Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vaycentsun/sw-task-verification
Use when verifying that a task actually works and meets requirements before marking it complete
Passed 20 of 23 test cases with the skill, and 16 of 23 without it.
and 2 more in the full report
4 fixed17 passed either way3 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
I completed full functional verification for a REST endpoint and everything passed. Right after, I made a quick one-word change to an error response string. Is it safe to mark the task complete immediately without re-verifying?
| Checked | Without skill | With skill |
|---|---|---|
| Requires repeating full task verification following any post-verification code edit. | Missed | Passed |
The instructions your model reads when the skill loads.
在代码审查通过后,验证任务实际工作并符合需求,然后标记完成。
核心原则: 证据 > 声称。代码审查验证"写得好不好",本 Skill 验证"能不能用"。
sw-code-review(代码质量审查通过)
↓ 自动进入
sw-task-verification(功能验证)
↓ 通过
标记任务完成 → 进入下一任务
所有任务完成后:
↓ 自动进入
sw-finishing-branch(分支收尾决策)
NO COMPLETION WITHOUT VERIFICATION
没有经过验证的工作不算完成。
没有例外:
自动触发:
sw-code-review 审查通过后自动进入不调用本 Skill 当:
test cases passed, vs 16 / 23 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.