Our review
Initiates an AutoGLM GUI automation task to perform browser-based workflows such as form filling, data extraction, and multi-step web navigation.
Strengths
- Delegates complex web tasks to a specialized planner and navigator
- Supports user constraints and safety checkpoints
- Handles sensitive steps with human-checkpoint reminders
Limitations
- Only works with browser-based GUI tasks
- Requires clear user goal for effective automation
- May fail on sites with heavy JavaScript or anti-bot measures
Use when you need to automate repetitive or multi-step browser tasks like searching, extracting structured data, or filling forms across several pages.
Avoid for tasks requiring real-time interaction or complex decision-making that cannot be pre-defined, or for tasks outside a web browser.
Security analysis
SafeThe skill only delegates to a subagent and does not execute any system commands, destructive actions, or data exfiltration. It provides safety reminders and leaves actual execution to other controlled components.
No concerns found
Examples
/gui-task Compare prices of iPhone 16 on Amazon, Best Buy, and Apple Store, and list the cheapest option with shipping costs./gui-task Go to LinkedIn, find the 'Software Engineer' job posting from Google, and apply using the attached resume – but do not submit without asking me first./gui-task Extract the top 10 news headlines from BBC News today and save them to a file named bbc_headlines.txt.name: gui-task description: > 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.
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."
Task Prioritizer
Productivity
Prioritizes your tasks using Eisenhower, ICE, and RICE frameworks.
Weekly Status Report Generator
Productivity
Generate structured and concise weekly status reports.
Daily Standup Report
Productivity
Generates structured and concise daily standup reports.