Chrome-Extension Agent Skill

Name: Chrome-Extension
Author: rish2jain

Chrome extension development guide. Use for creating browser extensions, manifest files, background scripts, content scripts, Chrome APIs…

Install this skill Read the source first Free Written by rish2jain

Context cost: 167.6k tokensestimated from the bundle, loaded when it triggers
Bundle: 14 files · 670.5 kBtext throughout, nothing executable
Licence: not declarednone named by its author
Last change: —no release on file
Servers it uses: Noneruns standalone

What it does

Chrome extension development guide. Use for creating browser extensions, manifest files, background scripts, content scripts, Chrome APIs, and publishing extensions on Chrome Web Store.

What this skill changes about the agent has not been set out here as a list. Its SKILL.md, shown below, says it in the author’s own words.

automationbrowser

Filed under

Web, Search & Scraping

The skill itself

A skill is instructions the model reads, so you can see what you are getting: below is the start of its SKILL.md. The front matter loads with every session, the body loads when the skill triggers, and the whole file comes with the install.

SKILL.md64.8 kB · preview

--- name: chrome-extension ---

6# Chrome-Extension Skill

8Comprehensive assistance with chrome-extension development, generated from official documentation.

10## When to Use This Skill

12This skill should be triggered when:

13- Working with chrome-extension

14- Asking about chrome-extension features or APIs

15- Implementing chrome-extension solutions

16- Debugging chrome-extension code

17- Learning chrome-extension best practices

19## Quick Reference

21### Common Patterns

23**Pattern 1:** Note: The Tabs API can be used by the service worker and extension pages, but not content scripts. Description Use the chrome.tabs API to interact with the browser's tab system. You can use this API to create, modify, and rearrange tabs in the browser. The Tabs API not only offers features for manipulating and managing tabs, but can also detect the language of the tab, take a screenshot, and communicate with a tab's content scripts. Permissions Most features don't require any permissions to use. For example: creating a new tab, reloading a tab, navigating to another URL, etc. There are three permissions developers should be aware of when working with the Tabs API. The "tabs" permission This permission does not give access to the chrome.tabs namespace. Instead, it grants an extension the ability to call tabs.query() against four sensitive properties on tabs.Tab instances: url, pendingUrl, title, and favIconUrl. { "name": "My extension", ... "permissions": [ "tabs" ], ... } Host permissions Host permissions allow an extension to read and query a matching tab's four sensitive tabs.Tab properties. They can also interact directly with the matching tabs using methods such as tabs.captureVisibleTab(), scripting.executeScript(), scripting.insertCSS(), and scripting.removeCSS(). { "name": "My extension", ... "host_permissions": [ "http://*/*", "https://*/*" ], ... } The "activeTab" permission activeTab grants an extension temporary host permission for the current tab in response to a user invocation. Unlike host permissions, activeTab does not trigger any warnings. { "name": "My extension", ... "permissions": [ "activeTab" ], ... } Use cases The following sections demonstrate some common use cases. Open an extension page in a new tab A common pattern for extensions is to open an onboarding page in a new tab when the extension is installed. The following example shows how to do this. background.js: chrome.runtime.onInstalled.addListener(({reason}) => { if (reason === 'install') { chrome.tabs.create({ url: "onboarding.html" }); } }); Note: This example doesn't require any permissions. Get the current tab This example demonstrates how an extension's service worker can retrieve the active tab from the currently-focused window (or most recently-focused window, if no Chrome windows are focused). This can usually be thought of as the user's current tab. async function getCurrentTab() { let queryOptions = { active: true, lastFocusedWindow: true }; // tab will either be a tabs.Tab instance or undefined. let [tab] = await chrome.tabs.query(queryOptions); return tab; } function getCurrentTab(callback) { let queryOptions = { active: true, lastFocusedWindow: true }; chrome.tabs.query(queryOptions, ([tab]) => { if (chrome.runtime.lastError) console.error(chrome.runtime.lastError); // tab will either be a tabs.Tab instance or undefined. callback(tab); }); } Mute the specified tab This example shows how an extension can toggle the muted state for a given tab. async function toggleMuteState(tabId) { const tab = await chrome.tabs.get(tabId); const muted = !tab.mutedInfo.muted; await chrome.tabs.update(tabId, {muted}); console.log(Tab ${tab.id} is ${muted ? "muted" : "unmuted"}); } function toggleMuteState(tabId) { chrome.tabs.get(tabId, async (tab) => { let muted = !tab.mutedInfo.muted; await chrome.tabs.update(tabId, { muted }); console.log(Tab ${tab.id} is ${ muted ? "muted" : "unmuted" }); }); } Move the current tab to the first position when clicked