From devflow
Use when designing test suites, generating test cases, or reviewing test coverage — covers unit, integration, and E2E strategies
npx claudepluginhub nexuz-sys/devflow --plugin devflowThis skill uses the workspace's default tool permissions.
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Executes pre-written implementation plans: critically reviews, follows bite-sized steps exactly, runs verifications, tracks progress with checkpoints, uses git worktrees, stops on blockers.
Design and generate comprehensive test suites that catch real bugs and document behavior.
Announce at start: "I'm using the devflow:test-generation skill."
/ E2E \ Few, slow, expensive — critical user flows only
/----------\
/ Integration \ Moderate — component boundaries, API contracts
/----------------\
/ Unit Tests \ Many, fast, cheap — business logic, pure functions
/____________________\
describe("<Subject>")
it("should <expected behavior> when <condition>")
Given: <setup/preconditions>
When: <action>
Then: <assertion>
describe("UserRegistration")
// Happy path
it("should create user with valid email and password")
it("should hash password before storing")
it("should return user ID and email (not password)")
// Edge cases
it("should trim whitespace from email")
it("should accept emails with + and . variants")
it("should accept unicode names")
// Error paths
it("should reject duplicate email with 409")
it("should reject password shorter than 8 chars")
it("should reject invalid email format")
it("should reject missing required fields with 400")
// Integration
it("should send welcome email after creation")
it("should create default settings for new user")
| Test Type | Use For | Mock? |
|---|---|---|
| Unit | Pure functions, business logic, utilities | Mock external deps |
| Integration | API endpoints, DB queries, service interactions | Real DB, mock external APIs |
| E2E | Critical user flows (login, checkout, signup) | Nothing mocked |
| Snapshot | UI component rendering (use sparingly) | N/A |
TDD iron law applies: superpowers:test-driven-development
agent({ action: "orchestrate", agents: ["test-writer"], task: "<description>" })
skill({ action: "getContent", skill: "test-generation" })
Read .context/agents/test-writer.md and .context/skills/test-generation/SKILL.md.
Read .context/docs/testing-strategy.md for project-specific test conventions.
| Pattern | Problem |
|---|---|
| Testing implementation, not behavior | Tests break on refactoring |
| 100% coverage as a goal | Coverage measures lines hit, not bugs caught |
| Tests with shared mutable state | Flaky, order-dependent failures |
expect(result).toBeTruthy() | Asserts nothing useful — be specific |
| Copy-pasting tests with minor changes | Extract parameterized/table-driven tests |
| Only happy-path tests | Bugs cluster at edges and error paths |