Token导航 LogoToken导航

Agent Skill · 研究检索

spec%3atest-plan(指定%3 测试计划)

用于辅助测试设计、自动化测试、用例整理和回归验证。它适合让 Agent 编写单元测试、端到端测试、测试计划或根据失败日志定位问题。使用时需要确认项目测试框架、运行命令和夹具数据,避免为了通过测试而改坏真实逻辑;涉及浏览器或外部服务时,应区分本地模拟、测试环境和生产环境。

spec%3atest-plan 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,权限为只读;许可证信息还不明确,暂无第三方扫描结果,按安装量在研究检索类的 73,675 个 Skill 里排第 70,604。

总安装 210周安装 9GitHub Stars 公开资料未说明下载 73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:spec%3atest-plan(指定%3 测试计划)
来源仓库:https://github.com/ikatsuba/skills
仓库路径:skills/spec%3Atest-plan
安装命令:
npx skills add https://github.com/ikatsuba/skills --skill spec:test-plan
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/ikatsuba/skills --skill spec:test-plan

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。

spec%3atest-plan 用于辅助测试设计、自动化测试和用例整理。适合编写单元测试、端到端测试或根据失败日志定位问题。使用时需确认项目测试框架、运行命令和夹具数据。涉及浏览器或外部服务时应区分本地模拟与生产环境。

适用宿主包括 Codex、Claude、Cursor、Gemini CLI,接入前应确认版本、权限和运行环境要求。

来源仓库内路径:skills/spec%3Atest-plan

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/ikatsuba/skills --skill spec:test-plan;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

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

spec%3atest-plan 怎么安装?

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

spec%3atest-plan 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。

spec%3atest-plan 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

spec%3atest-plan 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。

spec%3atest-plan 用的人多吗?

公开数据是累计安装 210 次,近一周安装 9 次,下载 73 次。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。

spec%3atest-plan 安全吗?

没有查到第三方扫描结果,安全性无法从公开资料判断,安装前请自行审查源码、依赖和命令行为。

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。
  • 标注为只读权限,试用阶段不容易误改本地文件。

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。
  • 没有第三方扫描结果,安全性只能靠自己读源码判断。
  • 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。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 要求有安全扫描结论才肯安装的团队。
  • 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
spec%3atest-plan

指定%3 测试计划 · 本页

210—只读未明确未收录

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

Generate Test Plan

Role

You are a QA Engineer. Your job is to design tests that find bugs, not confirm success.

  • Derive test cases from requirements, not from the implementation
  • Prioritize edge cases, error states, and boundary conditions alongside happy paths
  • Write steps precise enough that any tester can reproduce without interpretation
  • Never assume the implementation is correct — test what the requirements demand

Creates a manual test plan document based on the specification documents. This skill reads requirements, research, design, and tasks to generate a structured test plan with traceable test cases.

When to use

Use this skill when the user needs to:

  • Create a manual test plan after implementation is complete
  • Generate test scenarios from existing specification documents
  • Establish a structured testing phase for a feature

Specification Files Structure

All specification documents are located in .specs/<spec-name>/ directory:

FileDescription
.specs/<spec-name>/requirements.mdRequirements and acceptance criteria
.specs/<spec-name>/research.mdResearch findings and chosen solutions
.specs/<spec-name>/design.mdTechnical design and architecture
.specs/<spec-name>/tasks.mdImplementation tasks with checkboxes

Read all available files to understand the full context before generating the test plan.

Instructions

Step 0: Check Prerequisites

Read the frontmatter of the prerequisite document. If no frontmatter exists, treat as DRAFT.

PrerequisitePathGate
design.specs/<spec-name>/design.mdHARD
  • HARD gate failed (missing or status is not APPROVED): Display: "Cannot proceed: design.md is missing or not APPROVED (current status: <status>). Run spec:approve <spec-name> design first." Use AskUserQuestion with options: "Run spec:approve now", "Cancel".
  • All gates pass: Proceed silently to Step 1.

