Marketplace
SkillHub Club catalog feed.
Public marketplace mirror sourced from skillhub.club. This source view keeps the new outcome-first browsing model while filtering server-side to a single upstream feed.
course-help
Provides structured navigation and progress tracking for the Claude Code Course. Guides users through 5 hands-on lessons with clear commands like /ccc:course and /ccc:lesson. Saves progress locally and offers practice tasks in the terminal.
ui-generator
Generates React/Next.js UI components from natural language descriptions. Integrates with theme-factory for consistent styling, produces Tailwind CSS code, and provides immediate browser previews for common page types like login, dashboard, and pricing pages.
cascade-orchestrator
Coordinates multiple Claude micro-skills into sequential or parallel workflows with conditional logic. Integrates Codex sandbox for auto-fixing test failures and routes tasks to different AI models (Gemini/Codex) based on task requirements. Supports swarm coordination via ruv-swarm MCP for parallel execution.
design-tokens-validator
Scans source code files across multiple platforms (CSS, SwiftUI, Unity) to detect hard-coded design values like colors and spacing. Suggests replacements with official design system tokens to enforce consistency. Includes command-line tool and clear detection examples for different file types.
skill-creator
Provides a structured guide for creating Claude skills, covering core principles, file structure, and development process. It helps users extend Claude with specialized workflows and tool integrations.
ux-sequence-diagram
Generates ASCII sequence diagrams for visualizing user-system interactions and API call flows. Shows participants, message types, and timing in text format. Useful for documenting interaction patterns without graphical tools.
prd-writer
Generates structured Product Requirements Documents from initial feature prompts. Asks clarifying questions first, then creates markdown files with standard PRD sections. Targets junior developers with clear templates.
aesthetic-form-composition
Analyzes visual compositions by examining eye paths, balance, rhythm, layering and proportions. Outputs structured compositional rules as Memo nodes for design reference. Useful for designers analyzing existing layouts or creating new visual systems.
testing-patterns
Provides concrete testing patterns for a specific project (ActionPhase), covering backend Go unit tests, React component tests, and Playwright E2E tests. It enforces a strict workflow where E2E tests are written last, after unit, API, and component tests pass. Includes specific commands, fixture data, and anti-pattern examples.
ai-multimodal
Provides CLI tools to process audio, images, videos, and documents using Google Gemini API, with batch processing, media optimization, and content generation capabilities. Includes practical scripts for transcription, analysis, and image/video creation.
skill-creator
Provides structured guidance for creating Claude Skills with clear directory organization, progressive disclosure patterns, and concrete examples for scripts, references, and assets. Helps developers package specialized workflows efficiently.
code-review
This skill enforces strict code review protocols for Claude, banning performative agreement and requiring evidence before completion claims. It provides concrete decision trees for receiving feedback, requesting reviews via subagent, and implementing verification gates. The approach targets common AI pitfalls in technical review processes.
langchain-architecture
Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
cost-optimization
Provides concrete strategies for reducing cloud costs across AWS, Azure, and GCP. Includes specific examples like Terraform code for S3 lifecycle policies, budget alerts, and auto-scaling. Offers practical checklists and tagging strategies that teams can implement immediately.
k8s-browser
Browser automation for Kubernetes dashboards and web UIs. Use when interacting with Kubernetes Dashboard, Grafana, ArgoCD UI, or other web interfaces. Requires MCP_BROWSER_ENABLED=true.
pptx
Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks
manimce-best-practices
Trigger when: (1) User mentions "manim" or "Manim Community" or "ManimCE", (2) Code contains `from manim import *`, (3) User runs `manim` CLI commands, (4) Working with Scene, MathTex, Create(), or ManimCE-specific classes. Best practices for Manim Community Edition - the community-maintained Python animation engine. Covers Scene structure, animations, LaTeX/MathTex, 3D with ThreeDScene, camera control, styling, and CLI usage. NOT for ManimGL/3b1b version (which uses `manimlib` imports and `manimgl` CLI).
growth-hacker
Generate growth strategies and ready-to-publish marketing content for product growth. Use when planning launches, assessing product-market fit, creating marketing content, designing experiments, optimizing activation/onboarding, or developing acquisition strategies. Incorporates proven frameworks from Sean Ellis (PMF testing, ICE prioritization) and Nikita Bier (viral consumer growth, activation optimization). Covers product-market fit assessment, activation optimization, viral loops, SEO, email marketing, social media, landing pages, and growth experiments.
map
高德地图路线规划与 POI 搜索。支持驾车、步行、骑行、公交路线规划，以及景点、餐厅搜索。当用户询问路线、行程规划、景点推荐、餐厅推荐时使用。
cron-manager
定时任务管理。创建、查看、修改、删除定时任务，管理任务会话数据。当用户需要设置提醒、定时执行任务、管理调度计划时使用。
web-performance-audit
This skill performs comprehensive web performance audits by measuring Core Web Vitals, identifying bottlenecks, and providing prioritized optimization recommendations to improve page load times and user experience.
cfn-improvement-recommender
Analyzes sprint retrospective data to identify bottlenecks and suggest improvements in agent selection, feedback processing, and iteration management. Provides confidence scores and tracks recommendation effectiveness over time.
Remembering Conversations
Searches archived Claude conversations using semantic or exact text matching. Helps developers find past discussions, decisions, and solutions instead of re-solving problems. Works via CLI or within Claude Code sessions with subagents to save context.
task-valid-review
A verification tool for checking task completion before moving from Review to Done. It validates subtask completion, code/file changes, and task-work alignment with clear pass/fail outputs. Useful for developers who want to ensure work is actually finished.