This example shows how to move a tab while a drag may or may not be in progress. While this example uses chrome.tabs.move, you can use the same waiting pattern for other calls that modify tabs while a drag is in progress. chrome.tabs.onActivated.addListener(moveToFirstPosition); async function moveToFirstPosition(activeInfo) { try { await chrome.tabs.move(activeInfo.tabId, {index: 0}); console.log("Success."); } catch (error) { if (error == "Error: Tabs cannot be edited right now (user may be dragging a tab).") { setTimeout(() => moveToFirstPosition(activeInfo), 50); } else { console.error(error); } } } Important: Using catch(error) in a Promise is a way to ensure that an error that otherwise populates chrome.runtime.lastError is not unchecked. chrome.tabs.onActivated.addListener(moveToFirstPositionMV2); function moveToFirstPositionMV2(activeInfo) { chrome.tabs.move(activeInfo.tabId, { index: 0 }, () => { if (chrome.runtime.lastError) { const error = chrome.runtime.lastError; if (error == "Error: Tabs cannot be edited right now (user may be dragging a tab).") { setTimeout(() => moveToFirstPositionMV2(activeInfo), 50); } else { console.error(error); } } else { console.log("Success."); } }); } Pass a message to a selected tab's content script This example demonstrates how an extension's service worker can communicate with content scripts in specific browser tabs using tabs.sendMessage(). function sendMessageToActiveTab(message) { const [tab] = await chrome.tabs.query({ active: true, lastFocusedWindow: true }); const response = await chrome.tabs.sendMessage(tab.id, message); // TODO: Do something with the response. } Extension examples For more Tabs API extensions demos, explore any of the following: Manifest V2 - Tabs API extensions. Manifest V3 - Tabs Manager. Types MutedInfo Chrome 46+ The tab's muted state and the reason for the last state change. Properties extensionId string optional The ID of the extension that changed the muted state. Not set if an extension was not the reason the muted state last changed. muted boolean Whether the tab is muted (prevented from playing sound). The tab may be muted even if it has not played or is not currently playing sound. Equivalent to whether the 'muted' audio indicator is showing. reason MutedInfoReason optional The reason the tab was muted or unmuted. Not set if the tab's mute state has never been changed. MutedInfoReason Chrome 46+ An event that caused a muted state change. Enum "user" A user input action set the muted state."capture" Tab capture was started, forcing a muted state change."extension" An extension, identified by the extensionId field, set the muted state. Tab Properties active boolean Whether the tab is active in its window. Does not necessarily mean the window is focused. audible boolean optional Chrome 45+ Whether the tab has produced sound over the past couple of seconds (but it might not be heard if also muted). Equivalent to whether the 'speaker audio' indicator is showing. autoDiscardable boolean Chrome 54+ Whether the tab can be discarded automatically by the browser when resources are low. discarded boolean Chrome 54+ Whether the tab is discarded. A discarded tab is one whose content has been unloaded from memory, but is still visible in the tab strip. Its content is reloaded the next time it is activated. favIconUrl string optional The URL of the tab's favicon. This property is only present if the extension has the "tabs" permission or has host permissions for the page. It may also be an empty string if the tab is loading. frozen boolean Chrome 132+ Whether the tab is frozen. A frozen tab cannot execute tasks, including event handlers or timers. It is visible in the tab strip and its content is loaded in memory. It is unfrozen on activation. groupId number Chrome 88+ The ID of the group that the tab belongs to. height number optional The height of the tab in pixels. highlighted boolean Whether the tab is highlighted. id number optional The ID of the tab. Tab IDs are unique within a browser session. Under some circumstances a tab may not be assigned an ID; for example, when querying foreign tabs using the sessions API, in which case a session ID may be present. Tab ID can also be set to chrome.tabs.TAB_ID_NONE for apps and devtools windows. incognito boolean Whether the tab is in an incognito window. index number The zero-based index of the tab within its window. lastAccessed number Chrome 121+ The last time the tab became active in its window as the number of milliseconds since epoch. mutedInfo MutedInfo optional Chrome 46+ The tab's muted state and the reason for the last state change. openerTabId number optional The ID of the tab that opened this tab, if any. This property is only present if the opener tab still exists. pendingUrl string optional Chrome 79+ The URL the tab is navigating to, before it has committed. This property is only present if the extension has the "tabs" permission or has host permissions for the page and there is a pending navigation. pinned boolean Whether the tab is pinned. selected boolean Deprecated Please use tabs.Tab.highlighted.Whether the tab is selected. sessionId string optional The session ID used to uniquely identify a