Skip to content

Commit 9b28afb

Browse files
committed
chore: add a skill for chrome-devtools
1 parent adac7c5 commit 9b28afb

1 file changed

Lines changed: 151 additions & 0 deletions

File tree

Lines changed: 151 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,151 @@
1+
---
2+
name: chrome-devtools-cli
3+
description: Use this to skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.
4+
---
5+
6+
The `chrome-devtools-mcp` package includes a CLI interface that allows you to interact with the browser directly from your terminal. This is particularly useful for debugging or when you want an agent to generate scripts that automate browser actions.
7+
8+
## Getting started
9+
10+
Install the package globally to make the `chrome-devtools` command available:
11+
12+
```sh
13+
npm i chrome-devtools-mcp@latest -g
14+
chrome-devtools status # check if install worked.
15+
```
16+
17+
## How it works
18+
19+
The CLI acts as a client to a background `chrome-devtools-mcp` daemon.
20+
21+
- **Automatic Start**: The first time you call a tool (e.g., `list_pages`), the CLI automatically starts the MCP server and the browser in the background if they aren't already running.
22+
- **Persistence**: The same background instance is reused for subsequent commands, preserving the browser state (open pages, cookies, etc.).
23+
- **Manual Control**: You can explicitly manage the background process using `start`, `stop`, and `status`. The `start` command forwards all subsequent arguments to the underlying MCP server (e.g., `--headless`, `--userDataDir`).
24+
25+
Snapshots looks like this:
26+
27+
```
28+
uid=1_0 RootWebArea "Example Domain" url="https://example.com/"
29+
uid=1_1 heading "Example Domain" level="1"
30+
uid=1_2 StaticText "This domain is for use in documentation examples without needing permission. Avoid use in operations."
31+
uid=1_3 link "Learn more" url="https://iana.org/domains/example"
32+
uid=1_4 StaticText "Learn more
33+
```
34+
35+
## Command Usage
36+
37+
The CLI supports all tools available in the Chrome DevTools MCP by default.
38+
39+
```sh
40+
chrome-devtools <tool> [arguments] [flags]
41+
```
42+
43+
- **Required Arguments**: Passed as positional arguments.
44+
- **Optional Arguments**: Passed as flags (e.g., `--filePath`, `--fullPage`).
45+
46+
Each command accepts `--format=json` to output in JSON format. The default format is Markdown (`md`).
47+
48+
## Input Automation (<uid> from snapshot)
49+
50+
```bash
51+
chrome-devtools take_snapshot --help # Help message for commands, works for any command.
52+
chrome-devtools take_snapshot # Take a text snapshot of the page to get UIDs for elements
53+
chrome-devtools click "id" # Clicks on the provided element
54+
chrome-devtools click "id" --dblClick true --includeSnapshot true # Double clicks and returns a snapshot
55+
chrome-devtools drag "src" "dst" # Drag an element onto another element
56+
chrome-devtools drag "src" "dst" --includeSnapshot true # Drag an element and return a snapshot
57+
chrome-devtools fill "id" "text" # Type text into an input or select an option
58+
chrome-devtools fill "id" "text" --includeSnapshot true # Fill an element and return a snapshot
59+
chrome-devtools fill_form "json" # Fill out multiple form elements at once
60+
chrome-devtools fill_form "json" --includeSnapshot true # Fill a form and return a snapshot
61+
chrome-devtools handle_dialog accept # Handle a browser dialog
62+
chrome-devtools handle_dialog dismiss --promptText "hi" # Dismiss a dialog with prompt text
63+
chrome-devtools hover "id" # Hover over the provided element
64+
chrome-devtools hover "id" --includeSnapshot true # Hover over an element and return a snapshot
65+
chrome-devtools press_key "Enter" # Press a key or key combination
66+
chrome-devtools press_key "Control+A" --includeSnapshot true # Press a key and return a snapshot
67+
chrome-devtools type_text "hello" # Type text using keyboard into a focused input
68+
chrome-devtools type_text "hello" --submitKey "Enter" # Type text and press a submit key
69+
chrome-devtools upload_file "id" "file.txt" # Upload a file through a provided element
70+
chrome-devtools upload_file "id" "file.txt" --includeSnapshot true # Upload a file and return a snapshot
71+
```
72+
73+
## Navigation
74+
75+
```bash
76+
chrome-devtools close_page 1 # Closes the page by its index
77+
chrome-devtools list_pages # Get a list of pages open in the browser
78+
chrome-devtools navigate_page --url "https://example.com" # Navigates the currently selected page to a URL
79+
chrome-devtools navigate_page --type "reload" --ignoreCache true # Reload page ignoring cache
80+
