Skill Creator
majiayu000
6838 published skills · 19,665 GitHub stars across the catalog. View on GitHub ↗
unit-tests
Write pytest tests using Test-Driven Development (TDD). Use when implementing features, fixing bugs, or when the user mentions testing, TDD, or pytest. Tests should be written BEFORE implementation code.
kanban
Kanban methodology including boards, WIP limits, flow metrics, and continuous delivery. Activate for Kanban boards, workflow visualization, and lean project management.
model-skill
Create Pydantic v2 data models with validation, type hints, and proper configuration. Use when designing data structures or schemas.
auto-linter
Run linters/formatters on changed files and apply safe, mechanical fixes. Use in Flow 3 and Flow 4.
responsive-mobile-first
Mobile-first responsive patterns with sticky headers, floating CTAs, accessible navigation, and touch-friendly interactions. Use when implementing responsive layouts, mobile navigation, or ensuring touch-friendly UI.
chart-generation
生成专业金融图表(K线图、技术指标图)。适用于数据可视化、技术分析展示、报告生成等场景。支持多种图表类型(basic、comprehensive)和自定义样式(深色、浅色主题)。
bash-defensive-patterns
Use when writing or reviewing Bash scripts to apply defensive programming patterns including strict mode, proper error handling, safe variable handling, argument parsing, and idempotent design. Ensures scripts are robust, maintainable, and production-ready.
conductor-methodology
This skill should be used when the user asks about "conductor methodology", "context-driven development", "conductor directory structure", "conductor files", "tracks.md", "plan.md", "spec.md", or when commands reference conductor concepts. Provides comprehensive understanding of the Conductor framework for Context-Driven Development.
gamebuddies-game-generator
Generate complete multiplayer games for GameBuddies.io platform with full integration including streamer mode, lobby system, chat, WebRTC video, and real-time gameplay. Creates server logic, client UI, type definitions, and game mechanics following GameBuddies template patterns.
auto-prompt-enhancer
Expert prompt engineering assistant that analyzes vague requests, asks clarifying questions, and transforms them into structured, high-quality prompts using XML tags, examples, and chain-of-thought reasoning. Always active - transparently shows enhanced prompts before execution. Use for vague requests, feature implementation, or architecture decisions.
casebook-editing
Guidance for developing and editing legal casebooks
ai-file-analyzer
Analyze Adobe Illustrator (.ai) files to extract design information including text content, fonts, color palettes, vector paths, and generate high-resolution preview images. Use when analyzing logo files, design assets, or any Adobe Illustrator documents that need programmatic inspection.
article-analysis
Analyze blog posts and web articles by fetching content from URLs. Use when the user mentions blog post, article, Substack, Medium, web page, newsletter, or provides a URL to analyze.
project-orchestration
Coordinate multiple agents by routing tasks to appropriate specialists. EXCLUSIVE to project-manager agent.
tailwind-styling
Tailwind CSS styling patterns, dark theme implementation, and theme management for this project. Use when styling components, implementing UI changes, or working with the design system.
harness-runner
Run WaveCap-SDR test harness with automated parameter sweeps and validation. Use when regression testing, validating audio quality across configurations, testing SDR hardware, or benchmarking demodulation performance.
phrack-exploit-analyzer
Phrack magazine article analysis, binary exploitation, vulnerability research, exploit development, Use-After-Free (UAF), heap exploitation, ROP chain, GDB debugging, pwntools, memory corruption, CVE analysis, ProFTPd exploitation, Docker exploit lab, security research, educational hacking, buffer overflow, stack exploitation, shellcode development
mcp-bridge
Use the MCP Code Execution Bridge for context-efficient access to Supabase and shadcn tools. Provides API-based database operations (query, insert, update, delete) that work without Docker/MCP servers. Use when you need database access or component management without loading all tool definitions into context.
design-system-starter
Use this skill when creating or evolving design systems for applications. Provides design token structures, component architecture patterns, documentation templates, and accessibility guidelines. Ensures consistent, scalable, and accessible UI design across products.
gemini-image-gen
Guide for implementing Google Gemini API image generation - create high-quality images from text prompts using gemini-2.5-flash-image model. Use when generating images, creating visual content, or implementing text-to-image features. Supports text-to-image, image editing, multi-image composition, and iterative refinement.
semantic-intelligence
Use Miller's semantic search capabilities for conceptual code understanding. Activates when searching for concepts, cross-language patterns, business logic, or exploring unfamiliar code. Combines text and semantic search for optimal results.
prompt-optimization
Transform vague requests into production-ready, hallucination-free prompts optimized for Claude 4.x. Applies investigation-first protocols, anti-hallucination guards, extended thinking patterns, and multishot examples. Use when user requests prompt improvement, optimization, or asks to fix hallucinations, structure vague requests, apply Claude 4.x best practices, or create production-grade prompts.
tech-stack-analyzer
Delegates tech stack detection to a lightweight agent. Use when you need to know the project's language, frameworks, or dependencies without loading manifest files into context.
app-theming
Your approach to handling app theming. Use this skill when working on files where app theming comes into play.