Skill Creator
WarrenZhu050413
44 published skills · 220 GitHub stars across the catalog. View on GitHub ↗
example
Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations. Adapted for Warren's system with snippet integration.
using-linear
Guide for working with Linear project management via GraphQL API. Use when creating/updating Linear issues, changing status, adding comments, or uploading files/screenshots. Covers raw GraphQL, Python SDK (linear-py), issue search, mutations, and file upload workflows with Google Cloud Storage signed URLs. Tested October 2025.
spanish-learning
Manage comprehensive Spanish learning system with A2 level support, vocabulary tracking, TTS integration, practice management, and deep search capabilities.
fetching-relevant-images
Find, fetch, and legally use images from the web. Covers Wikimedia Commons, free sources, copyright, fair use, and embedding. Use when you need images for any project.
generating-html
This snippet should be used when creating user-journey-optimized HTML documents that guide readers through a clear narrative arc with curated content and dark mode support.
sending-notifications
Send macOS notifications using display dialog method that works reliably in tmux.
managing-snippets
Comprehensive guide for managing Claude Code snippets v2.0 - discovering locations, creating snippets from files, searching by name/pattern/description, and validating configurations. Use this skill when users want to create, search, or manage snippet configurations in their Claude Code environment. Updated for LLM-friendly interface with TTY auto-detection.
using-clis-effectively
Best practices and patterns for discovering, using, and integrating with command-line interfaces
applying-style
Apply precise writing style that expresses ideas clearly with personal voice and logical flow.
making-files-clearer
Simplify and clarify files by removing redundancy, organizing content logically, and keeping only essential information. Use when asked to make something clearer, remove fluff, simplify, declutter, make more concise, or improve readability. Keywords - clarity, simplify, concise, declutter, remove redundancy, essential only, no fluff.
writing-lua
This snippet should be used when writing Neovim plugins with Lua, focusing on type safety, modular architecture, and best practices.
using-screenshots
This snippet should be used when reading, organizing, and naming screenshots with date prefixes.
documentation-tutorial
Build hands-on, code-first tutorials from any primary source - technical documentation, codebases, APIs, tools, or other complex material. Extract real examples, working code, and concrete scenarios. Create tutorials using markdown (text-heavy summaries) or React artifacts (complex interactive workflows). Keywords - tutorial, codebase, API, hands-on, code-first, copy-paste, interactive, real examples, primary source
visualizing-subagents
Visualize subagent task dependencies using ASCII diagrams before launching agents and create comprehensive HTML summaries after completion.
gmail-assistant
Use when composing, sending, searching, or managing Warren's emails via gmail CLI. Covers drafting with styles, finding similar emails for context, managing groups, discovering contacts online, and email workflows. Always test to fuchengwarrenzhu@gmail.com before real sends.
reflecting-on-learnings
Analyzes conversations to identify learnings, patterns, and techniques for capture in skills/snippets. Proposes updates or new skills, shows preview before changes. Use when user says "reflect", "what did we learn", or after complex tasks.
using-claude
Working with Claude Code features, debugging hooks, MCP integration, snippet verification, headless automation, and Agent SDK. Use this skill when the user asks about Claude Code features, hooks, memory, statusline, debugging, MCP servers, headless use patterns, CI/CD automation, Python/TypeScript Agent SDK, or building custom agents.
prompt-engineering
Anthropic's official prompt engineering best practices. Use when optimizing prompts, debugging outputs, or improving response quality.
testing-webapps
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
building-mcp
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
planning-html
This snippet should be used when creating technical execution plans in HTML format with mandatory quality review before display.
pdftext
Extract text from PDFs for LLM consumption using AI-powered or traditional tools. Use when converting academic PDFs to markdown, extracting structured content (headers/tables/lists), batch processing research papers, preparing PDFs for RAG systems, or when mentions of "pdf extraction", "pdf to text", "pdf to markdown", "docling", "pymupdf", "pdfplumber" appear. Provides Docling (AI-powered, structure-preserving, 97.9% table accuracy) and traditional tools (PyMuPDF for speed, pdfplumber for quality). All processing is on-device with no API calls.
writing-scripts
Best practices for writing automation scripts in Python and Bash. Use when writing automation scripts, choosing between languages, debugging subprocess errors, or implementing error handling patterns. Load language-specific references as needed.
uv-debug
Troubleshooting and debugging problems with uv (Python package manager). Use when encountering uv installation issues, stale build cache, package not updating, or discrepancies between uv run and global installs.