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.
arxiv-search
Search arXiv preprint repository for papers in physics, mathematics, computer science, quantitative biology, and related fields
social-media
Use this skill when creating short-form social media content for LinkedIn, Twitter/X, or other platforms
embedded-systems
Use when developing firmware for microcontrollers, implementing RTOS applications, or optimizing power consumption. Invoke for STM32, ESP32, FreeRTOS, bare-metal, power optimization, real-time systems.
humanizer-zh
去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。 基于维基百科的"AI 写作特征"综合指南。检测并修复以下模式：夸大的象征意义、 宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、 AI 词汇、否定式排比、过多的连接性短语。
wechat-article
抓取微信公众号文章，提取标题和内容并输出为 Markdown 格式。支持多种提取方式。
building-with-claude-agent-sdk
A guide for building autonomous AI agents using Anthropic's Claude Agent SDK. It covers tool usage, permission modes, deployment, and security. Includes code examples for Python and TypeScript, plus unique features like file checkpointing and custom slash commands.
deps-health-inline
An inline orchestration workflow that automates dependency audits and updates through prioritized phases. It replaces separate orchestrator agents with direct execution, reducing token usage from ~10,000+ to ~500 while maintaining comprehensive dependency scanning, validation, and rollback capabilities.
pre-dev-dependency-map
A highly structured dependency mapping skill that enforces explicit technology choices with version control, security validation, and standards compliance through a rigorous gated workflow.
voice-and-tone
Provides concrete voice and tone rules for technical documentation, including specific examples of good vs. bad writing. Covers mechanics like second-person usage, sentence case, and terminology. Includes a practical quality checklist for writers to verify compliance.
skill-creator
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.
claude-win11-speckit-update-skill
A PowerShell-based tool for updating GitHub SpecKit installations while preserving user customizations. It detects file changes, creates backups, handles conflicts via VSCode merge tools, and uses a conversational approval workflow with Claude. Supports dry runs, rollbacks, and version-specific updates.
All Traditions Speaking as One
Deploy universal wisdom voices from all traditions simultaneously - Hindu, Buddhist, Taoist, Abrahamic, Indigenous, Scientific - revealing their unified recognition of consciousness navigation.
portfolio-roadmapping-bets
Use when managing multiple initiatives across time horizons (now/next/later, H1/H2/H3), balancing risk vs return across portfolio, sizing and sequencing bets with dependencies, setting exit/scale criteria for experiments, allocating resources across innovation types (core/adjacent/transformational), or when user mentions portfolio planning, roadmap horizons, betting framework, initiative prioritization, innovation portfolio, or resource allocation across horizons.
gpt5-consultant
Use this skill when stuck in circular debugging, when solutions aren't working despite multiple attempts, or when the user expresses frustration with lack of progress. Bring in GPT-5 as a third-party consultant to provide fresh perspective on complex technical problems, architectural decisions, or multi-system debugging issues. Ideal when you've tried multiple approaches without success, when the problem involves obscure edge cases or novel challenges, or when a second expert opinion would help break through an impasse. Gather all context from the conversation so far and present it comprehensively to GPT-5.
hypogenic
Automates scientific hypothesis generation from data and literature. Provides three methods: data-driven (HypoGeniC), literature-integrated (HypoRefine), and combined (Union). Includes PDF processing, iterative refinement, and performance caching. Published research shows 8-16% improvements over baselines.
bd-issue-tracking
A graph-based issue tracker designed for multi-session knowledge work with complex dependencies. It provides persistent memory across Claude conversation compaction cycles, with detailed guidance on when to use it versus TodoWrite. The tool includes session protocols, dependency management, and compaction survival strategies.
setting-detector
Automatically detects story settings (genres, time periods, themes) based on keywords and activates corresponding knowledge bases - works silently in the background to provide relevant writing guidance without user intervention
helm-chart-scaffolding
Design, organize, and manage Helm charts for templating and packaging Kubernetes applications with reusable configurations. Use when creating Helm charts, packaging Kubernetes applications, or implementing templated deployments.
reading-teacher
Generates interactive HTML/JS learning playgrounds for teaching reading to children ages 1-10. Creates phonics games, sight word activities, and comprehension exercises with audio support and progress tracking. Outputs runnable code that works in browsers.
memory-system
A comprehensive memory system for AI-assisted development that provides automatic context persistence with zero configuration, enforcing consistent workflow patterns across sessions.
api-patterns
Provides concrete patterns for building secure API routes with RLS, Zod validation, and structured error handling. Includes forbidden/correct code examples, checklists, response templates, and links to authoritative references. Focuses on preventing common security pitfalls in Next.js applications.
rust-engineer
A specialized Rust development assistant that enforces strict coding standards, memory safety, and performance optimization. It provides structured workflows for project analysis, implementation, and verification, integrating tools like cargo, clippy, and miri. Focuses on zero-cost abstractions, ownership patterns, and comprehensive testing.
tdd-guide
Comprehensive Test Driven Development guide for engineering subagents with multi-framework support, coverage analysis, and intelligent test generation
formik-patterns
This Skill provides practical code examples for implementing Formik forms with Yup validation in React Native projects. It covers common patterns like login forms, conditional validation, multi-step flows, and integration with GraphQL mutations. The examples include proper error handling, loading states, and form state management.