Verify and Stop
JuliusBrussee/caveman
Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile…
Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output.
SKILL.md written in Chinese; this summary is our English description.
Install Verification Before Completion
$ npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install jnMetaCode/superpowers-zh verification-before-completion --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/verification-before-completion .claude/skills/verification-before-completion && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "verification-before-completion" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completion into .claude/skills/verification-before-completion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verification-before-completion", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completionType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install jnMetaCode/superpowers-zh verification-before-completion --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/verification-before-completion .agents/skills/verification-before-completion && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "verification-before-completion" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completion into .agents/skills/verification-before-completion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verification-before-completion", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install jnMetaCode/superpowers-zh verification-before-completion --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/verification-before-completion .cursor/skills/verification-before-completion && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "verification-before-completion" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completion into .cursor/skills/verification-before-completion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verification-before-completion", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/jnMetaCode/superpowers-zh.git --path skills/verification-before-completion--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install jnMetaCode/superpowers-zh verification-before-completion --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/verification-before-completion .gemini/skills/verification-before-completion && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "verification-before-completion" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completion into .gemini/skills/verification-before-completion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verification-before-completion", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install jnMetaCode/superpowers-zh verification-before-completionInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/verification-before-completion .github/skills/verification-before-completion && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "verification-before-completion" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completion into .github/skills/verification-before-completion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verification-before-completion", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install jnMetaCode/superpowers-zh verification-before-completion --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/jnMetaCode/superpowers-zh.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/verification-before-completion .opencode/skills/verification-before-completion && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "verification-before-completion" agent skill from https://github.com/jnMetaCode/superpowers-zh/tree/main/skills/verification-before-completion into .opencode/skills/verification-before-completion/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "verification-before-completion", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
verification-before-completion- GitHub stars
- 8.3k
- Token cost
- ~443 tokens
- SKILL.md length
- 97 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output.
- Before saying tests pass or a bug is fixed
- SKILL.md covers 概述, 铁律, 门控函数 and 常见失败模式, plus 4 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Before committing or opening a PR
What it does
A Chinese edition of a verification discipline. The iron rule is that no completion claim is allowed without fresh verification evidence: if the command was not run in the current message, tests cannot be said to pass. A gate procedure begins by identifying which command would prove the claim, then runs it and reads the output before any statement of success.
A table maps claims to what is actually required: tests need output showing zero failures, a linter claim needs linter output, a build needs exit 0, a bug fix needs the original symptom retested, a regression test needs a red-green cycle, a delegated agent's success needs a check of the VCS diff, and requirements need a line-by-line checklist. It lists red flags such as hedging words and premature satisfaction, and a rationalization table with replies like confidence is not evidence.
When your agent uses it
- Before saying tests pass or a bug is fixed
- Before committing or opening a PR
- After a delegated agent reports success
- Before marking a task complete
Example prompts
- “Before you say it's fixed, run the tests and show me the output.”
- “Verify that the build really passes instead of relying on the linter.”
- “Check the VCS diff to confirm the subagent actually made the change.”
What it can do on your machine
Read from SKILL.md and the folder at commit fe34019. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Verification Before Completion loads about 443 tokens when it runs. Until then it costs about 24 tokens; SKILL.md has 97 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from jnMetaCode/superpowers-zh at commit fe34019, republished under its MIT licence (© jnMetaCode). 97 words, ~443 tokens.
Download SKILL.mdSave it as
.claude/skills/verification-before-completion/SKILL.md (or your agent's skills folder).- 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
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
© jnMetaCode, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/verification-before-completion of jnMetaCode/superpowers-zh.
Open the folder on GitHubat commit fe34019
Compare with similar skills
Verification Before Completion next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Verification Before Completion this skilljnMetaCode/superpowers-zh | 8.3k | — | ~443 | Automated safety check: Pass | MIT | |
| Verify and StopJuliusBrussee/caveman | 110k | 1 repos | ~176 | Automated safety check: Pass | Apache-2.0 | |
| Iteration Progress Auditprime-radiant-inc/iterative-development | 181 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | |
| QA Verdict JudgeQ00/ouroboros | 6.2k | — | ~2.3k | Automated safety check: Pass | MIT | |
| Verify Before CompletionYeachan-Heo/oh-my-claudecode | 40k | — | ~277 | Automated safety check: Pass | MIT | |
| Nucleus Result Package Builderprotect-my-hair/nucleus-marketplace | 164 | — | ~414 | Automated safety check: Pass | MIT |
Similar skills
Iteration Progress Audit
prime-radiant-inc/iterative-development
Checks the quality of behavior evidence after each iteration in three tiers, using two auditor subagents in parallel to review the same work and find gaps.