tab obtained from the sessions API. status TabStatus optional The tab's loading status. title string optional The title of the tab. This property is only present if the extension has the "tabs" permission or has host permissions for the page. url string optional The last committed URL of the main frame of the tab. This property is only present if the extension has the "tabs" permission or has host permissions for the page. May be an empty string if the tab has not yet committed. See also Tab.pendingUrl. width number optional The width of the tab in pixels. windowId number The ID of the window that contains the tab. TabStatus Chrome 44+ The tab's loading status. Enum "unloaded" "loading" "complete" WindowType Chrome 44+ The type of window. Enum "normal" "popup" "panel" "app" "devtools" ZoomSettings Defines how zoom changes in a tab are handled and at what scope. Properties defaultZoomFactor number optional Chrome 43+ Used to return the default zoom level for the current tab in calls to tabs.getZoomSettings. mode ZoomSettingsMode optional Defines how zoom changes are handled, i.e., which entity is responsible for the actual scaling of the page; defaults to automatic. scope ZoomSettingsScope optional Defines whether zoom changes persist for the page's origin, or only take effect in this tab; defaults to per-origin when in automatic mode, and per-tab otherwise. ZoomSettingsMode Chrome 44+ Defines how zoom changes are handled, i.e., which entity is responsible for the actual scaling of the page; defaults to automatic. Enum "automatic" Zoom changes are handled automatically by the browser."manual" Overrides the automatic handling of zoom changes. The onZoomChange event will still be dispatched, and it is the extension's responsibility to listen for this event and manually scale the page. This mode does not support per-origin zooming, and thus ignores the scope zoom setting and assumes per-tab."disabled" Disables all zooming in the tab. The tab reverts to the default zoom level, and all attempted zoom changes are ignored. ZoomSettingsScope Chrome 44+ Defines whether zoom changes persist for the page's origin, or only take effect in this tab; defaults to per-origin when in automatic mode, and per-tab otherwise. Enum "per-origin" Zoom changes persist in the zoomed page's origin, i.e., all other tabs navigated to that same origin are zoomed as well. Moreover, per-origin zoom changes are saved with the origin, meaning that when navigating to other pages in the same origin, they are all zoomed to the same zoom factor. The per-origin scope is only available in the automatic mode."per-tab" Zoom changes only take effect in this tab, and zoom changes in other tabs do not affect the zooming of this tab. Also, per-tab zoom changes are reset on navigation; navigating a tab always loads pages with their per-origin zoom factors. Properties MAX_CAPTURE_VISIBLE_TAB_CALLS_PER_SECOND Chrome 92+ The maximum number of times that captureVisibleTab can be called per second. captureVisibleTab is expensive and should not be called too often. Value 2 TAB_ID_NONE Chrome 46+ An ID that represents the absence of a browser tab. Value -1 TAB_INDEX_NONE Chrome 123+ An index that represents the absence of a tab index in a tab_strip. Value -1 Methods captureVisibleTab() chrome.tabs.captureVisibleTab( windowId?: number, options?: ImageDetails,): Promise<string> Captures the visible area of the currently active tab in the specified window. In order to call this method, the extension must have either the <all_urls> permission or the activeTab permission. In addition to sites that extensions can normally access, this method allows extensions to capture sensitive sites that are otherwise restricted, including chrome:-scheme pages, other extensions' pages, and data: URLs. These sensitive sites can only be captured with the activeTab permission. File URLs may be captured only if the extension has been granted file access. Parameters windowId number optional The target window. Defaults to the current window. options ImageDetails optional Returns Promise<string> Chrome 88+ connect() chrome.tabs.connect( tabId: number, connectInfo?: object,): runtime.Port Connects to the content script(s) in the specified tab. The runtime.onConnect event is fired in each content script running in the specified tab for the current extension. For more details, see Content Script Messaging. Parameters tabId number connectInfo object optional documentId string optional Chrome 106+ Open a port to a specific document identified by documentId instead of all frames in the tab. frameId number optional Open a port to a specific frame identified by frameId instead of all frames in the tab. name string optional Is passed into onConnect for content scripts that are listening for the connection event. Returns runtime.Port A port that can be used to communicate with the content scripts running in the specified tab. The port's runtime.Port event is fired if the tab closes or does not exist. create() chrome.tabs.create( createProperties: object,): Promise<Tab> Creates a new tab. Parameters createProperties object active boolean optional Whether the tab should become the active tab in the window. Does not