✨Data Intelligence Lab@HKU✨

Build dashboard panels in vanilla TypeScript with shared loading and error displays, saved panel state, and request handling. Examples show retries with increasing delays and CircuitBreaker integration to pause repeated failures and reuse cached results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building dashboard panels in vanilla TypeScript
• Adding caching and cooldowns to existing service calls
• Retrying requests with increasing delays

Build a new dashboard or admin panel by following existing project patterns. This skill coordinates server endpoints, service logic, interface components, registration, and styling, then checks that the pieces connect consistently.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Adding a new dashboard panel
• Implementing a feature across server and interface layers
• Matching existing panel conventions

Package a completed codebase or project directory as a ZIP archive in a separate final step. Verify that the archive exists, inspect its contents, and report the file location with a brief contents summary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Delivering a completed codebase as a ZIP file
• Packaging projects for download
• Archiving deliverables containing multiple files

Build serverless endpoints that relay external API requests for a dashboard while keeping API keys on the server. Includes Vercel examples for input checks, caching, cross-origin access, and consistent JSON responses.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Connect a dashboard to external APIs without exposing API keys
• Create endpoints for stock quotes and news
• Standardize API responses and error handling

Diagnose file access problems by checking directories, permissions, file headers, and line counts in parallel batches. Also reviews TypeScript imports, fixes duplicates and type-only imports, and checks module exports before retrying the failed operation.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate missing files, incorrect paths, and permission errors
• Review multiple source files in parallel batches
• Check CSS and configuration file headers and line counts

Build dashboard panels in vanilla TypeScript with resizing, saved layout state, loading indicators, and retry controls. Examples also show how to wrap existing data-fetching functions with caching and temporary request pauses after repeated failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building dashboard panels in vanilla TypeScript
• Saving panel sizes across page reloads
• Adding retry controls to failed data requests

Create dashboard panels in plain TypeScript using the browser’s page-building API. Follow a shared base class to add titles, counts, loading indicators, error messages, manual retry buttons, and periodically refreshed content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Add a stock price panel to a dashboard
• Show loading indicators and retry buttons on failure
• Standardize titles and item counts across panels

Build dashboard panels in plain TypeScript with automatic retries for failed requests, error messages, and retry buttons. Save expanded or collapsed state and panel dimensions in localStorage, the browser’s local storage.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building dashboard panels in TypeScript
• Adding automatic retries to failed requests
• Saving panel size and collapsed state

Continue suitable tasks when web search repeatedly fails by assessing whether existing knowledge is sufficient. Mark unverified claims, distinguish confidence levels, and provide a follow-up checklist so readers can see what still needs checking.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Assessing whether work can continue without web search
• Drafting documents from established knowledge during search outages
• Marking unverified claims and confidence levels

Diagnose unclear failures from run_shell commands through a stepwise workflow. Capture error output, verify directories and command availability, check environment variables, and test simpler commands to narrow down problems with paths, permissions, or the execution environment.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating unknown errors returned by run_shell
• Comparing local and agent execution environments
• Checking paths, permissions, and command availability

Move Python execution to saved script files when execute_code_sandbox repeatedly fails or becomes unstable. The skill covers writing single or multiple files, running them through run_shell, inspecting outputs and errors, and removing temporary scripts afterward.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Switch execution methods after repeated sandbox failures
• Run Python code split across multiple files
• Process JSON input and write CSV output

Recover failed Python tasks by saving the code as a script and running it through the system shell. The workflow covers spreadsheet generation, data processing, output verification, and troubleshooting missing packages, paths, or permissions.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retry spreadsheet generation after a sandbox failure
• Rerun data processing that timed out
• Run scripts with system-installed Python libraries

Run Python code directly on the host when repeated e2b sandbox failures block execution. The skill explains saving scripts, launching them through the shell, and checking outputs when an isolated environment is unnecessary.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resume Python work after repeated e2b errors
• Run a saved script to create an Excel file
• Investigate sandbox timeouts and connection failures

Continue Python tasks when sandbox execution fails by saving code as a script and running it through run_shell. The workflow covers dependencies, execution checks, and output verification for PDFs, image processing, data analysis, and file operations.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing Python tasks after sandbox initialization failures
• Generating PDFs from a saved script
• Running image processing or data analysis through the shell

Recover Python tasks when execute_code_sandbox fails with errors or timeouts. Install required packages, run the code through run_shell, and inspect messages and generated files to check the result.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming Python tasks after sandbox failures
• Installing missing packages before execution
• Creating a Word document through shell execution

Find input files in confirmed workspace folders, save outputs to explicit locations, and check the results against task requirements. Useful in restricted execution environments where familiar folders may be missing or inaccessible.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Finding input files in an unfamiliar workspace
• Checking generated spreadsheet sheets and formulas
• Validating CSV or JSON outputs before delivery

Decide when repeated search failures justify continuing document creation with existing knowledge. Track errors, distinguish retryable problems, and record verification limits, while excluding tasks that require current information or explicit external verification.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deciding what to do after repeated search errors
• Continuing technical document drafts with established knowledge
• Recording information that could not be externally verified

Hand complex document generation or data processing to shell_agent when direct tools repeatedly fail. Define the required output, let the tool choose libraries and recover from errors, then verify the resulting files and content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Resuming work after repeated tool failures
• Delegating PDF or DOCX document generation
• Handing off multi-step data processing

Delegate file creation to shell_agent when direct generation tools fail. Specify the required format and content, then locate generated files by extension or modification time, copy them to the working directory, and check their integrity.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recover from failures in direct file generation
• Delegate PowerPoint creation with specific requirements
• Generate a PDF report containing charts and tables

Generate documents through shell scripts when standard tools fail, then locate files saved in nested folders. Covers finding PowerPoint or PDF outputs, copying them to the delivery location, and checking that the resulting files exist and are usable.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Generate documents when standard tools fail
• Find PowerPoint or PDF files in nested folders
• Copy generated files to the delivery folder

Run Python through run_shell when code execution tools repeatedly fail. This workflow embeds a multiline script directly in a shell command, supporting tasks such as CSV conversion and PDF generation while checking execution output.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing Python work after repeated tool errors
• Converting CSV data to JSON
• Generating PDFs with reportlab

Create structured medical notes in SOAP format, covering patient reports, observed findings, assessment, and care plans. The skill organizes supplied clinical information, writes all four sections to a file together, and checks that the record is complete.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Organizing patient visit information into SOAP notes
• Documenting medical meetings in a consistent format
• Checking all four sections of a clinical record

Process Excel files with Python after checking that input files and source URLs are accessible. The workflow covers data transformations, formulas, and formatting, with alternative sources and error logs when access fails.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transforming Excel data after checking input files
• Applying formulas and formatting across multiple sheets
• Trying backup sources when a data URL is unavailable

Process Excel workbooks by saving Python scripts to files and running them through the shell. Covers multiple sheets, data transformations, formulas, formatting, and error reporting for complex spreadsheet tasks.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Transform revenue data and save a processed Excel workbook
• Apply calculations across multiple worksheets
• Format report headers with colors and alignment