QA Verdict Judge
Q00/ouroboros
Gives a fast single-pass quality verdict on any artifact, with a score from 0 to 1, PASS, REVISE or FAIL, and suggestions for what to change.
Verify Before Completion
Yeachan-Heo/oh-my-claudecode
Has the agent prove that a feature, fix or refactor works, using existing tests first, then narrow commands and manual checks, and report only what was actually verified.
Nucleus Result Package Builder
protect-my-hair/nucleus-marketplace
Builds the result.json file for a Nucleus V2 workflow run from its context, gates, blockers and step status, and exits non-zero when the run is blocked.
Procoder Commit Gate
azrtydxb/procoder
Applies Procoder's senior-developer discipline in a repository: run the commit gate, format through the binary and work through specs, plans and todos.
More from jnMetaCode/superpowers-zh
All 21 skills in this repoBrainstorming Before Building
jnMetaCode/superpowers-zh
Turns a rough idea into an approved design before any code is written, sorting the request into spike, bounded or architectural and enforcing an approval gate.
Chinese Commit Conventions
jnMetaCode/superpowers-zh
Reference for Chinese-language git commits and changelogs: Conventional Commits adapted for Chinese teams, with templates, breaking-change notes and issue links for several platforms.
Inline Plan Execution
jnMetaCode/superpowers-zh
Executes a written implementation plan task by task in the current session, with a progress ledger, test-first gates and one fresh-context review at the end.
Git Worktree Isolation
jnMetaCode/superpowers-zh
Sets up an isolated workspace before feature work or plan execution, preferring native worktree tools and falling back to git worktree, with instructions in Chinese.
Agency Orchestrator Workflow Runner
jnMetaCode/superpowers-zh
Runs agency-orchestrator YAML workflows inside the current agent session, with the session's own model playing each role in turn and no API key needed.
Chinese Code Review Etiquette
jnMetaCode/superpowers-zh
Gives Chinese-language templates and priority labels for code review feedback, plus guidance on bilingual comments, commit messages and common team anti-patterns.
Related
Categories
Questions about Verification Before Completion
What does Verification Before Completion do?
Chinese-language rule that bars an agent from claiming work is done, fixed or passing until it has run a verification command and read the output. A Chinese edition of a verification discipline. The iron rule is that no completion claim is allowed without fresh verification evidence: if the command was not run in the current message, tests cannot be said to pass.
When should I use Verification Before Completion?
Verification Before Completion fits situations like: before saying tests pass or a bug is fixed; before committing or opening a PR; after a delegated agent reports success; before marking a task complete.
How do I install Verification Before Completion in Claude Code?
Run `npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a claude-code`. Or copy the skill folder (skills/verification-before-completion in jnMetaCode/superpowers-zh) into .claude/skills/verification-before-completion in your project. Claude Code loads it when a task matches its description.
How do I install Verification Before Completion in Codex?
Run `npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a codex`. Or copy the skill folder (skills/verification-before-completion in jnMetaCode/superpowers-zh) into .agents/skills/verification-before-completion in your project. Codex loads it when a task matches its description.
Can I use Verification Before Completion in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add jnMetaCode/superpowers-zh --skill verification-before-completion -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/verification-before-completion, .gemini/skills/verification-before-completion, .github/skills/verification-before-completion and .opencode/skills/verification-before-completion in your project.
What does Verification Before Completion need to run?
SKILL.md names no scripts, command-line tools or credentials: Verification Before Completion is instructions for the agent only.
Does Verification Before Completion access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Verification Before Completion safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Verification Before Completion use?
Verification Before Completion is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Verification Before Completion use?
About 443 tokens (SKILL.md is roughly 1.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Verification Before Completion?
Skills that share tags, products or a category with Verification Before Completion: Verify and Stop (JuliusBrussee/caveman, 110k stars), Iteration Progress Audit (prime-radiant-inc/iterative-development, 181 stars), QA Verdict Judge (Q00/ouroboros, 6.2k stars) and Verify Before Completion (Yeachan-Heo/oh-my-claudecode, 40k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Verification Before Completion?
jnMetaCode (a GitHub user) maintains it in jnMetaCode/superpowers-zh, which has 8,270 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on October 4, 2026.
Source: jnMetaCode/superpowers-zh on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.