affect whether the window is focused (see windows.update). Defaults to true. index number optional The position the tab should take in the window. The provided value is clamped to between zero and the number of tabs in the window. openerTabId number optional The ID of the tab that opened this tab. If specified, the opener tab must be in the same window as the newly created tab. pinned boolean optional Whether the tab should be pinned. Defaults to false selected boolean optional Deprecated Please use active.Whether the tab should become the selected tab in the window. Defaults to true url string optional The URL to initially navigate the tab to. Fully-qualified URLs must include a scheme (i.e., 'http://www.google.com', not 'www.google.com'). Relative URLs are relative to the current page within the extension. Defaults to the New Tab Page. windowId number optional The window in which to create the new tab. Defaults to the current window. Returns Promise<Tab> Chrome 88+ detectLanguage() chrome.tabs.detectLanguage( tabId?: number,): Promise<string> Detects the primary language of the content in a tab. Parameters tabId number optional Defaults to the active tab of the current window. Returns Promise<string> Chrome 88+ discard() Chrome 54+ chrome.tabs.discard( tabId?: number,): Promise<Tab | undefined> Discards a tab from memory. Discarded tabs are still visible on the tab strip and are reloaded when activated. Parameters tabId number optional The ID of the tab to be discarded. If specified, the tab is discarded unless it is active or already discarded. If omitted, the browser discards the least important tab. This can fail if no discardable tabs exist. Returns Promise<Tab | undefined> Chrome 88+ duplicate() chrome.tabs.duplicate( tabId: number,): Promise<Tab | undefined> Duplicates a tab. Parameters tabId number The ID of the tab to duplicate. Returns Promise<Tab | undefined> Chrome 88+ get() chrome.tabs.get( tabId: number,): Promise<Tab> Retrieves details about the specified tab. Parameters tabId number Returns Promise<Tab> Chrome 88+ getCurrent() chrome.tabs.getCurrent(): Promise<Tab | undefined> Gets the tab that this script call is being made from. Returns undefined if called from a non-tab context (for example, a background page or popup view). Returns Promise<Tab | undefined> Chrome 88+ getZoom() chrome.tabs.getZoom( tabId?: number,): Promise<number> Gets the current zoom factor of a specified tab. Parameters tabId number optional The ID of the tab to get the current zoom factor from; defaults to the active tab of the current window. Returns Promise<number> Chrome 88+ getZoomSettings() chrome.tabs.getZoomSettings( tabId?: number,): Promise<ZoomSettings> Gets the current zoom settings of a specified tab. Parameters tabId number optional The ID of the tab to get the current zoom settings from; defaults to the active tab of the current window. Returns Promise<ZoomSettings> Chrome 88+ goBack() Chrome 72+ chrome.tabs.goBack( tabId?: number,): Promise<void> Go back to the previous page, if one is available. Parameters tabId number optional The ID of the tab to navigate back; defaults to the selected tab of the current window. Returns Promise<void> Chrome 88+ goForward() Chrome 72+ chrome.tabs.goForward( tabId?: number,): Promise<void> Go foward to the next page, if one is available. Parameters tabId number optional The ID of the tab to navigate forward; defaults to the selected tab of the current window. Returns Promise<void> Chrome 88+ group() Chrome 88+ chrome.tabs.group( options: object,): Promise<number> Adds one or more tabs to a specified group, or if no group is specified, adds the given tabs to a newly created group. Parameters options object createProperties object optional Configurations for creating a group. Cannot be used if groupId is already specified. windowId number optional The window of the new group. Defaults to the current window. groupId number optional The ID of the group to add the tabs to. If not specified, a new group will be created. tabIds number | [number, ...number[]] The tab ID or list of tab IDs to add to the specified group. Returns Promise<number> highlight() chrome.tabs.highlight( highlightInfo: object,): Promise<windows.Window> Highlights the given tabs and focuses on the first of group. Will appear to do nothing if the specified tab is currently active. Parameters highlightInfo object tabs number | number[] One or more tab indices to highlight. windowId number optional The window that contains the tabs. Returns Promise<windows.Window> Chrome 88+ move() chrome.tabs.move( tabIds: number | number[], moveProperties: object,): Promise<Tab | Tab[]> Moves one or more tabs to a new position within its window, or to a new window. Note that tabs can only be moved to and from normal (window.type === "normal") windows. Parameters tabIds number | number[] The tab ID or list of tab IDs to move. moveProperties object index number The position to move the window to. Use -1 to place the tab at the end of the window. windowId number optional Defaults to the window the tab is currently in. Returns Promise<Tab | Tab[]> Chrome 88+ query() chrome.tabs.query( queryInfo: object,): Promise<Tab[]> Gets all tabs that have