tdd-qa — for Claude Code tdd-qa, community, for Claude Code, ide skills, mocking-guidelines.md, interface-design.md, write-scenarios, tdd-cycle, backtest, mutation-check

v1.0.0
GitHub

关于此技能

适用场景： Perfect for Development Agents needing automated testing workflows with TDD and regression testing capabilities. 本地化技能摘要： Boundary: CORE/testing-guide.md = philosophy (always loaded). This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

功能特性

Workflow Routing (SYSTEM PROMPT)
Set up testing: "set up testing", "init testing", "bootstrap test infra"
- READ: ${PAI DIR}/skills/tdd-qa/workflows/init-project.md
- EXECUTE: Copy templates, create specs/ dir, configure bunfig.toml
Define test scenarios: "write scenarios for X", "define test cases", "spec out the feature"

# 核心主题

for Claude Code mocking-guidelines.md interface-design.md write-scenarios tdd-cycle backtest
multicam multicam
[2]
[0]
更新于: 3/28/2026

技能概览

先看适用场景、限制条件和安装路径，再决定是否继续深入。

适用场景： Perfect for Development Agents needing automated testing workflows with TDD and regression testing capabilities. 本地化技能摘要： Boundary: CORE/testing-guide.md = philosophy (always loaded). This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

核心价值

推荐说明： Empowers agents to automate testing workflows using file system-based context management, supporting RED→GREEN→REFACTOR cycles, and regression testing with JUnit XML baselines, enforcing quality gates and providing mutation score analysis with StrykerJS.

适用 Agent 类型

适用场景： Perfect for Development Agents needing automated testing workflows with TDD and regression testing capabilities.

↓ 赋予的主要能力 · tdd-qa

适用任务： Automating TDD cycles for new feature development
适用任务： Running test pyramids for comprehensive test coverage
适用任务： Debugging regressions with backtesting and quality gate enforcement
适用任务： Verifying E2E browser functionality with devtools-mcp
适用任务： Analyzing test effectiveness with mutation testing

! 使用限制与门槛

  • 限制说明： Requires project initialization with 'init-project' workflow
  • 限制说明： Limited to supporting TDD and regression testing workflows
  • 限制说明： Dependent on specific file formats like JUnit XML for baselining

关于来源内容

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

实验室 Demo

Browser Sandbox Environment

⚡️ Ready to unleash?

Experience this Agent in a zero-setup browser environment powered by WebContainers. No installation required.

Boot Container Sandbox

常见问题与安装步骤

以下问题与步骤与页面结构化数据保持一致，便于搜索引擎理解页面内容。

? FAQ

tdd-qa 是什么？

适用场景： Perfect for Development Agents needing automated testing workflows with TDD and regression testing capabilities. 本地化技能摘要： Boundary: CORE/testing-guide.md = philosophy (always loaded). This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

如何安装 tdd-qa？

运行命令：npx killer-skills add multicam/qara。支持 Cursor、Windsurf、VS Code、Claude Code 等 19+ IDE/Agent。

tdd-qa 适用于哪些场景？

典型场景包括：适用任务： Automating TDD cycles for new feature development、适用任务： Running test pyramids for comprehensive test coverage、适用任务： Debugging regressions with backtesting and quality gate enforcement、适用任务： Verifying E2E browser functionality with devtools-mcp、适用任务： Analyzing test effectiveness with mutation testing。

tdd-qa 支持哪些 IDE 或 Agent？

该技能兼容 Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer。可使用 Killer-Skills CLI 一条命令通用安装。

tdd-qa 有哪些限制？

限制说明： Requires project initialization with 'init-project' workflow；限制说明： Limited to supporting TDD and regression testing workflows；限制说明： Dependent on specific file formats like JUnit XML for baselining。

↓ 安装步骤

  1. 1. 打开终端

    在你的项目目录中打开终端或命令行。

  2. 2. 执行安装命令

    运行：npx killer-skills add multicam/qara。CLI 会自动识别 IDE 或 AI Agent 并完成配置。

  3. 3. 开始使用技能

    tdd-qa 已启用，可立即在当前项目中调用。

! 来源说明

此页面仍可作为安装与查阅参考。继续使用前，请结合上方适用场景、限制条件和上游仓库说明一起判断。

Upstream Repository Material

The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.

