playwright-console-monitor
Executes browser workflows while monitoring JavaScript console for errors, warnings, and messages. Use when you need error-free validation, debugging context during automation, or proactive error detection in web applications. Triggers on "check for console errors", "monitor JavaScript errors", "validate error-free execution", or "debug browser workflow". Works with Playwright MCP browser automation tools.
What this skill does
# 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:
| Level | Includes | When to Use |
|-------|----------|-------------|
| `error` | Critical errors only | After critical operations (checkout, submit) |
| `warning` | Warnings + errors | During form validation, feature usage |
| `info` | Info + warnings + errors | General workflow monitoring |
| `debug` | All messages | Detailed 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
| Metric | Before (Manual) | After (Skill) | Improvement |
|--------|----------------|---------------|-------------|
| **Error Detection** | Reactive (user reports) | Proactive (during automation) | +95% early detection |
| **Debugging Time** | 30-60 min (reproduce + debug) | 5-10 min (context provided) | 80% reduction |
| **False Negatives** | High (errors missed) | Low (systematic checking) | 90% reduction |
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.