Token导航 LogoToken导航

Agent Skill · 前端设计

playwright-console-monitor(Playwright console monitor 测试)

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。

playwright-console-monitor 是前端设计类 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,第三方扫描有提醒项,按安装量在前端设计类的 10,216 个 Skill 里排第 8,923。

总安装 247周安装 10GitHub Stars 1下载 78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:playwright-console-monitor(Playwright console monitor 测试)
来源仓库:https://github.com/dawiddutoit/custom-claude
仓库路径:skills/playwright-console-monitor
安装命令:
npx skills add https://github.com/dawiddutoit/custom-claude --skill playwright-console-monitor
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/dawiddutoit/custom-claude --skill playwright-console-monitor

这个 Skill 是做什么的

前端设计类 Skill 关注页面结构、视觉规范和组件写法,输出通常是可运行的界面代码。

用于辅助测试设计、自动化测试、用例整理和回归验证。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,避免误改逻辑。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。

playwright-console-monitor 属于前端设计类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/playwright-console-monitor

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/dawiddutoit/custom-claude --skill playwright-c…;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

playwright-console-monitor 怎么安装?

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

playwright-console-monitor 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。

playwright-console-monitor 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。

playwright-console-monitor 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。

playwright-console-monitor 用的人多吗?

公开数据是累计安装 247 次,近一周安装 10 次,下载 78 次,GitHub 1 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。

playwright-console-monitor 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。
  • 需要处理前端设计类任务、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。

前端设计类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
frontend-design

前端设计 · Codex、Claude

8,823,360126,072只读MIT通过
vercel-composition-patterns

Vercel 组合模式 · Codex、Claude

3,858,81625,893需要联网MIT通过
vercel-react-native-skills

Vercel React native skills 前端 · Codex、Claude

2,468,66425,878只读MIT通过
adapt

adapt 搜索 · Codex、Claude

2,027,04023,125操作浏览器未明确通过
bolder

bolder 分析 · Codex、Claude

2,004,28823,130只读未明确通过
playwright-console-monitor

Playwright console monitor 测试 · 本页

2471操作浏览器未明确有提醒

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

Playwright Console Monitor

Quick Start

Monitor console errors during a login workflow:

1. Navigate to application
2. Execute login steps
3. Check console for errors after each critical operation
4. Generate error report with screenshots
5. Provide debugging context

Immediate value: Catch JavaScript errors during automation that would otherwise go unnoticed.

Table of Contents

  1. When to Use This Skill
  2. What This Skill Does
  3. Console Error Monitoring Workflow 3.1 Setup and Navigation 3.2 Execute with Monitoring 3.3 Error Detection and Categorization 3.4 Report Generation
  4. Console Message Levels
  5. Supporting Files
  6. Expected Outcomes
  7. Integration Points
  8. Success Metrics
  9. Requirements
  10. Red Flags to Avoid
  11. Notes

When to Use This Skill

Explicit Triggers

  • User says "check for console errors"
  • User says "monitor JavaScript errors during [workflow]"
  • User says "validate error-free execution"
  • User says "debug this workflow"
  • User requests "console monitoring"

Implicit Triggers

  • Executing critical browser workflows (checkout, form submission, data operations)
  • Testing new features or deployments
  • Debugging intermittent failures
  • Validating application health
  • QA automation scenarios

Debugging Context

  • When workflows fail without obvious cause
  • When investigating "works for me" issues
  • When validating frontend error handling
  • When checking third-party script integration

What This Skill Does

This skill wraps browser automation workflows with console monitoring to:

  1. Proactive Error Detection - Catch JavaScript errors during workflow execution
  2. Error Categorization - Classify errors by severity (critical/warning/info/debug)
  3. Context Capture - Take screenshots and snapshots at error states
  4. Report Generation - Provide structured error reports with debugging context
  5. Continuous Monitoring - Check console after each critical operation

