Token导航 LogoToken导航

Agent Skill · 研究检索

verify(验证)

verify 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

verify 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为操作浏览器;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 45,111。

总安装 870周安装 37GitHub Stars 2下载 305核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:verify(验证)
来源仓库:https://github.com/uinaf/skills
仓库路径:skills/verify
安装命令:
npx skills add https://github.com/uinaf/skills --skill verify
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/uinaf/skills --skill verify

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

verify 用于查找、检索和筛选相关信息。适合在 Codex、Claude、Cursor、Gemini CLI 中快速定位候选结果。可结合来源仓库和原始 README 核验具体用法。安装前建议确认权限范围和维护状态。verify 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

注意是否会触发联网、命令执行或文件读写。

来源仓库内路径:skills/verify

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/uinaf/skills --skill verify;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要操作浏览器,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

verify 怎么安装?

在终端执行 npx skills add https://github.com/uinaf/skills --skill verify。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

verify 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

verify 需要什么权限?

权限级别是操作浏览器。该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

verify 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

verify 用的人多吗?

公开数据是累计安装 870 次,近一周安装 37 次,下载 305 次,GitHub 2 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

verify 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
verify

验证 · 本页

8702操作浏览器未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Verify

Self-check your own completed change before handing it off to review. Verify proves the change boots, passes guardrails, and survives the real surface — it is not a substitute for independent review.

Principles

  • Verify is the builder's gate before review; it does not replace review
  • The builder does not grade their own work in the same context — switch into a fresh evaluator context or separate subagent first
  • Run repo guardrails first, then hit the real surface
  • Prefer smoke, integration, contract, or e2e proof over unit tests that mock most of the behavior under test
  • Self-correct obvious issues you spot while exercising the change; leave the rigorous code-shape pass to review
  • Load shared doctrine from the repo's guidance files such as AGENTS.md, CLAUDE.md, or repo rules before judging the result
  • If the infrastructure is too weak to verify reliably, stop and hand off to agent-readiness

Handoffs

  • Verification passed → hand off to review for the independent ship decision
  • No stable boot / smoke / interact path, or infrastructure too weak to trust → use agent-readiness
  • Auditing existing code, a diff, branch, or PR you did not author → use review
  • Main problem is stale AGENTS.md, README, specs, or repo docs → use docs

Before You Start

  1. Define the exact change being verified and the expected user-visible behavior
  2. Switch into an independent evaluator context before judging your own work
  3. Load the target repo's guidance files such as AGENTS.md, CLAUDE.md, or repo rules, when present
  4. Confirm you can boot and interact with the real surface
  5. Pick the smallest check set that can disprove the change honestly

Workflow

1. Run deterministic guardrails first

  • Prefer the repo's built-in entrypoint: make verify, just verify, pnpm test, cargo test, or the nearest targeted equivalent
  • When choosing tests, prefer the strongest cheap proof available: smoke, integration, contract, or e2e checks beat mock-heavy unit suites that mainly replay implementation details
  • Swallow boring success output and surface only failures, anomalies, and exact commands

2. Exercise the real surface

  • UI → run the browser automation, navigate the changed flow, and capture screenshots
  • API → hit the local endpoint with a real request such as curl http://127.0.0.1:3000/health
  • CLI → run the shipped command such as node dist/cli.js --help or the repo's packaged entrypoint
  • state/config → verify round trips, restart behavior, and config boot paths

Follow references/evidence-rules.md when collecting proof.

3. Self-correct obvious issues

While exercising the change, fix anything cheap and obvious that you spot:

  • A typo in a log line, a stale comment, an unused import, a duplicated helper inside the diff
  • An any, unsafe as, or non-null assertion you can replace with a real type in seconds
  • A failure path that swallows errors silently when a one-line throw makes the diagnostic useful

Do not turn this into a full review pass. Substantive code-shape concerns (architecture mismatches, broader duplication, error-classification redesigns) belong to review. Use references/simplification.md only as a short self-check, not as a refactoring backlog.

4. Probe adjacent risk

  • Check the main happy path
  • Check at least one failure path or edge case
  • Check that at least one exercised failure path returns or logs a useful, actionable error instead of a vague or swallowed failure
  • Re-test any config, persistence, or restart-sensitive behavior touched by the change

5. Synthesize the verdict

Produce one clear outcome:

  • ready for review — guardrails green, real surface confirmed, no obvious self-correctable issues left
  • needs more work — the change is not ready to be reviewed; specific issues to address are listed
  • blocked — verification cannot proceed, usually because infrastructure is too weak (hand off to agent-readiness)

Verify never issues ship it. The independent ship decision is review's job.

Output

After verification, report:

  • verdict
  • change verified
  • surfaces exercised
  • self-corrections applied during verification (if any)
  • top findings by severity (issues you could not self-correct)
  • exact evidence: commands, screenshots, traces, responses, or file references
  • readiness gaps or doc drift discovered during verification
  • recommended follow-up: review, agent-readiness, docs, or more implementation

Example:

verdict: ready for review
change verified: retry banner after transient API failure
surfaces exercised: pnpm test test/retry.spec.ts, curl http://127.0.0.1:3000/api/retry
self-corrections: dropped unused import in src/retry/banner.ts; tightened error log to include status code
top finding: medium — the UI recovers, but the retry count is not persisted across refresh (left for review to weigh)
evidence: local API returned 200 after retry; browser screenshot after refresh shows count reset to 0
recommended follow-up: review

References

平台分布

Codex

39.44%
按下载量换算120

Claude

29.29%
按下载量换算89

Cursor

17.73%
按下载量换算54

Gemini CLI

9.74%
按下载量换算30

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

操作浏览器

该 Skill 可能涉及浏览器控制能力,使用时可能读取或操作网页内容,需要在受控环境中确认权限边界。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills