Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkills › Authors › HKUDS › Page 4

HKUDS

@HKUDS on GitHub →

344 Claude Code skills authored by HKUDS.

updated 2026-10-04 · showing 181–240 of 344 by quality score

Average Pro QualityScore: 64.1/100

For the full experience including quality scoring and one-click install features for each skill — upgrade to Pro.

Robust PowerPoint generation with shell_agent primary approach and python-pptx fallback, including working directory verification and inline error debugging
Fallback workflow for code execution when automated tools fail, using shell heredoc with verification
Delegate complex tasks to shell_agent when direct tool execution fails, leveraging autonomous error recovery and library selection
Diagnose and resolve file access issues by verifying directory structure, then reading multiple files in parallel batches for efficient auditing, with built-in guidance for…
Ensures codebase deliverables are properly exported as ZIP archives through a dedicated finalization step
Create and modify Excel workbooks with mandatory deterministic Python verification of workbook structure, required sheets, populated columns, and sample counts before reporting…
Browser automation CLI using DOMShell MCP server. Maps Chrome's Accessibility Tree to a virtual filesystem for agent-native navigation.
Command-line interface for CloudCompare — Agent-friendly harness for CloudCompare, the open-source 3D point cloud and mesh processing software.
Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell
Extract text from DOCX files with shell-primary approach and Python zipfile fallback for maximum reliability
Read-then-diff before writing a file to ensure the write is skipped when the content already matches, preventing unnecessary modifications and downstream side effects.
Extract PDF text content using shell tools or Python libraries when read_file PDF handler fails
Fallback method to execute Python code when execute_code_sandbox fails with e2b errors
Fallback workflow for document generation when code sandbox returns opaque errors
Handle code execution failures with fallback strategies and anchored workspace paths
Report tool failures transparently and attempt minimal viable output with disclaimers
Verify PDF page counts and file integrity programmatically using PyPDF2 after generation
Command-line interface for Tigris object storage — wraps the official `tigris` CLI to expose buckets, objects, presigned URLs, snapshots, IAM, and scoped access keys to AI agents.
Curated architecture index of the WorldMonitor open-source dashboard. Reference for extracting patterns — vanilla TypeScript, Panel class hierarchy, service layer, CSS grid, API…
Leverage shell_agent for autonomous file creation and modification with automatic tool selection and error recovery
Incremental audio production with duration alignment handling, per-stem verification, and adaptive extension strategies
Identify and handle agent failures with 0 iterations as pre-execution system issues
How to reliably write files containing multi-byte Unicode (emoji, special symbols) when write_file fails with 'unknown error' by falling back to run_shell with a heredoc.
Generate professional documents after tool failures using shell_agent for complex formats or write_file for simple text/markdown
Identify and handle pre-execution agent failures occurring before any iterations or tool usage
Command-line interface for Kdenlive - A stateful command-line interface for video editing, following the same patterns as the Blender CLI ...
Ensures agents extract data from context files with validation and fallback strategies before resorting to assumptions or external searches.
Complete PDF lifecycle: download, extract, and generate structured documents with reportlab
TypeScript compile-checking in projects where npx and node_modules/.bin symlinks fail, with a filtering technique to isolate errors from only newly-created or task-specific files…
Two-step script execution workflow for debugging when shell_agent and execute_code_sandbox consistently fail
Create Excel files with openpyxl by falling back to run_shell with inline Python heredoc when execute_code_sandbox fails
Document generation with direct pandoc/ReportLab execution (lightweight default) and optional shell_agent fallback for complex scenarios
Resilient PowerPoint generation with shell_agent primary path and python-pptx fallback
SiYuan (思源笔记) CLI — manage notebooks, documents, blocks, and search your knowledge base from the terminal.
Verify task completion by checking filesystem state when execute_code_sandbox or run_shell return misleading unknown errors
Reliable Python execution workflow when execute_code_sandbox or shell_agent fail
Use run_shell with inline Python for reliable file I/O when execute_code_sandbox cannot access working directory files
Debug Python script execution failures by capturing full tracebacks and verifying working directory
Resilient multi-format document generation with environment checks, auto-sanitization, and fallback engines
Create a dashboard panel component using vanilla TypeScript DOM API, following the worldmonitor Panel architecture.
Four-step recovery workflow for code execution failures when inline Python fails
Generate complex multi-page PDFs by running reportlab Python code directly via run_shell when shell_agent fails on document creation
Systematic approach to diagnose and recover from pandoc PDF conversion unknown errors
Capability-based multi-tool matrix for research, note-taking, document authoring, and publishing. Agents compose providers (CLI-Anything harnesses, public CLIs, Python libs,…
Create dashboard panel components with integrated resilient data services, combining UI construction and data fetching into a unified pattern.
Debug Python scripts with proper error surfacing and working directory verification
Clarifies that file creation tasks are complete when the deliverable is successfully written—no submission step required
Workaround for write_file failures caused by special characters (apostrophes, backticks, template literals) using a Python heredoc script, with mandatory post-write verif — from…
Stateful QGIS CLI for projects, writable layers, features, layouts, exports, and qgis_process operations using the real QGIS runtime.
Unified dashboard panel pattern combining circuit breaker resilience with enhanced UI features like retry logic, state persistence, and detailed error handling.
PDF extraction with ordered tool chain: read_file, then run_shell/pdftotext, then execute_code_sandbox/PyMuPDF
Use when the user wants Reasonix to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository.
Interactive CLI for Uni-Mol molecular property prediction training and inference workflows. — from HKUDS/CLI-Anything
Implement efficient virtual scrolling for rendering large lists with DOM recycling, chunk-based rendering, and performance optimizations
Create data fetching services with circuit breaker pattern for API resilience. Services handle fetch, cache, retry, and expose typed data to panel components.
Verify PowerPoint presentation contents using python-pptx via shell when standard file readers fail
Execute Python scripts from files for reliable spreadsheet operations, avoiding heredoc issues with shell_agent
List and count directories in a path by filtering list_dir results for directory entries and excluding hidden/system files
Systematic tracking and completion of all required deliverables before task termination
Check FFmpeg encoder availability before video encoding to avoid library mismatches
Search all 344 skills by HKUDS →