deliver-acceptance-criteria

<!-- PM-Skills | https://github.com/product-on-purpose/pm-skills | Apache 2.0 -->

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
• The criterion is a rate over model output, such as "90% of answers are faithful to their sources" -> use the AI Behavior and Evaluation section of deliver-prd, which says a rate needs a designed sample to verify it, and what to record until one exists

Instructions

When asked to create acceptance criteria, follow these steps:

1. 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.

1. 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.

1. Write each criterion as an observable scenario

Use Given/When/Then language only. Keep each criterion independently testable and avoid implementation details.

1. 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.

1. Include non-functional expectations

Add criteria for performance, accessibility, security, reliability, or auditability when they matter to the story.

1. 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.

1. 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.