Console Error Monitoring Workflow

3.1 Setup and Navigation

Step 1: Navigate to application

Use: mcp__playwright__browser_navigate
- Navigate to target URL
- Wait for page load

Step 2: Clear initial console messages (optional)

Use: mcp__playwright__browser_console_messages
- Read and discard initial load messages
- Establishes clean baseline for workflow monitoring

3.2 Execute with Monitoring

Step 3: Execute workflow with checkpoints

For each critical operation:

  1. Execute the action (click, type, navigate)
  2. Wait for expected state
  3. Check console messages
  4. Log any new errors/warnings

Example pattern:

Action: Click "Submit Order" button
  → mcp__playwright__browser_click
Wait: Order confirmation appears
  → mcp__playwright__browser_wait_for
Check: Console errors
  → mcp__playwright__browser_console_messages({ level: "error" })

Critical operation checkpoints:

  • Form submissions
  • Navigation between pages
  • AJAX/fetch requests
  • Third-party script loads
  • Authentication flows
  • Payment processing
  • Data mutations

3.3 Error Detection and Categorization

Step 4: Categorize detected errors

Use console message levels to filter:

LevelIncludesWhen to Use
errorCritical errors onlyAfter critical operations (checkout, submit)
warningWarnings + errorsDuring form validation, feature usage
infoInfo + warnings + errorsGeneral workflow monitoring
debugAll messagesDetailed debugging scenarios

Step 5: Capture error context

For each error detected:

  1. Take screenshot of current state mcp__playwright__browser_take_screenshot
  2. Capture page snapshot mcp__playwright__browser_snapshot
  3. Record error message, timestamp, and operation

3.4 Report Generation

Step 6: Generate structured error report

Report format:

Console Error Report
====================

Workflow: [workflow name]
Executed: [timestamp]
Total Errors: [count]

Critical Errors (level: error):
  - [timestamp] [message]
    Context: [operation that triggered]
    Screenshot: [filename]

Warnings (level: warning):
  - [timestamp] [message]
    Context: [operation that triggered]

Info Messages:
  - [summary if relevant]

Debugging Context:
  - URL at time of error
  - Page snapshot
  - Network state (if available via browser_network_requests)

Recommendations:
  - [specific debugging suggestions]

Console Message Levels

Playwright console messages follow browser console API levels:

error - Critical errors that prevent functionality

  • Uncaught exceptions
  • Failed network requests (4xx/5xx from critical APIs)
  • Missing required resources
  • Use after: Checkout, payment, form submission, authentication

warning - Non-fatal issues that may cause problems

  • Deprecated API usage
  • Failed optional resources
  • Validation warnings
  • Use after: Form interactions, navigation, feature usage

info - Informational messages

  • Application lifecycle events
  • Successful operations
  • Debug information from application
  • Use for: General monitoring, understanding application flow

debug - Verbose debugging output

  • All console.log, console.debug calls
  • Framework/library debug messages
  • Use for: Deep debugging, understanding detailed behavior

Default recommendation: Use level: "error" after critical operations, level: "warning" for general monitoring.

Supporting Files

This skill includes:

  • references/playwright-console-api.md - Detailed Playwright console API reference, message formats, and advanced patterns
  • examples/examples.md - 5+ real-world monitoring scenarios (e-commerce checkout, form submission, SPA navigation, authentication, third-party integrations)
  • assets/error-report-template.md - Template for structured error reports

Expected Outcomes

Successful Monitoring (No Errors)

✅ Console Monitoring Complete

Workflow: User Login Flow
Operations Monitored: 5
Console Errors: 0
Warnings: 0

All operations completed without console errors.

