Development

Precise token counter for GPT, Claude, and Gemini models (source of truth from software kernel)

Playwright를 사용하여 로컬 웹 애플리케이션과 상호작용하고 테스트하기 위한 툴킷입니다. 프런트엔드 기능 검증, UI 동작 디버깅, 브라우저 스크린샷 캡처 및 브라우저 로그 확인을 지원합니다.

Deploy to Azure Container Apps using azd (provision + deploy workflow)

Expert TypeScript/Node.js developer for building high-quality, performant, and maintainable CLI tools and libraries. Enforces best practices, strict typing, and modern patterns.

Expert guide for deploying Next.js apps to Vercel, managing environments, CI/CD pipelines, and production best practices. Use when deploying, setting up automation, or managing production.

Synesthete designer that translates emotional vibes and brand keywords into concrete visual DNA (colors, typography, layouts, interactions). Use when users describe desired "feel" (edgy, trustworthy, premium, playful, minimal) and need specific design specifications. NOT for technical implementation or coding.

Test-Driven Development for Rust. Use when creating new functionality, writing tests, or fixing bugs through the Red-Green-Refactor TDD cycle.

Teaches what React Compiler handles automatically in React 19, reducing need for manual memoization. Use when optimizing performance or deciding when to use useMemo/useCallback.

Create, apply, and rollback goose migrations for SQLite using the embedded migrate tool.

Delegates coding tasks to Coco CLI (Codebase Copilot) for prototyping, debugging, and code review. Use when needing algorithm implementation, bug analysis, or code quality feedback. Supports multi-turn sessions via SESSION_ID.

Production-ready skill for integrating TheSys C1 Generative UI API into React applications. This skill should be used when building AI-powered interfaces that stream interactive components (forms, charts, tables) instead of plain text responses. Covers complete integration patterns for Vite+React, Next.js, and Cloudflare Workers with OpenAI, Anthropic Claude, and Cloudflare Workers AI. Includes tool calling with Zod schemas, theming, thread management, and production deployment. Prevents 12+ common integration errors and provides working templates for chat interfaces, data visualization, and dynamic forms. Use this skill when implementing conversational UIs, AI assistants, search interfaces, or any application requiring real-time generative user interfaces with streaming LLM responses.Keywords: TheSys C1, TheSys Generative UI, @thesysai/genui-sdk, generative UI, AI UI, streaming UI components, interactive components, AI forms, AI charts, AI tables, conversational UI, AI assistants UI, React generative UI, V

Activates when reviewing code to identify quality issues, security vulnerabilities, and suggest improvements

Execute tests from persistent test cases. Reads ./tests/ directory, runs cleanup, wallet setup (if Web3), executes tests, and generates report.

Terraform infrastructure-as-code reference for HCL syntax, state management,module design, and provider configuration. Use when working with Terraformconfigurations (.tf files), running terraform commands, troubleshooting stateissues, or designing modules. Includes Telmate Proxmox provider patterns.Triggers: terraform, tfstate, .tf files, HCL, modules, providers, proxmox_vm_qemu.

Run a single-shot visual comparison between a Figma design node and an implementation URL (local app, Storybook iframe, or deployed page) using @uimatch/cli, then read the generated report to explain design fidelity and quality gate status. Use this skill when the user wants to check whether one specific UI component or page matches its Figma design or debug a particular mismatch.

Using Toolsmith functions instead of raw JavaScript operators and methods (&&, ||, !, .length, ===, etc.). Use when writing conditionals, comparisons, logic operations, or working with collections. Prefer Toolsmith functions to reduce cognitive load and improve readability.

Analyze blast radius, check what will break, review changes before commit. Use for pre-commit review, PR risk assessment, planning safe refactors, or checking if changes are safe to merge. NOT for debugging (use debugging) or exploring unfamiliar code (use exploring-codebases).

Prompt engineering technique to overcome mode collapse in LLM responses by generating multiple answers with probabilities. Use when you want to see alternative responses beyond the top-ranked answer, explore the full distribution of possible responses, discover unexpected solutions, or understand the probability range of different answers. Particularly useful for creative tasks, complex decision-making, brainstorming, and situations where conventional top-ranked answers may be limiting.

Clean Architecture and SOLID principles guide. Use this when designing systems, reviewing architecture, or making structural decisions.

Firebase Cloud Messaging and Apple Push Notification Service setup.