Skill UI

This skill provides comprehensive operational capabilities for managing FrontendExtension resources in a Kubernetes cluster. It covers the entire lifecycle, including resource creation, package generation, artifact inspection, publishing, unpublishing, deletion, and deep debugging of package and publish controller behaviors. Use it for troubleshooting FE status, managing deployment pipelines, or interacting with the FE API.

This tool helps users manage and address review comments on open GitHub Pull Requests (PRs). It interacts with the GitHub CLI (gh) to fetch comments, guides the user through selecting which comments need fixes, and then applies the necessary changes, ensuring a structured approach to PR review.

This skill automates the debugging and fixing of failing Continuous Integration (CI) checks on GitHub PRs. It uses the GitHub CLI (gh) to locate failures, fetch detailed logs from GitHub Actions, summarize the failure context, and propose a structured fix plan. After user approval, it can implement the necessary code changes and verify the fix, streamlining the development cycle.

This skill provides a direct, fast shell invocation to capture the current git diff (staged, working-tree, or specific file list) as raw text. It is designed to replace slower LLM agent steps that merely execute 'git diff' commands, significantly speeding up CI/CD workflows and meta-steps that require repository state analysis.

A comprehensive guide to using the GitHub CLI (`gh`) for programmatic interaction with repositories. This tool allows users to list, manage, and review Pull Requests (PRs), create and triage issues, check CI/workflow status, and execute advanced API queries directly from the terminal, making it essential for scripting and automated DevOps workflows.

jscpd is a comprehensive code quality tool designed to detect copy-pasted or duplicated segments across programming source code. Supporting over 150 languages, it identifies redundant code blocks and calculates the overall duplication percentage. It offers multiple reporters (AI, HTML, JSON) and integrates with refactoring workflows to help developers maintain high code integrity.

This skill automates the complex compilation process required for LaTeX documents, specifically implementing the sequence: xelatex -> bibtex -> xelatex -> xelatex. It takes pre-assembled content (such as abstracts and body text) and compiles them into a cohesive, structured academic paper. Ideal for the final steps of scientific and technical writing.

This meta-skill scans a target codebase path to extract modules, dependencies, and hotspots. It then intelligently classifies the most appropriate architectural diagram type (class, sequence, component, etc.) and renders the diagram simultaneously as both PlantUML source code and editable draw.io XML. Finally, it composes a structured Word document containing both deliverables for comprehensive documentation.

This meta-skill automates the process of handling a GitHub issue by fetching context, delegating the fix to a sub-agent, summarizing the resolution, and finally opening a pull request (PR). It is best suited for small, well-scoped issues with clear acceptance criteria. This pipeline simulates a complete development workflow.

A meta-skill designed to monitor long-running processes, such as model fine-tunes or CI builds, executed within a detached tmux session. It captures output, automatically uses a sub-agent to diagnose failures, proposes a fix, and records the complete debugging process to memory. Ideal for intermittent failure debugging and continuous integration pipelines.

This meta-skill provides a comprehensive, step-by-step plan for complex software migrations. It intelligently coordinates multiple steps, including gathering migration requirements, classifying the source and target stacks (e.g., CJS to ESM, Py2 to Py3), searching authoritative guides, and analyzing repository diffs to ensure a guided, reliable upgrade path for large-scale projects.

This meta-skill automates the complex process of modernizing legacy PDF documents (e.g., historical contracts, scanned manuals, legal documents). It follows a structured four-step pipeline: structural extraction, natural-language rewriting of problem pages, generating an audit summary, and finally re-merging the content into a single, refined PDF. This ensures content is modernized while maintaining fidelity to the original meaning, providing a human review summary before finalization.