chrome-devtools navigate_page --url "https://example.com" --timeout 5000 # Navigate with a timeout
81+
chrome-devtools navigate_page --handleBeforeUnload "accept" # Handle before unload dialog
82+
chrome-devtools navigate_page --type "back" --initScript "foo()" # Navigate back and run an init script
83+
chrome-devtools new_page "https://example.com" # Creates a new page
84+
chrome-devtools new_page "https://example.com" --background true --timeout 5000 # Create new page in background
85+
chrome-devtools new_page "https://example.com" --isolatedContext "ctx" # Create new page with isolated context
86+
chrome-devtools select_page 1 # Select a page as a context for future tool calls
87+
chrome-devtools select_page 1 --bringToFront true # Select a page and bring it to front
88+
chrome-devtools wait_for "Success!" # Wait for the specified text to appear on the page
89+
chrome-devtools wait_for "Success!" --timeout 10000 # Wait for text with a timeout
90+
```
91+
92+
## Emulation
93+
94+
```bash
95+
chrome-devtools emulate --networkConditions "Offline" # Emulate network conditions
96+
chrome-devtools emulate --cpuThrottlingRate 4 --geolocation "0,0" # Emulate CPU throttling and geolocation
97+
chrome-devtools emulate --colorScheme "dark" --viewport "1920x1080" # Emulate color scheme and viewport
98+
chrome-devtools emulate --userAgent "Mozilla/5.0..." # Emulate user agent
99+
chrome-devtools resize_page 1920 1080 # Resizes the selected page's window
100+
```
101+
102+
## Performance
103+
104+
```bash
105+
chrome-devtools performance_analyze_insight "1" "LCPBreakdown" # Get more details on a specific Performance Insight
106+
chrome-devtools performance_start_trace true false # Starts a performance trace recording
107+
chrome-devtools performance_start_trace true true --filePath t.gz # Start trace and save to a file
108+
chrome-devtools performance_stop_trace # Stops the active performance trace
109+
chrome-devtools performance_stop_trace --filePath "t.json" # Stop trace and save to a file
110+
chrome-devtools take_memory_snapshot "./snap.heapsnapshot" # Capture a memory heapsnapshot
111+
```
112+
113+
## Network
114+
115+
```bash
116+
chrome-devtools get_network_request # Get the currently selected network request
117+
chrome-devtools get_network_request --reqid 1 --requestFilePath req.json # Get request by id and save to file
118+
chrome-devtools get_network_request --responseFilePath res.json # Save response body to file
119+
chrome-devtools list_network_requests # List all network requests
120+
chrome-devtools list_network_requests --pageSize 50 --pageIdx 0 # List network requests with pagination
121+
chrome-devtools list_network_requests --resourceTypes '["Fetch"]' # Filter requests by resource type
122+
chrome-devtools list_network_requests --includePreservedRequests true # Include preserved requests
123+
```
124+
125+
## Debugging & Inspection
126+
127+
```bash
128+
chrome-devtools evaluate_script "() => document.title" # Evaluate a JavaScript function on the page
129+
evaluate_script "(a) => a.innerText" --args 1_4 # Evaluate JS with UID arguments
130+
chrome-devtools get_console_message 1 # Gets a console message by its ID
131+
chrome-devtools lighthouse_audit --mode "navigation" # Run Lighthouse audit for navigation
132+
chrome-devtools lighthouse_audit --mode "snapshot" --device "mobile" # Run Lighthouse audit for a snapshot on mobile
133+
chrome-devtools lighthouse_audit --outputDirPath ./out # Run Lighthouse audit and save reports
134+
chrome-devtools list_console_messages # List all console messages
135+
chrome-devtools list_console_messages --pageSize 20 --pageIdx 1 # List console messages with pagination
136+
chrome-devtools list_console_messages --types '["error"]' # Filter console messages by type
137+
chrome-devtools list_console_messages --includePreservedMessages true # Include preserved messages
138+
chrome-devtools take_screenshot # Take a screenshot of the page viewport
139+
chrome-devtools take_screenshot --fullPage true --format "jpeg" --quality 80 # Take a full page screenshot as JPEG with quality
140+
chrome-devtools take_screenshot --uid "id" --filePath "s.png" # Take a screenshot of an element
141+
chrome-devtools take_snapshot # Take a text snapshot of the page from the a11y tree
142+
chrome-devtools take_snapshot --verbose true --filePath "s.txt" # Take a verbose snapshot and save to file
143+
```
144+
145+
## Service Management
146+
147+
```bash
148+
chrome-devtools start # Start or restart chrome-devtools-mcp
149+
chrome-devtools status # Checks if chrome-devtools-mcp is running
150+
chrome-devtools stop # Stop chrome-devtools-mcp if any
151+
```

0 commit comments

Comments
 (0)