agentsclimarketplace

Discipline test is truth

Skill yli769227-jpg/awesome-claude-code-cn/skills/discipline-test-is-truth

Karpathy 教你 LLM 会犯什么错。我教你 LLM 在我这犯了什么错、怎么治。8 条铁律 + 真实反例 + 中文 Claude Code 实战包

Install
npx -y skills add yli769227-jpg/awesome-claude-code-cn --skill discipline-test-is-truth

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

测试即结论 —— 完成的定义不是"代码写完",而是"测试结果可验证"。触发: 即将向用户声明任务完成、即将说"应该没问题"、即将合并 PR、即将关闭 issue、即将派 agent 子任务前。任何完成声明必须附带 ✅/❌/⚠️ 三段式测试结论。

SKILL.md

1.3 KB, as published. Nobody here has run it

二、测试即结论（完成的定义）

工作的结束不是写完代码，而是完成测试。

  1. 代码写完不等于完成，必须有可执行的验证步骤证明功能正确。
  2. 测试必须可证伪，不只是"跑通了"，还要验证错误路径（无效输入、连接断开、超时等）。
  3. 冒烟测试是最低要求，端到端运行一次，观察实际行为，不靠想象。
  4. Agent 完成任务时也必须包含测试，派给 teammate 的任务描述中要明确要求验证步骤。
  5. 结论格式：测试后输出"✅ 通过什么 / ❌ 失败什么 / ⚠️ 未覆盖什么"。
  6. 测你改的，不是测你没改的。测试必须靶向实际变更点。

加载时机

  • 即将向用户说"做完了 / 应该可以了 / 跑通了"
  • 即将 merge PR / close issue
  • 派子 agent 任务时(任务描述必须含验证步骤)
  • 修了 bug 后准备收工

配套

具体反面例子 / 正面例子见 EXAMPLES.md。

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.