agentleFS
vibevalleyhqvibevalleyhq/vibevalley/.agents/skills/create-verification-skill/SKILL.md

create-verification-skill

Skill12 starsChanged 7 days agoApache-2.0View on GitHub

为 VibeValley 的一类改动写验收的一份分册(.agents/skills/vv-acceptance/references/<块>.md):把「怎么证明这次改动真的能用」变成下一个 agent 照着就能做的步骤。用在:一类改动没有现成的验证办法;你刚花了不少工夫才弄清怎么验证一个改动;同一类问题测试和检查都没拦住、到了主人手里才发现;主人说「写个验证 skill」「把这个验证流程固定下来」「加进验收」「create verification skill」。只写改动后的验证,不写怎么实现功能。

77 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use setup-pstack, ketchup-video 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.
  • bnemaSkill

    setup-pstack

    Configure which Pi models pstack uses per role. Detects available provider/model specs and writes pstack's user configuration. Use for /setup-pstack, "configure pstack models", or changing pstack model choices.

    Also in 25 projects that use this

  • tristanphvnSkill

    ketchup-video

    Catch the user up like /keel:ketchup, with a short silent video of slides for what happened and the waiting calls as text under it. Use for /keel:ketchup-video.

    Also in 13 projects that use this

  • ianclearySkill

    poteto-help

    Guides users through pstack setup, /poteto-mode, and picking the skill, playbook, or principle for a task. Type /poteto-help with a question.

    Also in 14 projects that use this

  • eryzerzSkill

    make-bot-ui

    Use when building a custom UI (page, dashboard, buttons) that should wake a Grok Bot over a webhook, when the user must provide a webhook sender key, or when exposing that UI on Tailscale.

    Also in 19 projects that use this

  • ianclearySkill

    principle-explain-the-number

    Apply before you trust, report, or act on a number you measured: a speedup, a regression, a throughput, a latency, or an eval result. Find what limits it, and rule out that it measured something other than the work you think.

    Also in 27 projects that use this

  • drafaelSkill

    in-your-own-words

    Restate the user's goals and the problem they are trying to solve to check understanding. Manual invocation only; use when the user explicitly invokes in-your-own-words or requests this understanding check. Do not solve the task or rewrite the assistant's last answer.

    Also in 26 projects that use this

The file

Files
SKILL.md

给验收加一份分册

验收(vv-acceptance)只有一个 skill:入口写共同的沙箱、证据和收拾,每一块的做法是 references/ 下的一份分册。分册回答一个问题:改了这一块,怎么在真的程序上看到它对了。它补的是测试和检查之后的那一段:服务端真的起来、接口真的返回、客户端真的画出来。

这一层是「文字」,排在代码和静态检查后面(AGENTS.md)。所以写之前先过第 1 步。

1. 先问能不能不写

按顺序问,答「能」就去做那件事,不写分册:

  1. 能不能改代码,让这类错误写不出来(类型、不变量、只留一个入口)?
  2. 能不能写成测试或检查,进 vp run server:check、vp run web:check、vp run --filter @vibevalley/web e2e、vp run docs:verify?服务端的测试能用 oar 的 scriptedRuntime、真的 git 仓库和照脚本回答的模型(@vibevalley/ai/testing),页面的 Playwright 对着真的服务端,大部分行为都能这样测。

只有要真的跑起来看、要判断(画面对不对、交互顺不顺、真的帮工能不能开工)的,才写分册。一份分册里能改成检查的步骤,也宜改成检查,分册里只留一句命令。

已有的分册管得住的(同一块地方的新改动),改那份,不另写。

2. 先真的验证一次

不照着想象写。在这次改动上把验证完整做一遍,边做边记:

  • 每条命令原样记下,连同工作目录和环境变量。
  • 每一步看到了什么:输出的哪一行、接口返回的哪个字段、截图里的哪个东西,说明成功。
  • 哪里卡住了、怎么绕过去的:端口占用、要先生成、服务端不自动重载、要临时的家目录。
  • 做完要收拾什么:停掉的进程、删掉的临时目录。

做不完的步骤不写进分册,或者明写「这一步还没走通」。

3. 写分册

放在 .agents/skills/vv-acceptance/references/<块>.md,<块> 用实际的概念或目录名(server、page、mobile),不用皮的叫法。分册没有 frontmatter:agent 什么时候读它,由入口的表决定。

开头一句指回入口([验收](.agents/skills/vv-acceptance/SKILL.md)的一份分册),说它证明什么。正文用这几节,名字固定,vp run docs:verify 会查:

  • ## 什么时候用:哪些路径、哪类改动;哪些改动只跑检查就够、不用它。
  • ## 准备:要先有什么(生成的代码最新、构建、模拟器、钥匙),每条带命令。
  • ## 步骤:编号列表,一步一条命令或一个动作,动词开头。要服务端的,用入口的沙箱(vpx scripts/verify-server.ts -- …),不另起。
  • ## 证据:做完要拿给主人看的东西:命令的哪几行输出、接口的哪个字段、截图。
  • ## 出错时:这一块常见的失败、怎么认出来、怎么办;沙箱自己的失败入口已经写了,不重复。
  • ## 收拾:停进程、删临时目录。

要花钱、连网、动主人东西的,在入口里也写一句,让没读分册的 agent 也看得到。

写法照 docs/style/writing.md:一步一件事,命令放在代码块里,原样能复制。

4. 从头照着做一遍

开一个新的子 agent(或清掉上下文),只给它 vv-acceptance 和一个改动,让它照着验收。它卡住的地方,就是分册(或入口的表)漏写的地方;补上再试,直到它不问问题就能做完。

5. 登记

  1. 在 vv-acceptance 的入口「什么时候用」的表里加一行:改了什么、读哪份、证明什么;入口的 description 补上触发它的路径和说法。
  2. 跑 vp run docs:verify:它查每份分册有那几节,入口的表正好列全分册。

维护

分册是当前的文档,不是历史:命令、路径、端口变了,同一个改动里改它。某一步后来变成了检查,就把那一步换成检查的命令。一份分册里的步骤全都成了检查,就删掉它和入口表里的那一行。

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.