Creates risk-based test plans and strategies. Use when planning testing, defining test scope, or documenting QA approach.
/plugin marketplace add jkappers/claude-code-software-delivery-plugin/plugin install jkappers-software-delivery-pack-claude@jkappers/claude-code-software-delivery-pluginThis skill inherits all available tools. When active, it can use any tool Claude has access to.
Create practical, risk-based test plans.
Small feature: One-page plan (scope, risks, approach). Large feature: Full plan with all sections. Ask "Does the reader need this?" for every section.
| Risk/Impact | High Impact | Low Impact |
|---|---|---|
| High Risk | Test thoroughly | Test defensively |
| Low Risk | Test key paths | Minimal testing |
/ E2E \ Few, slow, expensive
/ Integ. \ Some, moderate
/ Unit \ Many, fast, cheap
Overview - Feature under test, objectives, link to spec
Scope - In scope (what tested), Out of scope (what not, and why)
Test Strategy - Test types, approach per component, automation decisions
Risk Assessment - Identified risks, severity, mitigation, attention areas
Test Cases - Organized by feature, priority (P0/P1/P2), happy path and edge cases
Environment & Data - Test environments, data requirements, dependencies
Entry/Exit Criteria - When testing starts, when testing is complete
### TC-001: [Description]
**Priority**: P0 | P1 | P2
**Type**: Unit | Integration | E2E | Manual
**Preconditions**:
- [Required state]
**Steps**:
1. [Action]
**Expected Result**:
- [Outcome]
**Edge Cases**:
- [Variations]
| Priority | Description | Coverage |
|---|---|---|
| P0 | Critical path, must work | 100% automated |
| P1 | Important functionality | Mostly automated |
| P2 | Edge cases | Manual or deferred |
| Type | Purpose | When |
|---|---|---|
| Unit | Isolated functions | Business logic, utilities |
| Integration | Component interactions | APIs, database, services |
| E2E | Complete user flows | Critical journeys |
| Manual | Exploratory, UX | Complex UI, accessibility |
Link tests to requirements. Prefer automation. Test behavior, not implementation. Keep tests simple.
Do not test implementation details. Do not target 100% coverage as a goal. Do not create flaky tests. Do not rely on specific timing or order. Do not mock everything.
Use templates/test-plan.md for new plans.
Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.
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.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.