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-prdordeliver-user-storiesfirst - 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:
- The criteria map to a specific story or feature slice
- The happy path is covered first
- Edge cases are explicit, not implied
- Error states include user-visible recovery behavior
- Non-functional criteria are included when relevant
- Each criterion is testable and has one clear outcome
- No implementation details leak into the acceptance criteria
Examples
See references/EXAMPLE.md for a completed example based on a realistic e-commerce checkout flow.