the specified properties, or all tabs if no properties are specified. Parameters queryInfo object active boolean optional Whether the tabs are active in their windows. audible boolean optional Chrome 45+ Whether the tabs are audible. autoDiscardable boolean optional Chrome 54+ Whether the tabs can be discarded automatically by the browser when resources are low. currentWindow boolean optional Whether the tabs are in the current window. discarded boolean optional Chrome 54+ Whether the tabs are discarded. A discarded tab is one whose content has been unloaded from memory, but is still visible in the tab strip. Its content is reloaded the next time it is activated. frozen boolean optional Chrome 132+ Whether the tabs are frozen. A frozen tab cannot execute tasks, including event handlers or timers. It is visible in the tab strip and its content is loaded in memory. It is unfrozen on activation. groupId number optional Chrome 88+ The ID of the group that the tabs are in, or tabGroups.TAB_GROUP_ID_NONE for ungrouped tabs. highlighted boolean optional Whether the tabs are highlighted. index number optional The position of the tabs within their windows. lastFocusedWindow boolean optional Whether the tabs are in the last focused window. muted boolean optional Chrome 45+ Whether the tabs are muted. pinned boolean optional Whether the tabs are pinned. splitViewId number optional Chrome 140+ The ID of the Split View that the tabs are in, or tabs.SPLIT_VIEW_ID_NONE for tabs that aren't in a Split View. status TabStatus optional The tab loading status. title string optional Match page titles against a pattern. This property is ignored if the extension does not have the "tabs" permission or host permissions for the page. url string | string[] optional Match tabs against one or more URL patterns. Fragment identifiers are not matched. This property is ignored if the extension does not have the "tabs" permission or host permissions for the page. windowId number optional The ID of the parent window, or windows.WINDOW_ID_CURRENT for the current window. windowType WindowType optional The type of window the tabs are in. Returns Promise<Tab[]> Chrome 88+ reload() chrome.tabs.reload( tabId?: number, reloadProperties?: object,): Promise<void> Reload a tab. Parameters tabId number optional The ID of the tab to reload; defaults to the selected tab of the current window. reloadProperties object optional bypassCache boolean optional Whether to bypass local caching. Defaults to false. Returns Promise<void> Chrome 88+ remove() chrome.tabs.remove( tabIds: number | number[],): Promise<void> Closes one or more tabs. Parameters tabIds number | number[] The tab ID or list of tab IDs to close. Returns Promise<void> Chrome 88+ sendMessage() chrome.tabs.sendMessage( tabId: number, message: any, options?: object,): Promise<any> Sends a single message to the content script(s) in the specified tab, with an optional callback to run when a response is sent back. The runtime.onMessage event is fired in each content script running in the specified tab for the current extension. Parameters tabId number message any The message to send. This message should be a JSON-ifiable object. options object optional documentId string optional Chrome 106+ Send a message to a specific document identified by documentId instead of all frames in the tab. frameId number optional Send a message to a specific frame identified by frameId instead of all frames in the tab. Returns Promise<any> Chrome 99+ setZoom() chrome.tabs.setZoom( tabId?: number, zoomFactor: number,): Promise<void> Zooms a specified tab. Parameters tabId number optional The ID of the tab to zoom; defaults to the active tab of the current window. zoomFactor number The new zoom factor. A value of 0 sets the tab to its current default zoom factor. Values greater than 0 specify a (possibly non-default) zoom factor for the tab. Returns Promise<void> Chrome 88+ setZoomSettings() chrome.tabs.setZoomSettings( tabId?: number, zoomSettings: ZoomSettings,): Promise<void> Sets the zoom settings for a specified tab, which define how zoom changes are handled. These settings are reset to defaults upon navigating the tab. Parameters tabId number optional The ID of the tab to change the zoom settings for; defaults to the active tab of the current window. zoomSettings ZoomSettings Defines how zoom changes are handled and at what scope. Returns Promise<void> Chrome 88+ ungroup() Chrome 88+ chrome.tabs.ungroup( tabIds: number | [number, ...number[]],): Promise<void> Removes one or more tabs from their respective groups. If any groups become empty, they are deleted. Parameters tabIds number | [number, ...number[]] The tab ID or list of tab IDs to remove from their respective groups. Returns Promise<void> update() chrome.tabs.update( tabId?: number, updateProperties: object,): Promise<Tab | undefined> Modifies the properties of a tab. Properties that are not specified in updateProperties are not modified. Parameters tabId number optional Defaults to the selected tab of the current window. updateProperties object active boolean optional Whether the tab should be active. Does not affect whether the window is focused (see windows.update). autoDiscardable