QualityJavaScript

Verification Before Completion

by jnMetaCode

Verification Before Completion is a Quality skill for Claude Code, published by jnMetaCode in superpowers-zh.

7.7K stars729 forkson jnMetaCode/superpowers-zhAdded 2026/08/15Repository updated 2026/08/12
agent-skillsagentic-codingai-codingchineseclaude-codecode-reviewcursorgemini-clikiromcpnpm-packageprompt-engineeringskillssuperpowerstddtrae
Install in seconds
Install Verification Before Completion
Copy Verification Before Completion into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completion ~/.claude/skills/verification-before-completion

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/jnMetaCode/superpowers-zh.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
skills/verification-before-completion/SKILL.md in jnMetaCode/superpowers-zh
Installs to
~/.claude/skills/verification-before-completion
Collection
One of 20 skills cataloged from this repository
Category
Quality1354 skills

What Verification Before Completion does

Verification Before Completion enforces running verification commands and checking output before claiming tests pass, builds succeed, or bugs are fixed. It prevents false success claims by requiring evidence for every assertion.

Verification Before Completion is cataloged under Quality on DirSkills. Verification Before Completion comes from a repository tagged agent-skills, agentic-coding, ai-coding, chinese and claude-code.

Documentation

README

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

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Verification Before Completion

  • What else does jnMetaCode publish alongside Verification Before Completion?

    Verification Before Completion is one of 20 skills that DirSkills catalogs from jnMetaCode/superpowers-zh, the repository it ships in. Its siblings there include Brainstorming, Chinese Code Review and Chinese Commit Conventions. Each one is a separate skill with its own page in this directory, installs the same way Verification Before Completion does, and is maintained by jnMetaCode in that same repository. The rest of the collection is listed on the jnMetaCode/superpowers-zh page.

  • How does Verification Before Completion compare to other Quality skills?

    Verification Before Completion ranks #239 by stars among the 1354 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Verification Before Completion against them. Open each page to compare what they document and how they install.

More from jnMetaCode/superpowers-zh

Verification Before Completion is one of 20 skills cataloged on DirSkills from jnMetaCode/superpowers-zh.

See all 20 skills
💡
2w ago

Brainstorming

Brainstorming turns ideas into design specifications through collaborative questioning before any implementation work. Use it before creating features, building components, adding functionality, or modifying behavior to explore user intent, requirements, and design.
AI Engineering
7.7K729
💬
2w ago

Chinese Code Review

Chinese Code Review provides communication templates and priority labels (must-fix/suggest/for-reference) for giving code review feedback in Chinese teams, avoiding over-politeness or bluntness. Use when explicitly invoked via /chinese-code-review to conduct or guide a code review.
Quality
7.7K729
📝
2w ago

Chinese Commit Conventions

Chinese Commit Conventions adapts Conventional Commits for Chinese teams with type tables, commit message templates, breaking change rules, issue linking, and changelog generation configs. Use it to set up commitlint, husky, and commitizen for Chinese-language commit workflows.
Quality
7.7K729
📝
2w ago

Chinese Documentation

Chinese Documentation provides a style guide for Chinese technical documentation, covering spacing, punctuation, terminology, and bilingual API doc formats. Use it when a user explicitly invokes /chinese-documentation to improve the readability and consistency of Chinese technical writing.
Writing
7.7K729
🔧
2w ago

Chinese Git Workflow

Chinese Git Workflow documents configuration differences for Gitee, Coding.net, Jihu GitLab, and CNB, covering SSH/HTTPS credentials, remote mirror sync, and CI/CD integration. Use it when setting up or standardizing Git workflows for teams in China.
DevOps
7.7K729
🤖
2w ago

Dispatching Parallel Agents

Dispatching Parallel Agents delegates independent debugging tasks to parallel subagents with isolated contexts, so each can work on a separate problem without interference. Use it when multiple unrelated test failures or subsystem issues can be investigated concurrently.
AI Engineering
7.7K729