Error Detection

❌ Console Errors Detected

Workflow: Checkout Process
Operations Monitored: 8
Console Errors: 2 critical, 1 warning

Critical Errors:
  1. [14:32:15] Uncaught TypeError: Cannot read property 'total' of undefined
     Context: After "Apply Discount Code" click
     Screenshot: checkout-error-1.png

  2. [14:32:18] Failed to load resource: POST /api/payment 500
     Context: After "Submit Payment" click
     Screenshot: checkout-error-2.png

Warnings:
  1. [14:32:10] [Deprecation] Synchronous XMLHttpRequest on the main thread
     Context: During address validation

Debugging Recommendations:
  - Investigate cart.total property initialization
  - Check /api/payment endpoint for server errors
  - Review discount code application logic

Integration Points

With Browser Automation Workflows

  • Wrap existing automation with console monitoring
  • Add checkpoints after critical operations
  • Enhance test suites with error detection

With Debugging Workflows

  • Console monitoring identifies error sources
  • Screenshots provide visual debugging context
  • Network requests correlate with console errors

With QA Processes

  • Automated error detection in test runs
  • Regression testing for console errors
  • Performance monitoring (console.time/timeEnd messages)

With CI/CD Pipelines

  • Fail builds on critical console errors
  • Track error trends across deployments
  • Validate error-free user flows

Success Metrics

MetricBefore (Manual)After (Skill)Improvement
Error DetectionReactive (user reports)Proactive (during automation)+95% early detection
Debugging Time30-60 min (reproduce + debug)5-10 min (context provided)80% reduction
False NegativesHigh (errors missed)Low (systematic checking)90% reduction
Context QualityMinimal (user description)Rich (screenshots, state, messages)10x improvement

Requirements

Required Tools

  • Playwright MCP browser automation

- mcp__playwright__browser_navigate - mcp__playwright__browser_console_messages - mcp__playwright__browser_snapshot - mcp__playwright__browser_take_screenshot - mcp__playwright__browser_click (for workflows) - mcp__playwright__browser_wait_for

Environment

  • Playwright browser configured and accessible
  • Target application URL

Knowledge

  • Basic understanding of JavaScript console API
  • Familiarity with browser automation workflows
  • Understanding of error severity levels

Red Flags to Avoid

  • Checking console only at end - Check after each critical operation
  • Ignoring warnings - Warnings often predict future critical errors
  • Not capturing context - Always take screenshots at error states
  • Wrong severity level - Use error level for critical operations
  • Skipping wait states - Ensure operations complete before checking console
  • Not clearing initial messages - Page load messages contaminate workflow monitoring
  • Missing operation context - Always note which operation triggered errors
  • Overly verbose monitoring - Don't check console after every single action
  • Ignoring network correlation - Console errors often correlate with network failures
  • Not providing recommendations - Error reports should suggest debugging steps

Notes

Key Principles:

  1. Monitor critical operations - Focus on checkout, submit, auth, payment
  2. Categorize by severity - Use appropriate console levels
  3. Capture rich context - Screenshots + snapshots + messages
  4. Provide actionable reports - Include debugging recommendations
  5. Balance coverage vs noise - Strategic checkpoints, not every action

Console Message Persistence:

  • Messages accumulate during page lifetime
  • Page navigation clears console (new document)
  • Consider clearing messages between checkpoints for clarity

Performance Considerations:

  • Console checks add minimal overhead (~100-200ms)
  • Screenshot capture is slower (~500ms-1s)
  • Balance monitoring thoroughness with workflow speed

Common Patterns:

  • Critical operations: Check level: "error" immediately after
  • Form workflows: Check level: "warning" after validation
  • Debugging: Use level: "info" or level: "debug" for full visibility
  • Regression testing: Establish baseline, detect new errors

Integration with Network Monitoring:

  • Combine with browser_network_requests for complete debugging context
  • Network failures often manifest as console errors
  • 500-series responses typically generate console errors
  • CORS issues appear in console, not network tab

平台分布

Codex

38.89%
按下载量换算30

Claude

28.95%
按下载量换算23

Cursor

17.46%
按下载量换算14

Gemini CLI

9.25%
按下载量换算7

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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