SkillAgentSearch skills...

verification-before-completion

在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言

Install / Use

npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion

Installs into whichever agent you are using.

About this skill
📄

SKILL.md

Installable skill definition

Quality Score

83/100

Supported Platforms

Universal

Tags

Our assessment of verification-before-completion

verification-before-completion scores 83/100 on our quality scale, 914th of 2,185 Development & Engineering skills we index (top 42%).

Its SKILL.md is 1.7 KB long, well organised into 9 sections with 7 code examples: moderately detailed.

With 8,211 GitHub stars, it is one of the more widely adopted skills in the catalogue.

Substance
20/30
Structure
20/20
Description
12/15
Adoption
17/20
Freshness
15/15

Maintenance, license and trust

  • The repository was last updated 9 days ago, so verification-before-completion is actively maintained.
  • It is released under the MIT license, a permissive license that allows use, modification and commercial use with attribution.
  • Its trust signals score 100/100, with no cautions. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

verification-before-completion compared with similar skills

All 4 of these similar skills score higher than verification-before-completion; compare them before choosing.

SkillScoreStarsUpdatedFormat
verification-before-completion (this skill)by jnMetaCode838.2k9d agoSKILL.md
ai-job-searchby MadsLorentzen10044.0k5d agoCLAUDE.md
claude-howtoby luongnv8910041.7ktodayCLAUDE.md
algorithmic-artby anthropics100177.9k4d agoSKILL.md
pptxby anthropics100177.9k4d agoSKILL.md

Frequently asked questions

How do I install verification-before-completion?
Run npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion. The install tabs above show the steps for each supported agent.
Which AI agents does verification-before-completion work with?
It is written for Universal, as a SKILL.md file. Other agents that read the same format can often use it too.
Is verification-before-completion safe to use?
It is MIT-licensed and scores 100/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is verification-before-completion still maintained?
The repository was last updated 9 days ago, so verification-before-completion is actively maintained.

name: verification-before-completion description: 在宣称工作完成、已修复或测试通过之前使用,在提交或创建 PR 之前——必须运行验证命令并确认输出后才能声称成功;始终用证据支撑断言 version: "1.0.0" license: MIT metadata: hermes: tags: [quality, verification]

完成前验证

概述

核心原则: 始终用证据支撑结论。

对这条规则敷衍了事,就等于违背了它的精神。

铁律

没有新鲜的验证证据,不许宣称完成

如果你在这条消息中没有运行验证命令,就不能声称测试通过。

门控函数

在宣称任何状态或表达满意之前:

1. 确定:什么命令能证明这个结论?
2. 运行:执行完整命令(重新运行,完整执行)
3. 阅读:完整输出,检查退出码,统计失败数
4. 验证:输出是否支持这个结论?
   - 如果否:用证据说明实际状态
   - 如果是:带证据陈述结论
5. 只有这时:才能做出结论

跳过任何一步 = 说谎,不是验证

常见失败模式

| 结论 | 需要 | 不够格 | |------|------|--------| | 测试通过 | 测试命令输出:0 failures | 之前的运行结果、"应该会通过" | | Linter 无报错 | Linter 输出:0 errors | 部分检查、推断 | | 构建成功 | 构建命令:exit 0 | linter 通过、日志看起来没问题 | | Bug 已修复 | 测试原始症状:通过 | 代码改了,假设已修复 | | 回归测试有效 | 红-绿循环已验证 | 测试只通过了一次 | | 代理已完成 | VCS diff 显示变更 | 代理报告"成功" | | 需求已满足 | 逐项核对清单 | 测试通过 |

红线——停下来

  • 使用"应该"、"大概"、"似乎"
  • 验证前就表达满意("太好了!"、"完美!"、"搞定!"等)
  • 即将提交/推送/创建 PR 却没有验证
  • 信任代理的成功报告
  • 依赖部分验证
  • 想着"就这一次"
  • 累了想赶紧收工
  • 任何暗示成功但实际未运行验证的措辞

防止合理化

| 借口 | 现实 | |------|------| | "应该能行了" | 运行验证命令 | | "我有信心" | 信心 ≠ 证据 | | "就这一次" | 没有例外 | | "Linter 通过了" | Linter ≠ 编译器 | | "代理说成功了" | 独立验证 | | "我累了" | 疲劳 ≠ 借口 | | "部分检查就够了" | 部分检查什么也证明不了 | | "换个说法这条规则就不适用了" | 精神大于字面 |

关键模式

测试:

✅ [运行测试命令] [看到:34/34 pass] "全部测试通过"
❌ "应该能通过了" / "看起来对了"

回归测试(TDD 红-绿):

✅ 编写 → 运行(通过)→ 回退修复 → 运行(必须失败)→ 恢复 → 运行(通过)
❌ "我写了回归测试"(没有经过红-绿验证)

构建:

✅ [运行构建] [看到:exit 0] "构建通过"
❌ "Linter 通过了"(linter 不检查编译)

需求:

✅ 重读计划 → 创建核对清单 → 逐项验证 → 报告缺口或完成
❌ "测试通过了,阶段完成"

代理委派:

✅ 代理报告成功 → 检查 VCS diff → 验证变更 → 报告实际状态
❌ 信任代理报告

何时使用

以下情况之前必须使用:

  • 任何形式的成功/完成声明
  • 任何满意的表达
  • 任何关于工作状态的正面陈述
  • 提交、创建 PR、标记任务完成
  • 进入下一个任务
  • 委派给代理

本规则适用于:

  • 准确措辞
  • 同义词和换一种说法
  • 暗示成功
  • 任何传达完成/正确性的沟通

Related Skills

View on GitHub
GitHub Stars8.2k
CategoryDevelopment
Updated9d ago
Forks767

Languages

JavaScript

Trust signals

100/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

No cautions