跳到正文
cccskills
免费在 GitHub 公开

exploratory-testing

Perform comprehensive exploratory testing on a website using browser automation, covering user journeys, forms, errors, accessibility, responsiveness, performance, and security basics. Use when asked to QA a site, explore an app, find bugs, or produce a browser testing report.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md4.4 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

Website Exploratory Testing

Goal

ultrathink

You are tasked with performing comprehensive exploratory testing on a website using the user's configured browser automation tool.

Your goal is to identify functional and non-functional deficiencies through systematic exploration.

Setup Instructions

  1. Use the available browser automation tool (see CLAUDE.md for configured tool)
  2. Create a sub-task for browser operations to manage context window efficiently

Authentication Handling

IMPORTANT: If you encounter login pages, authentication requirements, CORs errors, or areas requiring user credentials:

  • STOP testing immediately
  • Document what you've found so far
  • Ask the user to provide necessary login credentials (username/password, API keys, etc.)
  • Wait for credentials before proceeding with authenticated areas
  • Once provided, continue testing both public and authenticated sections

Testing Methodology

Perform exploratory testing using these established techniques:

Core Testing Areas

  • User Journey Testing: Navigate critical user paths (registration, login, checkout, etc.)
  • Boundary Testing: Test form inputs with edge cases (empty, max length, special characters)
  • Error Handling: Deliberately trigger errors to test graceful failure
  • Accessibility Testing: Check ARIA labels, keyboard navigation, color contrast
  • Responsive Design: Test different viewport sizes and orientations
  • Performance: Monitor page load times and resource usage
  • Security Basics: Check for exposed sensitive data, insecure forms
  • Cross-browser Compatibility: Test core functionality across browsers
  • Authentication Flow: Test login/logout, session management, password reset (when credentials provided)

Testing Approach

  1. Start with homepage reconnaissance - understand site structure
  2. Identify and test all publicly accessible interactive elements
  3. Stop and request credentials if authentication is required
  4. Test authenticated areas once credentials are provided
  5. Follow happy path user journeys first, then explore edge cases
  6. Test error scenarios and recovery paths
  7. Validate accessibility and usability patterns
  8. Check mobile responsiveness and touch interactions
  9. Monitor console errors and network issues throughout

Issue Classification

🔴 CRITICAL (Red X):

  • Broken core functionality
  • Security vulnerabilities
  • Accessibility violations preventing usage
  • Site crashes or unrecoverable errors
  • Authentication bypasses or exposures

⚠️ WARNING (Yellow Warning):

  • Poor UX patterns
  • Minor accessibility issues
  • Performance concerns
  • Inconsistent behavior
  • Weak authentication patterns

✅ PASSED (Green Checkmark):

  • Working functionality
  • Good user experience
  • Proper error handling
  • Accessibility compliance
  • Secure authentication flow

Report Requirements

Create a comprehensive markdown report saved as exploratory_testing_report_YYYY-MM-DD_HH-MM-SS.md (use current date and timestamp) with:

Structure:

  1. 🔴 CRITICAL ISSUES (at top for visibility)
  2. ⚠️ WARNINGS & CONCERNS
  3. ✅ PASSED TESTS
  4. AUTHENTICATION STATUS (what was tested with/without login)
  5. EXECUTIVE SUMMARY (2-3 readable paragraphs)
  6. RECOMMENDED ACTION PLAN (prioritized steps to resolve issues)

Content Guidelines:

  • Include specific steps to reproduce issues
  • Capture screenshots for visual problems
  • Note which browsers/devices were tested
  • Clearly distinguish between authenticated vs non-authenticated testing
  • Provide clear, actionable recommendations
  • Use proper markdown formatting with checkboxes and status icons

Execution Notes

  • Work systematically through each testing area
  • Document everything you test, even if it passes
  • Always stop and ask for credentials when auth is encountered
  • When you find issues, explore related functionality for patterns
  • Take screenshots of important findings
  • Keep detailed notes of your testing process

Please provide the website URL you'd like me to test when ready to begin.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

中文简介正在准备中。当前显示原文说明。

SDiamante13/dotfiles112026年10月2日 更新

catchup

免费

Rebuilds session context after a clear by reading git history, plans, and beads state. Triggers on 'catch up'.

中文简介正在准备中。当前显示原文说明。

SDiamante13/dotfiles112026年10月2日 更新

changelog

免费

Generate a bullet-point summary of branch changes for a PR description. Triggers on "changelog", "pr summary", "summarize branch", or "/changelog".

中文简介正在准备中。当前显示原文说明。

SDiamante13/dotfiles112026年10月2日 更新

commit

免费

Commit the current changes with quality checks, status review, staged diff inspection, appropriate tests, and a clear commit message. Use when the user says "commit", "c", asks to make a commit, or wants changes saved in git.

中文简介正在准备中。当前显示原文说明。

SDiamante13/dotfiles112026年10月2日 更新

declutter

免费

Refactor code to remove dead code, useless comments, unused variables, and unused imports. Use when asked to declutter a class, clean up noisy code, remove cruft, or run `/refactor:declutter`.

中文简介正在准备中。当前显示原文说明。

SDiamante13/dotfiles112026年10月2日 更新

dry

免费

Refactor duplicated code by extracting helpers, shared abstractions, or clearer reusable structure. Use when asked to apply DRY, remove duplication, consolidate repeated logic, or run `/refactor:dry`.

中文简介正在准备中。当前显示原文说明。

SDiamante13/dotfiles112026年10月2日 更新

查看 SDiamante13 的全部技能

报告此技能的问题