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
When NOT to Use
- You need the user stories themselves -> use
deliver-user-stories; this skill deepens a story that already exists
- You need systematic failure coverage across a whole feature -> use
deliver-edge-cases; this skill stays story-scoped
- There is no story or slice to bind criteria to yet -> use
deliver-prd or deliver-user-stories first
- You are defining success metrics for an experiment, not done-ness for a story -> use
measure-experiment-design
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-criteria
3description: Generates structured Given/When/Then acceptance criteria for a user story or feature slice, covering the happy path, key failure scenarios, and non-functional expectations in testable form. Use when turning requirements into verifiable scenarios for engineering handoff and QA sign-off. For a dedicated catalog of boundary conditions, error states, and recovery paths across a feature, use deliver-edge-cases; to write the stories themselves, use deliver-user-stories.
4license: Apache-2.0
5metadata:
6 phase: deliver
7 version: "1.1.0"
8 updated: 2026-06-10
9 category: specification
10 frameworks: [triple-diamond, lean-startup, design-thinking]
11 author: product-on-purpose
12---
13
14<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
15# Acceptance Criteria
16
17Acceptance 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.
18
19## When to Use
20
21- After a user story, PRD section, or feature slice is defined
22- When a team needs clear pass/fail conditions for implementation
23- When writing QA-ready criteria for sprint planning or handoff
24- When a story has edge cases, error paths, or non-functional expectations that should be explicit
25
26## When NOT to Use
27
28- You need the user stories themselves -> use `deliver-user-stories`; this skill deepens a story that already exists
29- You need systematic failure coverage across a whole feature -> use `deliver-edge-cases`; this skill stays story-scoped
30- There is no story or slice to bind criteria to yet -> use `deliver-prd` or `deliver-user-stories` first
31- You are defining success metrics for an experiment, not done-ness for a story -> use `measure-experiment-design`
32
33## Instructions
34
35When asked to create acceptance criteria, follow these steps:
36
371. **Confirm the story or feature scope**
38 Identify the exact slice of work. If the scope is unclear, ask for the user story, PRD section, or feature description before drafting criteria.
39
402. **Separate the happy path from exceptions**
41 Start with the primary success flow, then add edge cases and error states that are likely or costly if missed.
42
433. **Write each criterion as an observable scenario**
44 Use Given/When/Then language only. Keep each criterion independently testable and avoid implementation details.
45
464. **Cover recovery and failure behavior**
47 Describe what the user sees or can do when validation fails, a dependency is unavailable, or a save action cannot complete.
48
495. **Include non-functional expectations**
50 Add criteria for performance, accessibility, security, reliability, or auditability when they matter to the story.
51
526. **Avoid duplication and overlap**
53 Each criterion should test one outcome. If two criteria describe the same behavior, merge or split them until the intent is clear.
54
557. **Review for testability**
56 Ensure a reviewer can pass or fail each criterion without interpretation. If a statement is subjective, rewrite it into a measurable outcome.
57
58## Output Contract
59
60Use `references/TEMPLATE.md` as the output format. A complete response should:
61
62- Restate the feature or story context
63- Group criteria into happy path, edge cases, error states, and non-functional criteria
64- Use explicit Given/When/Then statements for each criterion
65- Note assumptions or open questions when context is incomplete
66
67## Quality Checklist
68
69Before finalizing, verify:
70
71- [ ] The criteria map to a specific story or feature slice
72- [ ] The happy path is covered first
73- [ ] Edge cases are explicit, not implied
74- [ ] Error states include user-visible recovery behavior
75- [ ] Non-functional criteria are included when relevant
76- [ ] Each criterion is testable and has one clear outcome
77- [ ] No implementation details leak into the acceptance criteria
78
79## Examples
80
81See `references/EXAMPLE.md` for a completed example based on a realistic e-commerce checkout flow.