boolean optional Chrome 54+ Whether the tab should be discarded automatically by the browser when resources are low. highlighted boolean optional Adds or removes the tab from the current selection. muted boolean optional Chrome 45+ Whether the tab should be muted. openerTabId number optional The ID of the tab that opened this tab. If specified, the opener tab must be in the same window as this tab. pinned boolean optional Whether the tab should be pinned. selected boolean optional Deprecated Please use highlighted.Whether the tab should be selected. url string optional A URL to navigate the tab to. JavaScript URLs are not supported; use scripting.executeScript instead. Returns Promise<Tab | undefined> Chrome 88+ Events onActivated chrome.tabs.onActivated.addListener( callback: function,) Fires when the active tab in a window changes. Note that the tab's URL may not be set at the time this event fired, but you can listen to onUpdated events so as to be notified when a URL is set. Parameters callback function The callback parameter looks like: (activeInfo: object) => void activeInfo object tabId number The ID of the tab that has become active. windowId number The ID of the window the active tab changed inside of. onAttached chrome.tabs.onAttached.addListener( callback: function,) Fired when a tab is attached to a window; for example, because it was moved between windows. Parameters callback function The callback parameter looks like: (tabId: number, attachInfo: object) => void tabId number attachInfo object newPosition number newWindowId number onCreated chrome.tabs.onCreated.addListener( callback: function,) Fired when a tab is created. Note that the tab's URL and tab group membership may not be set at the time this event is fired, but you can listen to onUpdated events so as to be notified when a URL is set or the tab is added to a tab group. Parameters callback function The callback parameter looks like: (tab: Tab) => void tab Tab onDetached chrome.tabs.onDetached.addListener( callback: function,) Fired when a tab is detached from a window; for example, because it was moved between windows. Parameters callback function The callback parameter looks like: (tabId: number, detachInfo: object) => void tabId number detachInfo object oldPosition number oldWindowId number onHighlighted chrome.tabs.onHighlighted.addListener( callback: function,) Fired when the highlighted or selected tabs in a window changes. Parameters callback function The callback parameter looks like: (highlightInfo: object) => void highlightInfo object tabIds number[] All highlighted tabs in the window. windowId number The window whose tabs changed. onMoved chrome.tabs.onMoved.addListener( callback: function,) Fired when a tab is moved within a window. Only one move event is fired, representing the tab the user directly moved. Move events are not fired for the other tabs that must move in response to the manually-moved tab. This event is not fired when a tab is moved between windows; for details, see tabs.onDetached. Parameters callback function The callback parameter looks like: (tabId: number, moveInfo: object) => void tabId number moveInfo object fromIndex number toIndex number windowId number onRemoved chrome.tabs.onRemoved.addListener( callback: function,) Fired when a tab is closed. Parameters callback function The callback parameter looks like: (tabId: number, removeInfo: object) => void tabId number removeInfo object isWindowClosing boolean True when the tab was closed because its parent window was closed. windowId number The window whose tab is closed. onReplaced chrome.tabs.onReplaced.addListener( callback: function,) Fired when a tab is replaced with another tab due to prerendering or instant. Parameters callback function The callback parameter looks like: (addedTabId: number, removedTabId: number) => void addedTabId number removedTabId number onUpdated chrome.tabs.onUpdated.addListener( callback: function,) Fired when a tab is updated. Parameters callback function The callback parameter looks like: (tabId: number, changeInfo: object, tab: Tab) => void tabId number changeInfo object audible boolean optional Chrome 45+ The tab's new audible state. autoDiscardable boolean optional Chrome 54+ The tab's new auto-discardable state. discarded boolean optional Chrome 54+ The tab's new discarded state. favIconUrl string optional The tab's new favicon URL. frozen boolean optional Chrome 132+ The tab's new frozen state. groupId number optional Chrome 88+ The tab's new group. mutedInfo MutedInfo optional Chrome 46+ The tab's new muted state and the reason for the change. pinned boolean optional The tab's new pinned state. splitViewId number optional Chrome 140+ The tab's new Split View. status TabStatus optional The tab's loading status. title string optional Chrome 48+ The tab's new title. url string optional The tab's URL if it has changed. tab Tab onZoomChange chrome.tabs.onZoomChange.addListener( callback: function,) Fired when a tab is zoomed. Parameters callback function The callback parameter looks like: (ZoomChangeInfo: object) => void ZoomChangeInfo object newZoomFactor number oldZoomFactor number tabId number zoomSettings ZoomSettings

