AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Tdd

skill-blueprintos-analysis-to-delivery-tdd · by BlueprintOS

测试驱动开发(红绿循环)— 来自 superpowers 体系。本 skill 是桥接层,先写失败测试再写实现,完整纪律见 <SUPERPOWERS_SKILL_ROOT>/tdd/。

↗ Repository
— No reviews yet
0 installs
28 views
0.0% view→install

Install

$ agentstack add skill-blueprintos-analysis-to-delivery-tdd

✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

View the full security report →

Verified badge

Passed review? Show it. Paste this badge into your README, it links to the public security report.

AgentStack Verified badge Links to your public security report.
[![AgentStack Verified](https://agentstack.voostack.com/badges/verified.svg)](https://agentstack.voostack.com/security/report/skill-blueprintos-analysis-to-delivery-tdd)

Reliability & compatibility

✓ Security review passed
0 installs to date
— no reviews yet
● 2mo ago

Declared compatibility

Claude CodeClaude Desktop

Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.

Preview Execution monitoring

We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.

How agent discovery & health will work →
Are you the author of Tdd? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

TDD(桥接到 superpowers)

Contract

  • Inputs: executable task from writing plan, test target, acceptance criteria
  • Outputs: RED test, GREEN implementation, refactor notes
  • Gates: RED observed before implementation; GREEN observed after implementation
  • Required disciplines: stage-gate
  • Next: /executing-plans

> 本仓库不维护此 skill 的内容。完整纪律请读: > /tdd/SKILL.md

何时调

  • writing-plans 之后
  • 每个子任务开始时(红绿循环)

衔接点

  • 产出:RED 测试 + GREEN 实现 + REFACTOR
  • 下一步:/executing-plans(commit + 下一任务)
  • 门控:disciplines/stage-gate 第 3 层(RED 必须确认失败才能写实现)

降级方案(superpowers 未装时)

如果 /tdd/ 不存在,严格按以下 4 步红绿循环:

1. RED — 写失败测试

  • 在 src/test/ 写测试,只测一个最小行为
  • 跑测试 → 必须确认失败(看到红色 / FAILURE,不是 BUILD SUCCESS)
  • ❌ 跳过 RED = 你不知道测试到底在测什么

2. 最小实现

  • 写最少量代码让测试通过(可以丑 / 可以硬编码)
  • 不优化、不重构、不扩展

3. GREEN — 跑通

  • 再跑测试 → 必须确认通过(看到 BUILD SUCCESS / PASSED)
  • ❌ 测试莫名通过 = 测试没断言你想要的东西

4. REFACTOR — 重构

  • 改进实现 / 抽取方法 / 命名优化
  • 每次重构后必须重跑测试确认仍 GREEN
  • 改完再跑 = 唯一能防止重构破坏功能的方法

最小纪律摘要

  • RED 必须亲眼看到失败:写测试 → 跑 → 看 stack trace → 才写实现
  • GREEN 后才能 REFACTOR:实现未通过前重构 = 在错的地基上盖楼
  • 测试一次只测一个行为:堆叠断言 = 失败时不知道哪个挂了
  • 不 mock 你要测的东西:只 mock 边界 IO

安装提示

npx skills@latest add obra/superpowers-tdd

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet, be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in AI & ML