author: luo-kai
name: deliver-acceptance-criteria
description: Generates structured Given/When/Then acceptance criteria for a user story or feature slice. Use when translating product requirements into testable scenarios that cover the happy path, edge cases, error states, and non-functional expectations for engineering handoff and QA.
phase: deliver
version: "1.0.0"
updated: 2026-03-22
license: Apache-2.0
metadata:
category: specification
frameworks: [triple-diamond, lean-startup, design-thinking]
author: product-on-purpose
Acceptance Criteria
Acceptance criteria define the observable behavior that must be true for a story or feature to be considered done. This skill turns feature context into concise, testable Given/When/Then scenarios that engineers and QA can verify without guessing intent.
When to Use
- After a user story, PRD section, or feature slice is defined
- When a team needs clear pass/fail conditions for implementation
- When writing QA-ready criteria for sprint planning or handoff
- When a story has edge cases, error paths, or non-functional expectations that should be explicit
Instructions
When asked to create acceptance criteria, follow these steps:
Confirm the story or feature scope
Identify the exact slice of work. If the scope is unclear, ask for the user story, PRD section, or feature description before drafting criteria.
Separate the happy path from exceptions
Start with the primary success flow, then add edge cases and error states that are likely or costly if missed.
Write each criterion as an observable scenario
Use Given/When/Then language only. Keep each criterion independently testable and avoid implementation details.
Cover recovery and failure behavior
Describe what the user sees or can do when validation fails, a dependency is unavailable, or a save action cannot complete.
Include non-functional expectations
Add criteria for performance, accessibility, security, reliability, or auditability when they matter to the story.
Avoid duplication and overlap
Each criterion should test one outcome. If two criteria describe the same behavior, merge or split them until the intent is clear.
Review for testability
Ensure a reviewer can pass or fail each criterion without interpretation. If a statement is subjective, rewrite it into a measurable outcome.
Output Contract
Use references/TEMPLATE.md as the output format. A complete response should:
- Restate the feature or story context
- Group criteria into happy path, edge cases, error states, and non-functional criteria
- Use explicit Given/When/Then statements for each criterion
- Note assumptions or open questions when context is incomplete
Quality Checklist
Before finalizing, verify:
Examples
See references/EXAMPLE.md for a completed example based on a realistic e-commerce checkout flow.
1---2name: deliver-acceptance-criteria3description: <!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->4---5<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->6---7author: luo-kai8name: deliver-acceptance-criteria9description: Generates structured Given/When/Then acceptance criteria for a user story or feature slice. Use when translating product requirements into testable scenarios that cover the happy path, edge cases, error states, and non-functional expectations for engineering handoff and QA.10phase: deliver11version: "1.0.0"12updated: 2026-03-2213license: Apache-2.014metadata:15 category: specification16 frameworks: [triple-diamond, lean-startup, design-thinking]17 author: product-on-purpose18---19# Acceptance Criteria2021Acceptance criteria define the observable behavior that must be true for a story or feature to be considered done. This skill turns feature context into concise, testable Given/When/Then scenarios that engineers and QA can verify without guessing intent.2223## When to Use2425- After a user story, PRD section, or feature slice is defined26- When a team needs clear pass/fail conditions for implementation27- When writing QA-ready criteria for sprint planning or handoff28- When a story has edge cases, error paths, or non-functional expectations that should be explicit2930## Instructions3132When asked to create acceptance criteria, follow these steps:33341. **Confirm the story or feature scope**35 Identify the exact slice of work. If the scope is unclear, ask for the user story, PRD section, or feature description before drafting criteria.36372. **Separate the happy path from exceptions**38 Start with the primary success flow, then add edge cases and error states that are likely or costly if missed.39403. **Write each criterion as an observable scenario**41 Use Given/When/Then language only. Keep each criterion independently testable and avoid implementation details.42434. **Cover recovery and failure behavior**44 Describe what the user sees or can do when validation fails, a dependency is unavailable, or a save action cannot complete.45465. **Include non-functional expectations**47 Add criteria for performance, accessibility, security, reliability, or auditability when they matter to the story.48496. **Avoid duplication and overlap**50 Each criterion should test one outcome. If two criteria describe the same behavior, merge or split them until the intent is clear.51527. **Review for testability**53 Ensure a reviewer can pass or fail each criterion without interpretation. If a statement is subjective, rewrite it into a measurable outcome.5455## Output Contract5657Use `references/TEMPLATE.md` as the output format. A complete response should:5859- Restate the feature or story context60- Group criteria into happy path, edge cases, error states, and non-functional criteria61- Use explicit Given/When/Then statements for each criterion62- Note assumptions or open questions when context is incomplete6364## Quality Checklist6566Before finalizing, verify:6768- [ ] The criteria map to a specific story or feature slice69- [ ] The happy path is covered first70- [ ] Edge cases are explicit, not implied71- [ ] Error states include user-visible recovery behavior72- [ ] Non-functional criteria are included when relevant73- [ ] Each criterion is testable and has one clear outcome74- [ ] No implementation details leak into the acceptance criteria7576## Examples7778See `references/EXAMPLE.md` for a completed example based on a realistic e-commerce checkout flow.