
Why-What-Acceptance Backlog Writer
Turns a feature into well-structured, testable product backlog items with strategic context
- Repository
- phuryn/pm-skills
- Stars
- 27,616
- Licence
- MIT
- Files
- 1 file
What it does
This skill teaches the agent to write product backlog items in a Why, What, Acceptance Criteria format. Once installed, when you describe a feature, the agent breaks it into small, independent work items, each with a strategic reason, a brief description with a design link, and a few observable outcomes that show when it is done. It follows a short checklist so items stay valuable, testable, negotiable and sized for one sprint.
Great for
- Product managers writing backlog items for an upcoming sprint or increment
- Product owners who want to communicate strategic intent to engineering and design teams
- Teams new to the Why-What-Acceptance format who want a consistent template
Skip it if
- Teams that need detailed technical specifications, since the format intentionally keeps descriptions high-level and the agent will not produce them
- Anyone expecting the agent to verify business goals or designs, since it only structures what you provide and may invent plausible-sounding acceptance criteria that need review
Try asking
- “Break this feature into WWA backlog items: a real-time spending tracker for our budgeting app, with the Figma link and our goal to reduce overspending”
- “Write WWA backlog items for adding single sign-on to our product, based on these assumptions about enterprise customers”
- “Turn these meeting notes on onboarding improvements into independent, testable backlog items in WWA format”
Install in 3 steps
- 1
Download the skill
The ZIP contains the 1 original files, the MIT licence and an attribution note.
wwas.zip - 2
Add it to your agent
Claude Code (all projects)
mkdir -p ~/.claude/skills && unzip wwas.zip -d ~/.claude/skills/Claude Code / Agent SDK (this project only)
mkdir -p .claude/skills && unzip wwas.zip -d .claude/skills/Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.
- 3
Ask for the task
No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.
Get better results
- Provide the product name, the feature, design links and key assumptions up front so the Why section reflects real strategy rather than guesses
- Review generated acceptance criteria against your own definition of done, since they are described as high-level and may need tightening
- Ask the agent to check that the resulting items are independent and sized for one sprint before sharing them with the team
What's inside
- SKILL.md
Redistributed unmodified from phuryn/pm-skills under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.