Step 1: Locate and Read Specification Documents

  1. If $ARGUMENTS contains a spec name ($0), look in .specs/<spec-name>/
  2. If no spec name provided, list available specs in .specs/ and use the AskUserQuestion tool to let the user choose
  3. Read and parse all specification documents:

- requirements.md - understand what needs to be tested - research.md - understand chosen solutions and edge cases - design.md - understand architecture and integration points - tasks.md - understand what was implemented

Step 2: Analyze for Test Coverage

Before writing the test plan:

  1. Extract all testable requirements from requirements.md (SHALL/WHEN-THEN statements)
  2. Identify user flows and feature areas from the design
  3. Note edge cases, error states, and boundary conditions from research
  4. Review tasks to understand which components were built and how they connect
  5. Group related test cases by feature area or user flow

Step 3: Create the Test Plan Document

Create the document at .specs/<spec-name>/test-plan.md with this structure:

The document MUST begin with YAML frontmatter before the first # heading:

---
status: DRAFT
created: <today's date YYYY-MM-DD>
updated: <today's date YYYY-MM-DD>
---
# Manual Test Plan: [Feature Name]

## Overview
[What is being tested, scope, and goals of this test plan]

## Prerequisites
- [Environment setup needed]
- [Test data or accounts required]
- [Access or permissions needed]
- [Dependencies that must be running]

## Test Scenarios

- [ ] 1. [Scenario Group Name]
  - [ ] 1.1 [Test Case Name]
    - **Preconditions:** [Required state before testing]
    - **Steps:**
      1. [Action to perform]
      2. [Next action]
      3. [Continue as needed]
    - **Expected:** [Observable result that confirms success]
    - _Requirements: X.X_

  - [ ] 1.2 [Test Case Name]
    - **Preconditions:** [Required state]
    - **Steps:**
      1. [Action]
    - **Expected:** [Result]
    - _Requirements: X.X_

- [ ] 2. [Another Scenario Group]
  - [ ] 2.1 [Test Case]
    - **Preconditions:** [State]
    - **Steps:**
      1. [Action]
    - **Expected:** [Result]
    - _Requirements: X.X_

## Summary
- Total: N tests
- Passed: 0
- Failed: 0
- Skipped: 0

Test Plan Guidelines

  1. Trace every requirement - Each testable requirement from requirements.md must be covered by at least one test case via _Requirements: X.X_
  2. Group by feature area - Organize scenario groups by user flow or feature area, not by requirement number
  3. Include edge cases - Add test cases for error states, boundary conditions, empty states, and invalid inputs
  4. Be specific in steps - Each step should be a concrete action the tester can perform without ambiguity
  5. Be specific in expected results - Describe exactly what the tester should observe, not vague outcomes
  6. Include preconditions - State any setup needed before running the test case
  7. Order logically - Start with happy paths, then edge cases, then error scenarios within each group

Checkbox States

  • [] - Pending (not tested)
  • [-] - In progress (currently being tested)
  • [x] - Passed
  • [!] - Failed

Step 4: Confirm with User

After creating the document, show the user:

  1. The location of the created file
  2. A summary of the test plan structure
  3. Total number of test scenarios and test cases
  4. Coverage: which requirements are covered
  5. Use the AskUserQuestion tool to ask if they want to make changes or start testing, with options like "Looks good, start testing", "I want to make changes", "Review test plan first"

Arguments

  • $ARGUMENTS / $0 - The spec name (e.g., "user-auth", "payment-flow")

If not provided, list available specs and ask the user to choose.

平台分布

Codex

35.17%
按下载量换算26

Claude

31.56%
按下载量换算23

Cursor

17.36%
按下载量换算13

Gemini CLI

9.17%
按下载量换算7

安全审计

暂无安全审计结果可展示。

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

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