Claude Code Skills·Claude Skills·The open SKILL.md registry for Claude
ClaudSkillsAuthors › HKUDS › Page 3

HKUDS

@HKUDS on GitHub →

327 Claude Code skills authored by HKUDS.

updated 2026-08-21 · showing 121–180 of 327 by quality score

Average Pro QualityScore: 64.0/100

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

Execute Python scripts for spreadsheets with prerequisite data validation and source accessibility checks
Token unlock schedule analysis and project treasury tracking — vesting cliffs, linear unlocks, team/investor/ecosystem token releases, treasury diversification, and sell pressure…
AI-powered video captioning — transcribe speech, optimize/translate subtitles, and burn them into video via the stable VideoCaptioner backend. Free ASR and translation included.
Execute Python scripts with prerequisite data validation and fallback strategies for inaccessible sources
Execute complex Python code via run_shell heredoc when execute_code_sandbox fails
Unicode-safe fallback workflow for multi-format document generation with character sanitization — from HKUDS/OpenSpace
Diagnose and resolve file access issues by verifying directory structure, reading multiple files in parallel batches, running combined shell property checks (head/wc-l) in the…
Verify generated PDFs for integrity and page count using PyPDF2 before task completion.
Use when the user wants OpenClaw to build, refine, test, or validate a CLI-Anything harness for a GUI application or source repository.
Multi-fallback PDF/text extraction with early failure detection and sequential tool fallbacks
Identify and handle pre-execution agent failures occurring before any iterations or tool usage
Handle code execution failures with fallback strategies and anchored workspace paths
Use shell tools safely in sandboxed environments by discovering files from real workspace roots instead of assumed user folders, then explicitly verifying output artifacts after…
Create serverless API proxy endpoints that hide API keys and provide a unified backend for the dashboard frontend. Designed for Vercel deployment.
Resilient PowerPoint generation with shell_agent primary path and python-pptx fallback
Fallback pattern for executing Python code when sandbox execution fails by writing scripts to disk and running via shell
Command-line interface for Calibre - A stateful CLI harness for e-book library management, metadata editing, and format conversion wrapping the real Calibre tools (calibredb,…
Two-step script execution workflow for debugging when shell_agent and execute_code_sandbox consistently fail
Enhanced dashboard panel component with robust error handling, retry logic, and localStorage persistence for state management.
Debug Python script execution failures by capturing full output with exit codes and verifying working directory before file operations
Fallback pattern for PDF/document generation when execute_code_sandbox fails with opaque errors
Command-line interface for Kdenlive - A stateful command-line interface for video editing, following the same patterns as the Blender CLI ...
List and count directories in a path by filtering list_dir results for directory entries and excluding hidden/system files
Use run_shell with inline Python for reliable file I/O when execute_code_sandbox cannot access working directory files
Unified guide for authoring dashboard panel components in vanilla TypeScript — covers the Panel base class architecture, localStorage state persistence, exponential-backo — from…
Integrate with news APIs (GNews, NewsAPI, etc.) for aggregated news feeds. Covers headline fetching, search, and category filtering.
Debug Python code execution failures by capturing partial traces, isolating failing functions, and incrementally verifying outputs
Use a deterministic Python/openpyxl inspection pass to verify workbook structure, counts, marked rows, and output-file existence when delegated spreadsheet summaries seem…
Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
Systematic Python debugging workflow for spreadsheet tasks to isolate environment issues from script logic
Generate complex multi-page PDFs by running reportlab Python code directly via run_shell when shell_agent fails on document creation
Generate spreadsheets, diagrams, and PDF reports with iteration budgeting and error recovery
Command-line interface for Ollama - Local LLM inference and model management via Ollama REST API. Designed for AI agents and power users who need to manage models, generate text,…
Create data fetching services with circuit breaker pattern for API resilience. Services handle fetch, cache, retry, and expose typed data to panel components.
Fallback workflow for running code via file write and shell when sandbox execution fails
Four-step recovery workflow for code execution failures when inline Python fails
Dashboard panel components (class-based, self-fetching) and push-update sidebar modules (functional, externally-driven) using vanilla TypeScript DOM API, with retry logic,…
Systematic approach to diagnose and recover from pandoc PDF conversion unknown errors
Unmerge merged cells in openpyxl worksheets before writing values to avoid AttributeError
Experimental NotebookLM harness for listing notebooks, managing sources, asking questions, generating artifacts, and downloading outputs through an installed notebooklm CLI.
Fallback to run_shell and write_file when execute_code_sandbox or shell_agent fail on filesystem operations
Stateful QGIS CLI for projects, writable layers, features, layouts, exports, and qgis_process operations using the real QGIS runtime.
Extract text from DOCX files using shell commands when python-docx is unavailable — from HKUDS/OpenSpace
Create Excel files with openpyxl by falling back to shell-based Python heredoc when sandbox execution fails
Multi-method PDF extraction with sequential fallback and OCR for scanned documents
Fallback workflow for reliable file creation and verification when automated code execution fails
Fallback pattern when primary tools fail - embed known data in scripts and persist to JSON for auditability
Create React components with localStorage persistence and keyboard navigation support
Generate PowerPoint files using shell_agent and locate them in nested workspace directories
Incremental audio production with duration mismatch handling, adaptive stem extension, and pre-mix alignment verification
Debug Python scripts with proper error surfacing and working directory verification
Command-line interface for SeaClip-Lite - A stateless CLI for managing issues, pipelines, agents, schedules, and activity on the SeaClip-Lite project management board.
Domain specification for a personal daily monitoring dashboard. Defines all target panels (email, Feishu, Office, social, news, Twitter, code status, schedule, stock market, daily…
Complete PDF workflow: verify, extract content, assemble reports, and generate output PDFs using command-line tools
Use direct Python execution for reliable document creation including spreadsheets, PDFs, and structured reports
Recover from execute_code_sandbox failures by writing Python scripts to files and executing via run_shell
Create coordinated internal/external documents from reference materials with consistent formatting and cross-references
Create Excel files with openpyxl by falling back to run_shell with inline Python heredoc when execute_code_sandbox fails
Systematic workflow for auditing TypeScript codebases for import hygiene issues (value vs. type imports, duplicates), missing base class extensions, and incomplete barrel file…
Extract PDF text content using shell tools or Python libraries when read_file PDF handler fails
Search all 327 skills by HKUDS →