✨Data Intelligence Lab@HKU✨

Analyze agent runs that fail before any work begins. By checking execution counts, tool calls, outputs, and conversation logs, this skill classifies startup failures and directs investigation toward system setup, resources, or input processing.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating failed runs with zero execution steps
• Classifying failures with no tool calls or outputs
• Routing startup incidents to infrastructure teams

Check files created or edited by another agent, subprocess, or tool against explicit requirements. Verify the actual location, structure, counts, and key fields, then rerun with absolute paths when the results contradict the completion report.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Checking files produced by another agent
• Verifying spreadsheet sheets and row counts
• Checking CSV headers and record counts

Extract text from Word DOCX files with unzip and sed, command-line utilities, when Python document libraries are unavailable. Read the document’s main text, remove XML tags, clean whitespace, and save the extracted content.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading Word text without installing Python libraries
• Extracting DOCX text in containers or minimal environments
• Saving document text to a TXT file

Extract text, tables, and headings from Word documents when standard file reading tools fail. The workflow uses Python and python-docx through run_shell to recover document content for further review or analysis.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Reading Word documents after file tool failures
• Extracting table contents from Word documents
• Listing headings or numbered paragraphs

Run Python code through a saved script and shell when repeated sandbox failures point to environment problems. Captures execution output and checks exit codes and expected files to verify whether the task completed.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing work after repeated sandbox execution failures
• Running Python scripts saved in the workspace
• Investigating failures through shell error output

Continue Python tasks after repeated sandbox failures by saving code as a script and running it through the shell, a command interface. The workflow covers execution checks, result retrieval, and optional cleanup.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing data processing after repeated sandbox errors
• Saving execution results to files for later retrieval
• Checking script errors and exit codes

Recover from PDF and DOCX generation errors by checking the workspace, capturing error details, and trying alternative conversion engines or Python libraries. Verify that the resulting files exist and can be read.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recovering from PDF conversion errors
• Creating reports in DOCX and PDF
• Investigating garbled symbols in PDFs

Create formatted Excel files when sandbox code execution fails by running Python through the shell. Uses openpyxl to add styled headers, alternating row colors, borders, alignment, and adjusted column widths.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Recovering Excel creation after sandbox execution fails
• Creating schedules with colored headers and borders
• Formatting reports with alternating row colors

Debug repeated execution failures by saving Python code to a script file and running it through run_shell. Keep the script available for inspection, review intermediate output and errors, and edit it for another run.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate repeated agent or sandbox execution failures
• Trace data processing with intermediate output
• Edit and rerun a saved Python script

Recover from failed file and directory operations by switching to run_shell, a shell command tool. Create nested folders, write files, and verify each result before continuing with tasks that depend on those files.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retry file creation after an unknown error
• Create nested project folders explicitly
• Write files containing multiple lines

Generate DOCX, PDF, and HTML from Markdown through separate, observable conversion steps. The workflow replaces problematic characters for PDF output, captures error messages, and switches PDF engines when needed to troubleshoot document generation failures.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Export one Markdown document to DOCX, PDF, and HTML
• Investigate unclear document conversion errors
• Replace special characters before PDF conversion

Investigate Python failures in a sandbox, an isolated execution environment, by capturing partial logs, testing functions separately, and checking output files one at a time. Use the findings to identify failing steps and rebuild a working script.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigate failures with missing or incomplete output
• Isolate a failing function in a large script
• Verify multiple generated files one at a time

Create Excel files with openpyxl, a Python spreadsheet library, by switching to shell execution when sandbox tools fail. Examples cover cell styling, formulas, merged cells, multiple sheets, error reporting, and checking that the output file exists.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Retrying Excel creation after sandbox failures
• Creating spreadsheets with styles and formulas
• Building workbooks with multiple sheets

Prepare audio stems, the separate parts of a track, for mixing by matching their durations with silence, loops, or crossfades. Verify each generated and processed file before moving to the next production step.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Match audio parts with different durations
• Extend drums and melodic parts using suitable methods
• Check audio specifications before mixing

Keep document creation moving when web searches and page retrieval repeatedly fail. The skill preserves the original task, uses the model’s existing knowledge, and clearly identifies information that could not be checked against external sources.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continue drafting after repeated web retrieval failures
• Preserve task requirements during network errors
• Mark information that could not be externally verified

Recover from repeated sandbox execution failures by saving Python code to a script and running it through run_shell. Check output, error messages, and exit codes to confirm results or diagnose remaining execution problems.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Continuing Python work after two consecutive sandbox failures
• Switching execution methods after persistent timeouts
• Diagnosing script failures through error output

Build working web pages, application interfaces, and components with a clear visual direction. Shape typography, color, layout, and animation around the intended audience and purpose, producing coordinated design and code in HTML, CSS, JavaScript, React, or Vue.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Building a landing page with a clear visual style
• Designing and implementing a dashboard
• Refining typography, colors, and spacing in an existing interface

Set up a consistent local environment for developing ClawTeam, then validate changes with focused tests and real agent workflows. Includes scripts for connecting other projects to local skills and guidance for investigating coordination bugs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Set up a consistent local development command
• Reproduce worker startup or messaging bugs
• Validate agent coordination after code changes

Coordinate multiple AI agents by assigning tasks, tracking dependencies, exchanging messages, and monitoring progress. Separate Git working directories help organize parallel changes, while context checks and snapshots support handoffs and recovery.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Split feature development and testing between agents
• Track task dependencies and team progress
• Check overlapping changes before a handoff

Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Remote-control tmux sessions for interactive CLIs by sending keystrokes and scraping pane output.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Dedicated to calling the FastCode backend to index code repositories and answer questions about them.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Create or update AgentSkills. Use when designing, structuring, or packaging skills with scripts, references, and assets.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Get current weather and forecasts (no API key required).

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.