发现 Skills

Lightweight guidance for using the Upstash Workflow SDK to define, trigger, and manage workflows. Use this Skill whenever a user wants to create workflow endpoints, run steps, or interact with the Upstash Workflow client.

Build production-ready Node.js backend services with Express/Fastify, implementing middleware patterns, error handling, authentication, database integration, and API design best practices. Use when creating Node.js servers, REST APIs, GraphQL backends, or microservices architectures.

TanStack Query (React Query) best practices for data fetching, caching, mutations, and server state management. Activate when building data-driven React applications with server state.

Formats finalized content into structured JSON for Notion publishing. Extracts metadata, structures content blocks, and produces publish-ready output. The actual Notion API interaction is handled by the implementation code.

This skill should be used when the user asks to "review infrastructure", "design helm chart", "check kubernetes manifests", "review terraform", "review terragrunt", "create argocd application", "audit infrastructure", or "/devops". Covers Kubernetes, Helm, ArgoCD, Terraform, and Terragrunt review and design.

YouTube 영상에서 쇼츠 클립 3개를 자동 제작합니다. yt-dlp, whisper, ffmpeg 파이프라인을 사용합니다. "쇼츠 만들어줘", "영상 클립 추출해줘" 요청 시 사용합니다.

Generate a namespaced Sidekiq background job with retry config and spec

Generate a database migration file

Run a code review for React + Next.js projects using the frontend-reviewer agent

Use this skill for any .NET task — APIs, services, repositories, config, tests, or refactoring. Targets .NET 8/9 with C# 12+, ASP.NET Core, and EF Core.

Pull request swarm management for multi-agent code review and validation. Use for coordinated PR reviews, automated validation, PR-based swarm creation, and intelligent merge workflows.

ISO Standards Specialist

Design agent memory architectures for cross-session persistence. Use this skill to build learning systems, maintain entity consistency, and track temporal knowledge. Based on muratcankoylan/Agent-Skills-for-Context-Engineering.

PowerPoint presentation toolkit for creating new presentations, editing existing ones, and using templates. Supports HTML-to-PPTX conversion, slide manipulation, and professional design. Use when building presentations, slide decks, or visual reports.

Use when starting any conversation — establishes how to find and use skills, requiring the Skill tool to be invoked before ANY response, including clarifying questions

Dedicated role for testing, evaluating, debugging, and verifying ADK agents.

A skill that provides weather information based on reference data.

Control Philips Hue lights and scenes via the OpenHue CLI.

Pre-built shadcn/ui components for json-render. Use when working with @json-render/shadcn, adding standard UI components to a catalog, or building web UIs with Radix UI + Tailwind CSS components.

Automated browser verification for dev servers. Triggers when a dev server starts to run a visual gut-check with agent-browser — verifies the page loads, checks for console errors, validates key UI elements, and reports pass/fail before continuing.

Standardized process and template for creating or updating agent skills in this repository.

Interactive setup wizard that generates a complete .claude/ guardrails system customized to your project — hooks, agents, skills, CLAUDE.md, and settings.

Use WordPress admin form-control widgets that ship in core, `wp-color-picker`, `jquery-ui-datepicker`, `jquery-ui-autocomplete`, and `wp-pointer`. Covers correct script/style enqueues, the missing jQuery UI datepicker CSS, `wpColorPicker` change / clear callbacks, datepicker `yy-mm-dd` formatting plus strict server sanitization, autocomplete `source` shapes with `response()`, core user/tag suggest, and `wp-pointer` dismissal through `dismiss-wp-pointer`. Use when adding color, date, typeahead, or first-run pointer controls to settings pages, metaboxes, or repeater rows.

Analyzes BDD (Gherkin) and Playwright test solutions for spec quality, flake resistance, semantic/accessibility locator usage, and AI-agent operability. Produces aspect-level scoring, an overall grade, issues classified by severity, and an actionable improvement roadmap.