Browser Automation Office Assistant
Paste the following prompt into your AI chat to install this skill:
Please install @org-02qudk26/browser-automation following https://skillhub.cn/install/skillhub.md.
About this skill
Problem
Repetitive browser work usually breaks when the page has not finished loading, a selector changes, or a failure leaves no evidence. Form filling, table scraping, and page regression checks all need stable waits, error handling, and maintainable selectors.
How It Works
The skill is organized around basic browser actions:
- Navigation: open, navigate, and go back
- Element Interaction: click, type, and select controls
- Data Extraction: read fields from page structure
- Screenshots & PDF: capture screenshots or export PDFs
A typical flow is: locate the element -> wait until it is actionable -> perform the action -> catch failures -> record evidence or retry. Prefer data-testid, run headless in production, rate-limit requests, and screenshot navigation failures.
Boundaries
It fits office-efficiency tasks such as repetitive forms, web data cleanup, page state validation, and lightweight E2E tests. It is not a good fit for aggressive scraping, complex session management, or high-risk automation; respect target-site terms and server load.
Use Cases
- Process daily internal approvals: open the approval page, click approve, and screenshot failures.
- Collect supplier quotation data: navigate to the listing page, extract fields, and produce sortable records.
- Validate a page redesign: confirm key buttons are clickable, form input displays correctly, and screenshot anomalies.
- Fill repetitive expense forms: enter amount, project, and notes, then keep a pre-submission screenshot.
Best For
- Operations staff reconciling suppliers: extract fields from multiple web quotation tables weekly.
- Frontend automation engineers: locate data-testid, wait for stable pages, and screenshot failures.
- Analysts cleaning web data: navigate to report pages, extract table fields, and keep auditable screenshots.
- Admin specialists maintaining approvals: batch-click, fill forms, and preserve failure evidence.
Related Skills
Generate and edit .pptx decks with python-pptx, applying structured layouts, design rules, native charts, and visual QA to reduce template-like output.
Tencent Cloud Table Recognition V3 is an OCR skill for detecting and recognizing tables in images or PDFs, supporting various table types like linear and borderless tables, with Excel export.
The complete set of online document operation tools provided by Tencent Docs MCP, supporting creation, querying, and editing of smart docs, Excel, PPT, mind maps, and more.
Turn a topic, notes, or tables into a complete PPT plan with logic, page layouts, visual and chart guidance, and natural defense scripts.