Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jnmetacode/test-driven-development
在实现任何功能或修复 bug 时使用，在编写实现代码之前
Passed 21 of 24 test cases with the skill, and 8 of 24 without it.
and 15 more in the full report
13 fixed8 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.6-flash on 10/2/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 13 test cases the skill fixed. Same model, same prompt, with and without the skill.
We are adding a feature to retry failed network requests. After getting a green test for retrying 3 times, what exact verification must we perform before declaring the Green step complete?
| Checked | Without skill | With skill |
|---|---|---|
| Requires running the entire test suite to verify no regressions occurred after making the test pass. | Passed | Passed |
| Requires confirming that test output is clean with no warnings or console errors. | Missed | Passed |
The instructions your model reads when the skill loads.
先写测试。看它失败。写最少的代码让它通过。
核心原则： 如果你没有看到测试失败，你就不知道它是否测试了正确的东西。
违反规则的字面意思就是违反规则的精神。
始终使用：
例外（需询问你的人类伙伴）：
想着"就这一次跳过 TDD"？停下来。那是在给自己找借口。
没有失败的测试，就不写生产代码
先写了代码再写测试？删掉它。从头来过。
没有例外：
从测试出发，重新实现。句号。
test cases passed, vs 8 / 24 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.