This is a preview of SKILL.md. Download or install the skill to get the whole thing.

In the file

SKILL.md9,446 words

Files14

Licencenot declared

Why you can read it

Nothing in a skill executes. The client loads the text and the model follows it, so a skill can be audited the way a runbook is — by reading it.

What it costs in context

Skills are not billed by the call. They are paid for in context: every token the instructions occupy is a token your code, your diff and your conversation cannot use. Here is what this one takes and when it takes it.

≈60

always loaded

The name and description, so the model knows the skill exists and when to reach for it.

167,565

on trigger

The instruction body and 13 supporting files, read only when the skill fires.

83.8%

of a 200k window

Ten skills this size would not fit in the window together.

050k100k150k200k context window

167.6k tokens, estimated from the bundle at four bytes to the token, held for the rest of the session once it triggers. Heavy. Teams tend to install this one per project rather than globally, and load it only when the job comes up.

Servers bill, skills cost

A server charges by the month. A skill charges once per session, in context, and then keeps charging it for as long as the session lives.

Before and after

The same question, put to the same model twice: once as it comes, and once with these instructions loaded.

No worked example has been published for this skill yet.

The procedure it runs

The procedure has not been set out here step by step. It is in the body of its SKILL.md: the start of it is shown above, and the whole file comes with the install.

Prose, not code

These steps are written for a model to follow, not executed by a runtime. It can still be told to skip one, and it will say so when it does.

Servers it uses

None. This skill calls no MCP servers at all.

Everything it needs is in the instructions, so it works in a project with nothing connected — the model reads the file and changes how it works with what it can already reach.

Its SKILL.md does not declare which tools it asks the agent for, so what it touches is whatever the instructions themselves ask for — read them before you install it.

What it asks for

Writes filesnot declared

Network accessnot declared

This SKILL.md carries no allowed-tools line, so neither is declared. A skill grants no permissions of its own — it can only ask for tools your client already has.

What it will not do

Every skill is narrow, and the useful ones say where they stop. These are the jobs this one is the wrong tool for.

What this skill is not for has not been published here. Nothing is implied by that: it is a section the author has not filled in.

