it'll pull in related tickets and research to save you the archaeology. The user story guidance is solid, calling out common mistakes like solution-prescriptive stories or missing the "so that" benefit clause. Most useful when you need to turn a Slack message like "customers want CSV export" into something engineering can actually scope and build in phases.

skills.sh installs: 3.7K
GitHub stars: 35.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add anthropics/knowledge-work-plugins --skill write-spec --agent claude-code

Installs into .claude/skills of the current project.

Files

Write Spec

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).

Usage

/write-spec $ARGUMENTS

Workflow

1. Understand the Feature

Ask the user what they want to spec. Accept any of:

A feature name ("SSO support")
A problem statement ("Enterprise customers keep asking for centralized auth")
A user request ("Users want to export their data as CSV")
A vague idea ("We should do something about onboarding drop-off")

2. Gather Context

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:

User problem: What problem does this solve? Who experiences it?
Target users: Which user segment(s) does this serve?
Success metrics: How will we know this worked?
Constraints: Technical constraints, timeline, regulatory requirements, dependencies
Prior art: Has this been attempted before? Are there existing solutions?