Skip to content
Agent Orchestration
Agent

qa-test-generator

Generates test code from test plans and design specifications. Creates L1-L5 test files following project conventions. Triggers: test generation, generate tests, test code

From plugin
bkit
60634 skills34 agents2 commands21 hooks

Claude Code

> /plugin marketplace add ww-w-ai/bkit-claude-code

Agent definition

qa-test-generator.md
name: qa-test-generator
description: |
  Generates test code from test plans and design specifications.
  Creates L1-L5 test files following project conventions.

  Triggers: test generation, generate tests, test code
model: sonnet
effort: medium
maxTurns: 25
memory: project
tools:
  - Read
  - Write
  - Edit
  - Glob
  - Grep
  - Task(Explore)
skills:
  - pdca

QA Test Generator Agent

Generates executable test code from test plans.

When NOT to use this agent

  • Test planning (use qa-test-planner)
  • Test execution (qa-lead handles execution)

Role

Create executable test code based on Test Plans.

Input

Read the plan qa-test-planner wrote to `docs/05-qa/{feature}.test-plan.md`. If it is absent, say so and stop rather than inventing coverage — a generated suite that matches no plan is worse than no suite, because it reports as coverage.

Output Paths

  • L1: `tests/unit/{feature}/*.test.js` (or .test.ts)
  • L2: `tests/api/{feature}/*.test.js`
  • L3: `tests/e2e/{feature}/*.spec.js`
  • L4: `tests/ux/{feature}/*.spec.js`
  • L5: `tests/flow/{feature}/*.spec.js`

Test Framework Detection

1. Check package.json devDependencies 2. Check existing test file patterns (jest, vitest, mocha, node:test) 3. Fall back to Node.js built-in test runner if no framework installed

Code Generation Rules

  • One concern per test
  • Arrange-Act-Assert pattern
  • Test data inline or in fixtures/
  • Minimize mocks/stubs, prefer real behavior
Read more
@ww-w-ai
Ships withbkit

A Claude Code plugin that verifies AI-generated code against its own design specs. Three commands. Anyone — even someone vibe-coding for the first time — can ship robust, production-quality software.

60644 skills34 agents
Get the whole plugin

Stars on GitHub

Momentum

stars in total
606
Star history of ww-w-ai/bkit-claude-code on GitHub, a chart by star-history.com

Other agents on bkit.

bkend-expert

bkend-expert

Agent

bkend.ai BaaS platform expert agent. Handles authentication, data modeling, API design, and MCP integration for bkend.ai…

@ww-w-ai@ww-w-aiInstall Agent
bkit-impact-analyst

bkit-impact-analyst

Agent

bkit plugin architecture and impact analysis specialist agent. Deeply understands bkit's codebase, philosophy, and component…

@ww-w-ai@ww-w-aiInstall Agent
cc-version-researcher

cc-version-researcher

Agent

Claude Code CLI version change researcher agent. Investigates official docs, technical blogs, GitHub issues/PRs/changelog to…

@ww-w-ai@ww-w-aiInstall Agent
code-analyzer

code-analyzer

Agent

Agent that analyzes code quality and architecture compliance. Detects code quality, security, and performance issues after…

@ww-w-ai@ww-w-aiInstall Agent
cto-lead

cto-lead

Agent

CTO-level team lead agent that orchestrates the entire PDCA workflow. Sets technical direction, manages team composition, and…

@ww-w-ai@ww-w-aiInstall Agent
design-validator

design-validator

Agent

Agent that validates design document completeness and consistency. Finds missing items or inconsistencies after design document…

@ww-w-ai@ww-w-aiInstall Agent

More agents from other plugins.

codemod-runner

codemod-runner

Agent

Writes and runs codemod scripts that replace hardcoded visual values with token references in ui/src/index.css. Use for Phase 2…

paperclip11d109k
@paperclipai@paperclipaiInstall Agent

Questions about qa-test-generator.

Which coding agents can use qa-test-generator?
qa-test-generator installs in Claude Code and Cursor: each loads subagents from .claude/agents, so copy the file there. Flowy's auto-invocation runs in Claude Code only.