If this is not it

2263 other skills in Web, Search & Scraping

What is in the bundle

14 files, 670.5 kB on disk. A bundle is text throughout: the instructions the model reads, plus the templates it fills in.

SKILL.md64.8 kB
references/apis.md294.0 kB
references/background_scripts.md16.2 kB
references/best_practices.md7.7 kB
references/content_scripts.md41.6 kB
references/examples.md0.3 kB
references/getting_started.md29.1 kB
references/index.md0.7 kB
references/manifest.md90.6 kB
references/other.md62.4 kB
references/runtime.md3.2 kB
references/testing.md4.2 kB
references/user_interface.md52.6 kB
references/webstore.md3.1 kB

What is not in it

No dependencies and nothing executable: a skill is text the agent reads, so the bundle is 14 files you can review in full before installing.

Install

Installing copies the bundle into your project. Nothing runs at install time — the files sit on disk until the model reads them.

# Chrome-Extension · 167.6k tokens when loaded · macOS, Linux
mkdir -p .claude/skills && t=$(mktemp -d) &&
  curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/chrome-extension/bundle.tar.gz &&
  tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/chrome-extension" ] &&
  { [ ! -e .claude/skills/chrome-extension ] || { mv .claude/skills/chrome-extension "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } &&
  mv "$t/chrome-extension" .claude/skills/ && echo "Installed .claude/skills/chrome-extension"

On Windows, or any OS with Node 20+

npx mcprush@latest skill add rish2jain/chrome-extension

Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither. Writes to .claude/skills/chrome-extension/ in the current project. For every project instead, run mkdir -p ~/.claude/skills && t=$(mktemp -d) && curl -fsSL -o "$t/bundle.tar.gz" https://mcprush.com/api/skills/chrome-extension/bundle.tar.gz && tar -xzf "$t/bundle.tar.gz" -C "$t" && [ -d "$t/chrome-extension" ] && { [ ! -e ~/.claude/skills/chrome-extension ] || { mv ~/.claude/skills/chrome-extension "$t/.previous" && echo "Previous copy moved to $t/.previous"; }; } && mv "$t/chrome-extension" ~/.claude/skills/ && echo "Installed ~/.claude/skills/chrome-extension" (macOS, Linux) — or add --global to the npx line. The curl line replaces .claude/skills/chrome-extension/ only after the download succeeds, so files left there by another skill of the same name, or by an older release, do not mix in. A copy already there is moved aside, not deleted, and the line prints where.

Which clients pick it up on their own

A skill is a folder of text. Most of these read a skills folder and pick it up without being told; the rest take the same folder another way — an upload in the app, a parameter on an API call — and then choose it by its description just the same.

Claude Code.claude/skills/

Claude DesktopCustomize › Skills

ChatGPTSkills › Create › Upload

Cursor.cursor/skills/

VS Code.github/skills/

Codex CLI.agents/skills/

Gemini CLI.gemini/skills/

Grok Build.grok/skills/

Microsoft CopilotSkills › Upload a skill

PerplexityComputer › Skills › Upload a skill

DeepSeek Harness.dsh/skills/

Zed.agents/skills/

Devin Desktop.devin/skills/

Windsurf (legacy).windsurf/skills/

OpenAI Agents SDKInstructions or sandbox Skills

HTTP / APIa request parameter

This release

Versionnot versioned

Publishedno release date on file

PriceFree

Referencerish2jain/chrome-extension

Versions

Its author publishes no version number, so there is nothing here to pin to: what you install is the folder as it stands today. Instructions change more often than APIs do — a skill can be rewritten entirely without anything it depends on moving.

Pinning

Nothing to pin to: this skill carries no version number of its own. What you install is what the folder holds on the day you install it.

Reviews

—no reviews yet

Nobody has reviewed this skill yet. The rating is the mean of the reviews written here, so there is none until somebody writes the first.

Sign in to review it

A review is tied to an account so it can be answered, edited and taken down by the person who wrote it.

Who can post

Anybody with an account, one review each. It carries the version that was current when you wrote it, and the publisher may reply once.

Who wrote it

rish2jain

Publishes on mcprush.

0 servers listed1 skill listednot claimed

Profile

Publisher

Servers0

Claim this skill