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-criteria3description: 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-2.05---6<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->
7# Acceptance Criteria
8
9Acceptance 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.
10
11## When to Use
12
13- After a user story, PRD section, or feature slice is defined
14- When a team needs clear pass/fail conditions for implementation
15- When writing QA-ready criteria for sprint planning or handoff
16- When a story has edge cases, error paths, or non-functional expectations that should be explicit
17
18## When NOT to Use
19
20- You need the user stories themselves -> use `deliver-user-stories`; this skill deepens a story that already exists
21- You need systematic failure coverage across a whole feature -> use `deliver-edge-cases`; this skill stays story-scoped
22- There is no story or slice to bind criteria to yet -> use `deliver-prd` or `deliver-user-stories` first
23- You are defining success metrics for an experiment, not done-ness for a story -> use `measure-experiment-design`
24
25## Instructions
26
27When asked to create acceptance criteria, follow these steps:
28
291. **Confirm the story or feature scope**
30 Identify the exact slice of work. If the scope is unclear, ask for the user story, PRD section, or feature description before drafting criteria.
31
322. **Separate the happy path from exceptions**
33 Start with the primary success flow, then add edge cases and error states that are likely or costly if missed.
34
353. **Write each criterion as an observable scenario**
36 Use Given/When/Then language only. Keep each criterion independently testable and avoid implementation details.
37
384. **Cover recovery and failure behavior**
39 Describe what the user sees or can do when validation fails, a dependency is unavailable, or a save action cannot complete.
40
415. **Include non-functional expectations**
42 Add criteria for performance, accessibility, security, reliability, or auditability when they matter to the story.
43
446. **Avoid duplication and overlap**
45 Each criterion should test one outcome. If two criteria describe the same behavior, merge or split them until the intent is clear.
46
477. **Review for testability**
48 Ensure a reviewer can pass or fail each criterion without interpretation. If a statement is subjective, rewrite it into a measurable outcome.
49
50## Output Contract
51
52Use `references/TEMPLATE.md` as the output format. A complete response should:
53
54- Restate the feature or story context
55- Group criteria into happy path, edge cases, error states, and non-functional criteria
56- Use explicit Given/When/Then statements for each criterion
57- Note assumptions or open questions when context is incomplete
58
59## Quality Checklist
60
61Before finalizing, verify:
62
63- [ ] The criteria map to a specific story or feature slice
64- [ ] The happy path is covered first
65- [ ] Edge cases are explicit, not implied
66- [ ] Error states include user-visible recovery behavior
67- [ ] Non-functional criteria are included when relevant
68- [ ] Each criterion is testable and has one clear outcome
69- [ ] No implementation details leak into the acceptance criteria
70
71## Examples
72
73See `references/EXAMPLE.md` for a completed example based on a realistic e-commerce checkout flow.