Test Writing — Testing & QA agent for Claude Code
读 confirmed cases.md + flow.md,生成测试代码 + 数据,跑 compliance 轻扫(阶段1)→ 用户裁决偏差后自跑自修 ≤3 轮并结算解构债(阶段2),产出 impl.md.
How to install Test Writing
Installs to ~/.claude/agents/569270901-claude-web-test-harness-test-writing.md
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/569270901/claude-web-test-harness/HEAD/.claude/agents/test-writing.md -o ~/.claude/agents/569270901-claude-web-test-harness-test-writing.md Restart Claude Code, or start a new session, for it to be picked up.
What Test Writing does
name: test-writing description: 读 confirmed cases.md + flow.md,生成测试代码 + 数据,跑 compliance 轻扫(阶段1)→ 用户裁决偏差后自跑自修 ≤3 轮并结算解构债(阶段2),产出 impl.md。由 orchestrator 分两次派发。
你是本项目多 agent 编排的 **test-writing agent**,现在以**独立 context 子 agent** 运行。
隔离须知(必读)
- 你不共享 orchestrator 的对话记忆。cases.md / flow.md / page_map / 知识库你自己读。
- 你不能派发其他子 agent——这意味着你不再自己调 review。你的职责到「写完代码 + compliance 轻扫 + 自跑自修 + 写 impl.md」为止;review 由 orchestrator 在你返回后单独派发 (前置轻闸=你跑 compliance scan,后置重闸=orchestrator 派
Alternatives in Testing & QA
- Claude Code Flow — by ruvnet - This mode serves as a code-first orchestration layer, enabling Claude to write, edit, test, and op 22.2k ★
- Lens Reviewer — Use this agent for severity-rated code review with 2-stage protocol (spec compliance first, then code quality) 523 ★
- Spec Compliance Judge — Use this agent when you need to determine whether a solution correctly implements a specific part of a specifi 173 ★
Full documentation available on GitHub
View Source RepositoryRelated Agents
Test Case Design
两阶段。阶段1=解构:读需求 + UI设计图 + page_map + 知识库,产出 decomp.md(7 张结构化表,GATE 0 人审)。阶段2=生成:读 confirmed decomp.md 查表映射出 cas
Post Merge QA
Post-merge QA on develop or develop- . Confirmed scope, environment preflight, flow/UX exercise, optional desi
QA Strategist
Use this agent for read-only test-coverage gap analysis between waves. Identifies missing boundary cases, erro
ADR Archaeologist
Reducer subagent. Reads every per-node sidecar's implicit_adrs block + bugs_limitations_corner_cases, applies
Voice Specialist
Defines the voice register, tense, point-of-view, and authorial stance for a scribe writing run. Reads the per
Scenario Griller
Brainstorms API test scenarios for a repo interactively (category by category, happy path first, then top edge
Related Skills
MCP Test
Run MCP protocol compliance tests — 39 tests across protocol, tools, resources, prompts, edge cases, and secur
Test Plan Flow
A workflow for turning a tracker issue into reviewed manual test cases — review depth decided by criticality t
Test Cases
Use when writing test cases, generating tests, supplementing test coverage, or improving test completeness — a