gui-task
Delegates web automation tasks to a navigator agent to handle browser workflows and multi-step web interactions.
Install
mkdir -p .claude/skills/gui-task && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12064" && unzip -o skill.zip -d .claude/skills/gui-task && rm skill.zipInstalls to .claude/skills/gui-task
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
Start an AutoGLM GUI automation task. Use when the user wants to automate a browser workflow: filling forms, searching, extracting data, navigating sites, or completing multi-step web tasks. Invoke with /gui-task followed by the goal description.Key capabilities
- →Extract user's goal for GUI automation
- →Confirm understanding of the goal
- →Delegate tasks to the `task-planner` subagent
- →Remind the user about pause/stop options
- →Inform the user about sensitive step intervention
How it works
The skill extracts the user's automation goal, confirms it, and then delegates the task to a `task-planner` subagent while informing the user about interaction protocols.
Inputs & outputs
When to use gui-task
- →Automate multi-step web form submission
- →Extract data from restricted or complex websites
- →Navigate and search web interfaces programmatically
About this skill
GUI Task Skill
You have been invoked to start an AutoGLM GUI automation task.
What to do
- Extract the user's goal from the invocation arguments
- Confirm your understanding of the goal with one sentence
- Immediately delegate to the
task-plannersubagent with the full goal
Invocation
Pass the complete goal to task-planner, including:
- The target website or service (if specified)
- The desired outcome
- Any constraints the user mentioned (e.g. "don't spend money", "read-only")
Example delegation prompt to task-planner
Automate the following task:
GOAL: [user's goal]
CONSTRAINTS: [any user-specified constraints, or "none"]
CONTEXT: [any relevant details from the conversation]
Decompose this into steps, validate each for safety, execute via web-navigator,
handle any blockers with human-checkpoint, and produce a final report.
Before delegating, remind the user
"I'll start the automation. You can pause or stop at any time. I'll ask for your input if I encounter a login, payment, or other sensitive step."
When not to use it
- →When the task does not involve browser-based automation
- →When the `task-planner` subagent is unavailable
- →When the user's goal is not clearly defined
Limitations
- →Requires delegation to the `task-planner` subagent
- →The skill itself does not perform the GUI automation
- →User input is required for login, payment, or sensitive steps
How it compares
This skill acts as an orchestrator for GUI automation by delegating to a specialized subagent and managing user communication, rather than performing the automation directly.
Compared to similar skills
gui-task side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| gui-task (this skill) | 0 | 5mo | No flags | Beginner |
| browser-automation | 39 | 1mo | Review | Intermediate |
| browser-use | 64 | 3mo | Review | Intermediate |
| web-browser | 2 | 2mo | Review | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by bivex
View all by bivex →You might also like
browser-automation
browserbase
Automate web browser interactions using natural language via CLI commands. Use when the user asks to browse websites, navigate web pages, extract data from websites, take screenshots, fill forms, click buttons, or interact with web applications. Triggers include "browse", "navigate to", "go to website", "extract data from webpage", "screenshot", "web scraping", "fill out form", "click on", "search for on the web". When taking actions be as specific as possible.
browser-use
browser-use
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, or extract information from web pages.
web-browser
mitsuhiko
Allows to interact with web pages by performing actions such as clicking buttons, filling out forms, and navigating links. It works by remote controlling Google Chrome or Chromium browsers using the Chrome DevTools Protocol (CDP). When Claude needs to browse the web, it can use this skill to do so.
telegrab-fetch
saturov
Use when the user needs to download one Telegram video from a post link through this repository's telegrab CLI with deterministic preflight checks and machine-readable result fields.
mcporter
consuelohq
--- name: mcporter description: Call MCP servers via MCPorter - browser automation, vision, and other MCP tools homepage: https://github.com/steipete/mcporter metadata: { "openclaw": { "emoji": "🧳", "requires": { "bins": ["npx"] } } }
powerskills-browser
aloth
Edge browser automation via Chrome DevTools Protocol (CDP). List tabs, navigate, take screenshots, extract page content/HTML, execute JavaScript, click elements, type text, fill forms, scroll. Use when needing to control Edge browser, scrape web content, automate web forms, or take browser screensho