Upstream Source

tdd-qa

本地化技能摘要： Boundary: CORE/testing-guide.md = philosophy (always loaded). This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

SKILL.md
Readonly
Upstream Repository Material
The section below comes from the upstream repository. Use it as supporting material alongside the fit, use-case, and installation summary on this page.
Upstream Source

Workflow Routing (SYSTEM PROMPT)

Set up testing: "set up testing", "init testing", "bootstrap test infra" -> READ: ${PAI_DIR}/skills/tdd-qa/workflows/init-project.md -> EXECUTE: Copy templates, create specs/ dir, configure bunfig.toml

Define test scenarios: "write scenarios for X", "define test cases", "spec out the feature" -> READ: ${PAI_DIR}/skills/tdd-qa/workflows/write-scenarios.md -> EXECUTE: Create Given/When/Then specs from requirements

Run a TDD cycle: "run TDD on X", "red green refactor", "TDD this feature" -> READ: ${PAI_DIR}/skills/tdd-qa/workflows/tdd-cycle.md -> EXECUTE: RED→GREEN→VERIFY loop with 2-retry escalation

Run test pyramid: "run the pyramid", "run all test layers", "full test suite" -> READ: ${PAI_DIR}/skills/tdd-qa/workflows/run-pyramid.md -> EXECUTE: Static→Unit→Integration→E2E in sequence

Check for regressions: "backtest", "check regressions", "compare test results", "quality gate" -> READ: ${PAI_DIR}/skills/tdd-qa/workflows/backtest.md -> EXECUTE: Compare JUnit XML baselines, check coverage delta, enforce gates

E2E browser verification: "verify E2E", "browser test", "e2e scenarios", "smoke test the UI" -> READ: ${PAI_DIR}/skills/tdd-qa/workflows/e2e-verify.md -> EXECUTE: Run scenarios via devtools-mcp, auto-draft .spec.ts

Mutation testing: "run mutation tests", "check mutation score", "how good are my tests" -> READ: ${PAI_DIR}/skills/tdd-qa/workflows/mutation-check.md -> EXECUTE: Run StrykerJS, report mutation score (advisory)

Philosophy/patterns/mocking: Not in this skill — see CORE testing-guide.md, mocking-guidelines.md, interface-design.md.

Boundary: CORE/testing-guide.md = philosophy (always loaded). This skill = executable blueprints (on-demand fork context).

Usage Modes

ModeFlow
New featurewrite-scenarios -> tdd-cycle -> backtest
Bug fixtriage-issue -> fix -> backtest
Confidencebacktest or run-pyramid
New projectinit-project (once)

Workflow steps are typed deterministic or agentic (Stripe Minions pattern). See references/blueprint-pattern.md.

Bombadil (v0.3.2) is experimental — invoke explicitly, not routed by default. → READ: workflows/explore-bombadil.md when user asks for Bombadil exploration.

Lifecycle Completion

Minimum Complete Cycle

  1. write-scenarios — Given/When/Then specs (mandatory human review gate at step 4)
  2. tdd-cycle — RED→GREEN→REFACTOR for each scenario
  3. backtest — regression check, baseline update

Complete when backtest passes with zero regressions and baseline updated.

Optional Extensions

ExtensionWhen to suggestPrerequisite
mutation-checkAfter backtest passes, for critical code pathsStrykerJS installed
e2e-verifyWhen feature has a browser UIdevtools-mcp available
run-pyramidBefore merging a PR, as final confidence checkTests exist at multiple layers

System-Level "Done"

A feature is fully tested when:

  • All quality gates pass (zero regressions, coverage not decreased)
  • Baseline updated
  • JM has reviewed and approved scenarios

Do not proactively run optional extensions unless JM asks or the feature touches critical code paths.

Composing Workflows

Canonical Sequences

Request typeSequenceSkippable steps
New featurewrite-scenarios → tdd-cycle → backtestwrite-scenarios skippable if JM provides inline requirements
Bug fixtdd-cycle (RED: failing test for bug) → backtestwrite-scenarios usually skipped for single bugs
Confidence checkbacktest or run-pyramidBoth standalone
Refactoringbacktest (before) → refactor → backtest (after)No TDD cycle — existing tests are the safety net

Ambiguous Requests

If a request spans multiple workflows, ask which workflow to start with rather than guessing. Example: "add auth and make sure nothing breaks" could mean write-scenarios + tdd-cycle + backtest, or just a confidence backtest on existing code.

相关技能

寻找 tdd-qa 的替代方案 (Alternative) 或可搭配使用的同类 community Skill？探索以下相关开源技能。

查看全部

openclaw-release-maintainer

Logo of openclaw
openclaw

本地化技能摘要： 🦞 # OpenClaw Release Maintainer Use this skill for release and publish-time workflow. It covers ai, assistant, crustacean workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 333.8k
⑂ 0
AI

widget-generator

Logo of f
f

本地化技能摘要： Generate customizable widget plugins for the prompts.chat feed system # Widget Generator Skill This skill guides creation of widget plugins for prompts.chat . It covers ai, artificial-intelligence, awesome-list workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf

★ 149.6k
⑂ 0
AI

flags

Logo of vercel
vercel

本地化技能摘要： The React Framework # Feature Flags Use this skill when adding or changing framework feature flags in Next.js internals. It covers blog, browser, compiler workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 138.4k
⑂ 0
浏览器

pr-review

Logo of pytorch
pytorch

本地化技能摘要： Usage Modes No Argument If the user invokes /pr-review with no arguments, do not perform a review . It covers autograd, deep-learning, gpu workflows. This AI agent skill supports Claude Code, Cursor, and Windsurf workflows.

★ 98.6k
⑂ 0
开发者工具