Delegate independent tasks to specialized agents working concurrently with isolated context.
Acceptance Criteria
aico-pm-acceptance-criteria
Define clear, testable acceptance criteria using Given/When/Then (Gherkin) format that can be directly used for testing. Use this skill when: - User asks for "acceptance criteria", "AC", "test criteria", "done criteria" - User asks "how do we know it's done?", "what counts as complete?" - User s...
SKILL.md
Full skill instructions
Acceptance Criteria
⚠️ CRITICAL RULES - READ FIRST
- READ STORY FIRST: Always read the story file from
docs/reference/pm/stories/before writing criteria - USE GIVEN/WHEN/THEN: All criteria must follow this format
- UPDATE STORY FILE: Add criteria to existing story file, don't create new files
Language Configuration
Before generating any content, check aico.json in project root for language field to determine the output language. If not set, default to English.
Process
- Review story/feature: Understand what needs to be done
- Identify success scenarios: Happy paths first
- Write Given/When/Then: For each scenario
- Add edge cases: Boundary conditions and errors
- Verify testability: Each criterion must be independently verifiable
Acceptance Criteria Template
### Acceptance Criteria for [Story/Feature]
#### Scenario 1: [Scenario Name]
- **Given** [precondition/context]
- **When** [action/trigger]
- **Then** [expected outcome]
#### Scenario 2: [Scenario Name]
- **Given** [precondition/context]
- **When** [action/trigger]
- **Then** [expected outcome]
#### Edge Cases
- **Given** [edge case condition]
- **When** [action]
- **Then** [expected behavior]
Criteria Categories
| Category | Examples |
|---|---|
| Functional | Feature works as specified |
| Validation | Input validation rules |
| Error handling | Error messages and recovery |
| Performance | Response time expectations |
| Accessibility | A11y requirements |
Quality Checklist
- Each criterion is independently testable
- No ambiguous language ("should", "might", "could")
- Edge cases are covered
- Error states are defined
- Performance expectations stated (if relevant)
Key Rules
- ALWAYS use Given/When/Then structure
- MUST make each criterion independently testable
- ALWAYS include edge cases and error scenarios
- NEVER use vague language - be specific
Common Mistakes
- ❌ Vague criteria ("works correctly") → ✅ Specific conditions
- ❌ Missing edge cases → ✅ Include boundary conditions
- ❌ Implementation details → ✅ Focus on observable behavior
More Other skills
brand-guidelines
Applies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply.
theme-factory
Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.
internal-comms
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Fundamental design principles for writing maintainable, testable Python code.
responsive-design
Modern responsive layouts using container queries, fluid typography, CSS Grid, and mobile-first strategies.
Generate Playwright tests from scenarios using interactive browser exploration and validation.
Automated website exploration and test case generation using Playwright.
Modern React state management with Redux Toolkit, Zustand, Jotai, and React Query for every state category.
gdpr-data-handling
GDPR-compliant data handling with consent management, data subject rights, and privacy controls.
Python error handling patterns including input validation, exception hierarchies, and partial failure handling. Use when implementing validation logic, designing exception strategies, handling batch processing failures, or building robust APIs.
refactor-plan
Detailed multi-file refactor planning with safety checks and rollback guidance.
