Back to Details

principle-prove-it-works

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Prove It Works

验证成果有效性

Verify every task output by checking the real thing directly. Do not infer from proxies, self-reports, or "it compiles."
Why: Unverified work has unknown correctness. Indirect verification (file mtimes, output freshness, agent self-reports, cached screenshots) feels cheaper than direct observation. Acting on a wrong inference costs far more than checking the source.
Pattern: After completing any task, ask: "how do I prove this actually works?"
Check the real thing, not a proxy:
  • Check process liveness directly, not indirectly through derived state
  • Read the actual value, not a cached or derived representation
  • When verification fails, suspect the observation method before suspecting the system
Code and features:
  1. Build it (necessary but not sufficient)
  2. Run it and exercise the actual feature path
  3. Check the full chain: does data flow from input to output?
  4. For integrations, test the full communication path end-to-end
Delegation: trust artifacts, not self-reports. When verifying delegated work, inspect the actual output artifact (git diff, file contents, runtime behavior), not the delegate's summary. Agents report what they intended, not always what happened.
直接检查真实产物来验证所有任务输出。不要通过代理指标、自我报告或“代码能编译”来推断结果。
原因： 未经验证的工作其正确性未知。间接验证（文件修改时间、输出新鲜度、Agent自我报告、缓存截图）看似比直接观察成本更低，但基于错误推断采取行动的代价远高于直接检查源头。
模式： 完成任何任务后，问自己：“我该如何证明这确实有效？”
检查真实产物，而非代理指标：
  • 直接检查进程是否存活，而非通过派生状态间接判断
  • 读取实际数值，而非缓存或派生的表示形式
  • 当验证失败时，先怀疑观察方法，再怀疑系统本身
代码与功能验证步骤：
  1. 构建代码（必要但不充分）
  2. 运行代码并实际执行功能路径
  3. 检查完整链路：数据是否能从输入流转到输出？
  4. 对于集成工作，端到端测试完整的通信路径
任务委托：信任产物，而非自我报告。 验证委托工作时，检查实际输出产物（git diff、文件内容、运行时行为），而非受托方的总结。Agent会报告他们的预期结果，但实际情况未必总是如此。

Script the check when you can

尽可能将验证过程脚本化

The strongest proof is a deterministic script that re-runs the same comparison, not a one-time eyeball. Write the script, run it, and keep its output as an artifact a reviewer can re-run instead of trusting your word. A script comparing the old and new compiled output catches what a glance misses.
Keep the artifact visible for the human. Commit it only for large or complex work where the trail has to be auditable later, like a big port or migration (the show-me-your-work skill). Most work just needs it visible, not committed.
最有力的验证方式是使用确定性脚本重复执行相同的对比，而非一次性人工检查。编写脚本、运行脚本，并将其输出作为评审人员可重新运行的产物，而非依赖你的口头说明。对比新旧编译输出的脚本能发现人工一瞥遗漏的问题。
让产物便于人员查看。仅在大型或复杂工作（如重大移植或迁移）中才提交该产物，以便后续可审计（即“展示工作过程”技能）。大多数工作只需让产物可见，无需提交。