agentleFS
Practice019Practice019/agent-skills/verify/SKILL.md

verify

Skill0 starsChanged 2 months agoMITView on GitHub

Verify 阶段:在真实运行环境里证明行为正确,失败时系统化恢复。三条分支:test-driven-development(用测试证明)/ browser-testing-with-devtools(浏览器/DOM/console/network 运行时验证,含截图看视图)/ debugging-and-error-recovery(坏了怎么复现定位修复防复发)。另含 stack-trace-triage 用于拿到报错堆栈时快速定位根因。对应 /test。Verify phase: prove behavior in a real runtime and recover from failure. Routes to test-driven-development, browser-testing-with-devtools, debugging-and-error-recovery. Use when testing, debugging, verifying browser behavior, or when a stack trace is pasted. Based on addyosmani/agent-skills v0.6.9.

188 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use instinct-export, instinct-import 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.
  • TheKREATORSSkill

    instinct-export

    Export instincts from project/global scope to a file

    Also in 3 projects that use this

  • TheKREATORSSkill

    instinct-import

    Import instincts from file or URL into project/global scope

    Also in 3 projects that use this

  • AviadPSkill

    risk-assess

    Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).

    Also in 3 projects that use this

  • diego-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 6 projects that use this

  • AaravChadhaSkill

    secure

    Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.

    Also in 3 projects that use this

  • ArvorCoSkill

    specify

    Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.

    Also in 10 projects that use this

  • +1 more from TheKREATORS

The file

Files
SKILL.md

Verify(验证阶段 · 路由)

来源:addyosmani/agent-skills v0.6.9 的 test-driven-development / browser-testing-with-devtools / debugging-and-error-recovery / stack-trace-triage。 本文件是路由层,原文是本技能目录下的子文件,用 read 按相对路径读取。

这个阶段干什么

用测试和真实运行数据证明代码可用,而不是「感觉应该可以」。 坏了就系统化恢复。

⚠️ 内嵌子文件没有注册成独立技能,用 read <文件名> 读(相对本技能目录)。

路由表

你要做的事读
用测试证明行为正确(要写/跑测试)test-driven-development.md
浏览器真实环境验证(DOM / console / network / 截图看视图)browser-testing-with-devtools.md
东西坏了,要系统化排错debugging-and-error-recovery.md
拿到一段报错堆栈 / traceback / panic / 崩溃日志stack-trace-triage.md(同目录) 见下

注:stack-trace-triage 不是上游内容(上游 skills/ 里没有它), 它是本库原有的本地子模块,从重置前的 git 历史恢复而来。

三条路径的顺序

1. 涉及浏览器行为? ──→ browser-testing-with-devtools(真实运行时,含截图看视图)
2. 要系统化排查失败? ─→ debugging-and-error-recovery(复现 → 定位 → 修 → 防复发)
3. 要证明它能用? ────→ test-driven-development(先失败测试,再让它过)

核心纪律

① 验证范围只由 diff 决定

git diff --name-only → 映射到包 → 反查谁依赖它
跑:受影响包 ∪ 反向依赖包

⛔ 不跑全量套件。 全量是人在最后那次端到端里自己决定要不要跑的事。

⚠️ 影响面是算出来的,所以可能算漏。反查时特别当心这几类静态图看不见的依赖: 靠字符串 / 反射 / DI 容器建立的、monorepo 里路径别名解析不到的、 测试夹具包引用方向反了的。 算的时候逐条检查 —— 这就是「不跑全量」的对价。

② 证据,不是感觉

「看起来对」永远不够。必须有:测试通过 / 构建输出 / 运行时数据。

③ 失败时先保留现场

别急着回滚把证据清掉。先记录,再按 debugging-and-error-recovery.md 走。

浏览器验证:截图看视图

本环境可以自己截图并看图(已实测):

# 无依赖:Chrome 无头截图
"C:\Program Files\Google\Chrome\Application\chrome.exe" \
  --headless --disable-gpu --hide-scrollbars \
  --window-size=1440,900 --screenshot=out.png <URL 或 file:// 路径>

# 需要交互/等渲染(SPA、点击、滚动)→ playwright

然后 read_image(out.png) 自己看。

⛔ 视觉验证是本技能能做的事,不该推给人。 真的截不了才如实写进「请人跑一次端到端」的清单。 把「没跑」写成「跑过了」是最严重的错误。

边界

做:跑测试、真实运行验证、截图看视图、系统化排错、从失败里恢复。

不做:

  • ❌ 不写新的实现(那是 build)—— 除非是为了修 bug
  • ❌ 不做合并前评审(那是 review)
  • ❌ 不代替人做主观判断(好不好用、顺不顺)—— 那只有人能判

★ 本技能管「怎么验证、怎么从失败恢复」;diagnose 管「硬 bug 的系统化定位纪律」 —— 失败顽固、复现困难、或属性能回归时,转 diagnose。

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.