verification
Skill2 starsChanged 2 months agoMITView on GitHub
在声称任务完成前强制收集证据。当 Agent 即将报告「完成 / 修复 / 通过」或修改了代码需要验证时使用;覆盖 typecheck / lint / test / build / 浏览器检查的选择与执行顺序。
47 other projects use a version of this.
Adopted by
Most recently taken up by
- neuraforge-cl-es/adaptive-engineeringtheir own version, first seen Nov 8, 2026
- facebook/docusaurustheir own version, first seen Nov 8, 2026
- maideps/ai-harness-frameworktheir own version, first seen Nov 8, 2026
- Lanqiao-Luca/ai-java-workflowtheir own version, first seen Nov 8, 2026
- Beskars-Code/Skillstheir own version, first seen Nov 6, 2026
- Gabriel-Lafrance/Skillstheir own version, first seen Nov 6, 2026
Used with
Projects with it also use evidence-driven-writing, experiment-results-planning and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Norman-burySkillevidence-driven-writing
Use when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims
Also in 3 projects that use this
Norman-burySkillexperiment-results-planning
Use when designing experiments, result tables, mock planning data, evaluation protocols, or results sections before real data are final
Also in 3 projects that use this
- +10 more from Norman-bury
Other versions47 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 47
- facebook/docusaurus★ 67ksame name
- open-metadata/OpenMetadata★ 16ksame name
- openai/plugins★ 7.8ksame name
- hi-godot/godot-ai★ 3.4ksame name
- Norman-bury/research-writing-skill★ 3.4ksame name
- Norman-bury/articlewriting-skill★ 3.4ksame name
- forcedotcom/salesforcedx-vscode★ 1ksame name
- vercel/vercel-plugin★ 328same name
- s3s-project/s3s★ 315same name
- project-numina/numina-lean-agent★ 279same name
37 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository5 other files it gives its agents.
- code-reviewSkill
- project-initializationSkill
- task-planningSkill
- feature-developmentSkill
- {{skill-name}}Skill
The file
Files
Verification(完成前验证)
Purpose
在报告完成之前强制运行检查阶梯并留下可复核证据,消灭「看起来没问题」式的完成声明。 产出的是证据清单:每条为「命令 → 输出关键行」。
When to Use
- 当即将报告任务「完成 / 修复 / 通过」时
- 当改动涉及代码且尚未运行任何检查时
- 当用户质疑改动是否破坏了其他功能时
- 当 CI 失败,需要先在本地复现时
When NOT to Use
- 纯文档 / 注释改动且不触发 lint:跳过阶梯,以
git diff摘要作为证据 - 定位失败根因:先用
debugging-and-error-recovery,找到根因再回来收尾验证 - 评审代码质量与设计:改用
code-review(本 skill 不做评审) - 尚未形成改动的探索性阅读:不需要验证阶梯
Inputs
- 项目检查命令(package.json
scripts、Makefile 或 CI 配置):读不到时向用户确认技术栈,禁止猜测命令 - 本次改动文件清单:缺失时先跑
git status+git diff --name-only收集 - 测试运行方式(runner、过滤参数、是否依赖数据库等外部服务):缺失时按仓库 README 确认
Workflow
1. Inspect
git status+git diff --name-only:确定受影响文件与改动规模- 从
package.json/ CI 配置读出实际可用的检查命令与其运行目录(monorepo 注意 workspace) - 判断各阶梯是否适用:无 UI → 跳过 browser;涉及类型、导入路径或依赖的改动 → 必须跑 build,其余情况 build 按需
2. Plan
- 写下要执行的阶梯顺序与每级具体命令,例如:
npx tsc --noEmit→npx eslint .→npx vitest run→npm run build→ 浏览器验证(UI 时) - 对每个计划跳过的级别写明理由(如「纯文档改动,无类型面」)
3. Implement
- 按顺序运行检查阶梯:
typecheck → lint → test → build(必要时)→ browser(UI 时) - 每级失败即停,修复后从该级重跑;不允许只跑通过的部分
- 记录每级的命令、退出码与输出关键行(用例数、错误摘要)
4. Verify
- 确认每级以退出码 0 结束,且输出中的用例数 / 检查文件数非 0(防止命令跑错目录造成的假绿)
- 对照
git diff --name-only:被改路径有对应测试覆盖,或写明覆盖缺口 - 把「命令 → 输出关键行」整理进最终报告
Rules
- 必须按
typecheck → lint → test → build → browser顺序执行;跳过任何一级都要写明理由 - 证据必须是「命令 + 输出」;禁止用「看起来没问题」「我检查过了」代替运行
- 修复后必须重跑失败级别及其下游级别,不得只重跑通过的部分
- 禁止为通过检查而删除或放宽测试断言;确需改动测试须说明理由并征得用户同意
- 证据清单未写入回复或变更说明前,不得声明完成
Common Failure Modes
| 症状 | 纠正 |
| 测试全绿但用例数为 0(跑错目录 / 过滤条件写错) | 核对输出中的用例数,改用仓库声明的命令重跑 |
| 跳过 build 后 CI 构建失败 | 涉及类型、导入路径或依赖的改动必须跑 build |
| 测试通过但未覆盖被改文件 | 补一个针对被改路径的用例,或说明为何无法覆盖 |
| 修复后只重跑单测,未重跑 lint | 修复涉及源码时,从 typecheck 起重跑阶梯 |
Common Rationalizations
| Agent says | Correct response |
| "这个改动很简单,不需要测试" | 运行最小相关测试 |
| "以后再补测试" | 当前任务完成前验证 |
| "我已经看过代码了" | 提供具体文件 / 证据 |
| "应该不会影响其他地方" | 执行受影响范围的验证 |
Verification
npx tsc --noEmit(或项目等价命令)→ 退出码 0- lint 与 test 命令 → 输出含非 0 的用例数 / 文件数,且失败数为 0
- 最终报告含「命令 → 输出关键行」清单,缺任一条不得声明完成
Exit Criteria
- 阶梯每一级要么以退出码 0 通过,要么写明跳过理由
- 报告附命令与输出关键行,第三方可按清单复跑
- 被改路径有对应测试覆盖,或写明覆盖缺口与原因
- 未删除或放宽任何测试断言(如有改动已说明并确认)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

