chrome-devtools-debugging
Debug and analyze web applications using Chrome DevTools MCP. Use for console log inspection, network request monitoring, performance analysis, and debugging authenticated sessions. For basic browser automation (screenshots, form filling), use browser-discovery skill instead.
What this skill does
# Chrome DevTools Debugging
Debug web applications by connecting to Chrome's DevTools Protocol. This skill enables:
- **Console inspection**: View errors, warnings, and log messages
- **Network analysis**: Monitor XHR/fetch requests with full headers/body
- **Performance tracing**: Record and analyze performance traces
- **JavaScript evaluation**: Execute code in browser context
- **Authenticated session debugging**: Connect to existing logged-in browsers
## When to Use This Skill
| Use Case | This Skill | browser-discovery |
|----------|------------|-------------------|
| Console error inspection | Yes | No |
| Network request analysis | Yes | Limited |
| Performance tracing | Yes | No |
| Authenticated sessions | Yes | No |
| Screenshots | No | Yes |
| Form filling | No | Yes |
| Basic navigation | Limited | Yes |
## Setup Requirements
### Option 1: Connect to Existing Chrome (Recommended)
Start Chrome with remote debugging enabled:
```bash
# Linux
google-chrome --remote-debugging-port=9222
# macOS
/Applications/Google\ Chrome.app/Contents/MacOS/Google\ Chrome --remote-debugging-port=9222
# Windows
"C:\Program Files\Google\Chrome\Application\chrome.exe" --remote-debugging-port=9222
```
Set the environment variable:
```bash
export CHROME_DEVTOOLS_URL=http://127.0.0.1:9222
```
### Option 2: Chrome Auto-Connect (145+)
For Chrome 145+, enable remote debugging at `chrome://inspect/#remote-debugging`.
## Progressive Disclosure Pattern
This skill uses **progressive MCP disclosure** for token efficiency:
```
Chrome DevTools MCP Server
|
v
Python Wrappers (.claude/ai-dev-kit/dev-tools/mcp_servers/chrome_devtools/)
|
v
Claude executes Python via Bash (on-demand)
|
v
Results returned (tools NOT in system prompt)
```
**Benefits**: 98%+ token reduction vs loading all MCP tools in system prompt.
## Quick Examples
### Get Console Errors
```bash
uv run python -c "
import sys; sys.path.insert(0, 'dev-tools')
from mcp_servers.chrome_devtools import console
errors = console.list_console_messages(types=['error'])
print(errors)
"
```
### List Network Requests
```bash
uv run python -c "
import sys; sys.path.insert(0, 'dev-tools')
from mcp_servers.chrome_devtools import network
requests = network.list_network_requests(resource_types=['xhr', 'fetch'])
print(requests)
"
```
### Execute JavaScript
```bash
uv run python -c "
import sys; sys.path.insert(0, 'dev-tools')
from mcp_servers.chrome_devtools import debug
title = debug.evaluate_script('document.title')
print(f'Page title: {title}')
"
```
### Debug Authenticated Session
```bash
# 1. Log into the site manually in Chrome (started with --remote-debugging-port=9222)
# 2. Then analyze the authenticated state:
uv run python -c "
import sys; sys.path.insert(0, 'dev-tools')
from mcp_servers.chrome_devtools import navigation, network, debug
# List open tabs
pages = navigation.list_pages()
print(pages)
# Get auth tokens from localStorage
tokens = debug.evaluate_script('JSON.stringify(localStorage)')
print(f'localStorage: {tokens}')
# See recent API calls
api_calls = network.get_api_requests()
print(api_calls)
"
```
## Available Tool Modules
### console
- `list_console_messages(types, page_size, page_idx)` - Get console output
- `get_console_message(message_id)` - Get specific message details
- `get_errors()` - Convenience: get error messages only
- `get_warnings()` - Convenience: get warnings only
### network
- `list_network_requests(resource_types, page_size, page_idx)` - List requests
- `get_network_request(request_id)` - Get full request/response details
- `get_failed_requests()` - Convenience: get 4xx/5xx requests
- `get_api_requests()` - Convenience: get XHR/fetch requests
- `get_slow_requests(threshold_ms)` - Convenience: get slow requests
### performance
- `start_trace(reload, auto_stop)` - Start recording trace
- `stop_trace()` - Stop and get trace data
- `get_insights()` - Get available insight sets
- `analyze_insight(insight_set_id, insight_name)` - AI-powered insight analysis
### debug
- `evaluate_script(expression)` - Execute JavaScript
### navigation
- `navigate_page(url, nav_type, ignore_cache, timeout)` - Navigate page
- `list_pages()` - List all tabs
- `select_page(page_idx, bring_to_front)` - Switch to tab by index
- `new_page(url, timeout)` - Open new tab
- `close_page(page_idx)` - Close tab by index
- `wait_for(text, timeout)` - Wait for text on page
## Red Flags
- Chrome not started with `--remote-debugging-port=9222`
- `CHROME_DEVTOOLS_URL` environment variable not set
- Port 9222 blocked by firewall
- Trying to use for screenshots (use browser-discovery instead)
- MCP server not installed (`npx chrome-devtools-mcp@latest`)
## See Also
- [reference.md](reference.md) - Full API documentation
- [cookbook/console-debugging.md](cookbook/console-debugging.md) - Console debugging patterns
- [cookbook/network-debugging.md](cookbook/network-debugging.md) - Network analysis patterns
- `browser-discovery` skill - For screenshots, basic automation
- [Chrome DevTools Protocol](https://chromedevtools.github.io/devtools-protocol/)
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.