Agent skill

scenario-testing

This skill should be used when writing tests, validating features, or needing to verify code works. Triggers on "write tests", "add test coverage", "validate feature", "integration test", "end-to-end", "e2e test", "mock", "unit test". Enforces scenario-driven testing with real dependencies in .scratch/ directory.

View SKILL.md on GitHub Repository
Stars 36
Forks 1

Install this agent skill to your Project

npx add-skill https://github.com/2389-research/claude-plugins/tree/main/scenario-testing/skills

SKILL.md

Scenario-Driven Testing for AI Code Generation

Core Principle

The Iron Law: "NO FEATURE IS VALIDATED UNTIL A SCENARIO PASSES WITH REAL DEPENDENCIES"

Mocks create false confidence. Only scenarios exercising real systems validate that code works.

The Truth Hierarchy

  1. Scenario tests (real system, real data) = truth
  2. Unit tests (isolated) = human comfort only
  3. Mocks = lies hiding bugs

As stated in the principle: "A test that uses mocks is not testing your system. It's testing your assumptions about how dependencies behave."

When to Use This Skill

  • Validating new functionality
  • Before declaring work complete
  • When tempted to use mocks
  • After fixing bugs requiring verification
  • Any time you need to prove code works

Required Practices

1. Write Scenarios in .scratch/

  • Use any language appropriate to the task
  • Exercise the real system end-to-end
  • Zero mocks allowed
  • Must be in .gitignore (never commit)

2. Promote Patterns to scenarios.jsonl

  • Extract recurring scenarios as documented specifications
  • One JSON line per scenario
  • Include: name, description, given/when/then, validates
  • This file IS committed

3. Use Real Dependencies

External APIs must hit actual services (sandbox/test mode acceptable). Mocking any dependency invalidates the scenario.

4. Independence Requirement

Each scenario must run standalone without depending on prior executions. This enables:

  • Parallel execution
  • Prevents hidden ordering dependencies
  • Reliable CI/CD integration

What Makes a Scenario Invalid

A scenario is invalid if it:

  • Contains any mocks whatsoever
  • Uses fake data instead of real storage
  • Depends on another scenario running first
  • Never actually executed to verify it passes

Common Violations to Avoid

Reject these rationalizations:

  • "Just a quick unit test..." - Unit tests don't validate features
  • "Too simple for end-to-end..." - Integration breaks simple things
  • "I'll mock for speed..." - Speed doesn't matter if tests lie
  • "I don't have API credentials..." - Ask your human partner for real ones

Definition of Done

A feature is complete only when:

  1. ✅ A scenario in .scratch/ passes with zero mocks
  2. ✅ Real dependencies are exercised
  3. ✅ .scratch/ remains in .gitignore
  4. ✅ Robust patterns extracted to scenarios.jsonl

Example Workflow

  1. Write scenario - Create .scratch/test-user-registration.py
  2. Use real dependencies - Hit real database, real auth service (test mode)
  3. Run and verify - Execute scenario, confirm it passes
  4. Extract pattern - Document in scenarios.jsonl
  5. Keep .scratch ignored - Never commit scratch scenarios

Why This Matters

  • Unit tests verify isolated logic
  • Integration tests verify components work together
  • Scenario tests verify the system actually works

Only scenario tests prove your feature delivers value to users.

Recommended Agent Skills

Expand your agent's capabilities with these related and highly-rated skills.

2389-research/claude-plugins

css-development

This skill should be used when working with CSS, creating components, styling elements, refactoring styles, or reviewing CSS code. Triggers on "CSS", "styles", "Tailwind", "dark mode", "component styling", "semantic class", "@apply", "stylesheet". Routes to specialized sub-skills for creation, validation, or refactoring.

36 1
Explore
2389-research/claude-plugins

css-development:create-component

This skill should be used when creating new styled components or adding new CSS classes. Triggers on "create component", "new button", "new card", "add styles", "style component", "build UI element". Guides semantic naming, Tailwind composition, dark mode support, and test coverage.

36 1
Explore
2389-research/claude-plugins

css-development:refactor

This skill should be used when refactoring existing CSS from inline styles or utility classes to semantic patterns. Triggers on "refactor CSS", "extract styles", "consolidate CSS", "convert inline", "clean up styles", "migrate to semantic". Transforms to semantic classes with dark mode and tests.

36 1
Explore
2389-research/claude-plugins

css-development:validate

This skill should be used when reviewing or auditing existing CSS code for consistency with established patterns. Triggers on "review CSS", "audit styles", "check CSS", "validate stylesheet", "CSS review". Checks semantic naming, dark mode coverage, Tailwind usage, and test coverage.

36 1
Explore
2389-research/claude-plugins

ceo-personal-os

This skill should be used when building a personal productivity or operating system for a CEO, founder, or executive. Triggers on "personal OS", "annual review", "life planning", "goal setting system", "Bill Campbell", "Trillion Dollar Coach", "startup failure patterns", "Good to Great", "Level 5 Leadership", "Buy Back Your Time", "E-Myth", "Customer Development", "Steve Blank", "Small Is Beautiful", "Schumacher", "human-scale", "subsidiarity", "Buddhist economics", "permanence".

36 1
Explore
2389-research/claude-plugins

gtm-partner

Strategic go-to-market partner that recommends channels, validates strategy with the user, and generates only the assets that matter. Use when a user has a validated business idea and needs tailored GTM strategy, not generic marketing assets.

36 1
Explore

Didn't find tool you were looking for?

Be as detailed as possible for better results