Marketplace
Find the right skill for the job.
Browse the full catalog through outcome-first channels, technical facets, rating filters, and server-side pagination built for a large public marketplace.
trading-coach
🏆 AI交易复盘教练 — 把你的券商CSV变成可执行的改进洞察！ 自动FIFO配对持仓，8维度质量评分(入场/出场/趋势/风险...)，10维度AI洞察。 支持富途(中/英)、老虎、中信、华泰等主流券商。 触发条件: 用户提供交易CSV、要求分析交易表现、评估交易质量、生成复盘报告、 计算盈亏统计、识别交易模式问题、"帮我复盘"、"分析我的交易"。
Swarm Orchestration
Coordinates multiple AI agents for parallel task execution using mesh, hierarchical, or adaptive topologies. Provides memory sharing, load balancing, and fault tolerance for complex workflows. Integrates with agentic-flow hooks for pre/post-task coordination.
server-actions
This skill helps developers create and manage Next.js server actions for form submissions, data mutations, and server-side logic. It provides concrete examples for blog posts, analytics tracking, and cache revalidation with practical patterns for validation, authentication, and file uploads.
moai-lang-r
This skill provides detailed R 4.4+ development guidance covering tidyverse, ggplot2, Shiny apps, and data science workflows. It includes modern R syntax examples, package development patterns, and production deployment instructions. The documentation offers concrete code patterns for common data analysis tasks.
moai-foundation-core
A foundational framework for AI-driven development that enforces quality standards via TRUST 5 principles and SPEC-First TDD. It provides concrete patterns for agent delegation, token budgeting, and modular architecture. Includes troubleshooting guides and diagnostic commands for real-world implementation.
convex-realtime
Provides guidance for implementing live data subscriptions using Convex's reactive query system. Shows how to auto-update UI components when backend data changes, useful for chat apps, dashboards, and collaborative editing features.
moai-domain-database
Provides concrete code examples for PostgreSQL, MongoDB, and Redis operations including connection setup, query patterns, and multi-database coordination. Covers practical scenarios like user data routing, cache warming, and rate limiting with working JavaScript/TypeScript implementations.
inmemoria
In Memoria builds persistent semantic understanding of codebases for AI agents via MCP. It learns project patterns once, then serves that intelligence without re-parsing. Includes setup, learn, check, watch, and server commands. Works with Claude, Copilot, and other MCP tools.
iot-engineer
Provides MCP tools and workflows for designing and implementing IoT solutions, covering device connectivity, edge processing, cloud integration, and data pipelines. It includes structured checklists, specific tool integrations for MQTT, AWS IoT, and Azure IoT, and predefined communication protocols for systematic IoT project execution.
context-manager
This skill manages shared state and context across multiple AI agents, focusing on fast retrieval (<100ms), strong consistency, and secure storage. It integrates with Redis, Elasticsearch, and vector databases to handle project metadata, task history, and agent interactions. The skill provides structured workflows for architecture analysis, implementation, and monitoring of distributed context systems.
langchain
Imported from https://www.skillhub.club/skills/langchain-ai-langchain.
coding-tutor
Personalized coding tutorials that build on your existing knowledge and use your actual codebase for examples. Creates a persistent learning trail that compounds over time using the power of AI, spaced repetition and quizes.
ai-news-daily-v1-0-3
AI 新闻日报 v1.0.3 - 自动抓取全球 AI 行业最新动态，每日推送 10 条精选新闻。支持英文标题/内容自动翻译、400-500 字中文摘要、外部配置 (config.yaml)、失败重试、智能去重。安装后自动创建 OpenClaw 定时任务，每天早上 9:00 自动推送到对话框。用于定时抓取 AI 新闻、RSS 聚合、多语言支持。
ai-news-zh
中文AI科技日报自动采集与推送。从The Verge、Wired、TechCrunch等英文源抓取最新AI资讯，自动翻译整理为中文，按分类推送到飞书/Telegram/Discord等渠道。适合关注AI行业动态的中文用户。
context-engineering
A skill focused on managing LLM context windows for agent systems. It provides principles, patterns, and scripts for reducing token usage while maintaining reasoning quality. Covers context degradation, compression strategies, multi-agent coordination, and evaluation methods.
pr-resolver
Automates GitHub PR review resolution by processing every comment and fixing all CI failures with strict commit-per-fix cadence. Enforces fresh data fetching and zero unresolved threads as mandatory requirements. Uses conventional commits and handles pagination for large PRs.
agent-organizer
This skill coordinates multiple AI agents for complex tasks. It breaks down work, selects suitable agents based on capabilities, and manages task execution. It includes checklists for agent selection, dependency handling, and performance monitoring.
creating-financial-models
Provides DCF analysis, Monte Carlo simulations, and sensitivity testing for investment decisions. Generates Excel workbooks with financial projections, valuation summaries, and risk metrics. Supports corporate valuation, project finance, and M&A analysis with built-in quality checks.
langfuse-observability
Provides self-hosted LLM observability with tracing, cost tracking, prompt versioning, and automated evaluation. Integrates directly into Python applications via decorators and client libraries for monitoring model usage and response quality.
codex
Execute Codex CLI for code analysis, refactoring, and automated code changes. Use when you need to delegate complex code tasks to Codex AI with file references (@syntax) and structured output.
nano-banana
This skill should be used for Python scripting and Gemini image generation. Use when users ask to generate images, create AI art, edit images with AI, or run Python scripts with uv. Trigger phrases include "generate an image", "create a picture", "draw", "make an image of", "nano banana", or any image generation request.
always-init
A context loader that automatically loads personal AI infrastructure (contacts, preferences, protocols) before processing any user request. It enforces a 'context-first' architecture by requiring invocation before all other operations.
ai-integration
Provides concrete implementation patterns for building RAG systems, vector search, and LLM API integrations with working code examples for ChromaDB, Pinecone, and Weaviate. Covers practical aspects like error handling, cost optimization, and observability.
git-writer
A git skill focused on safe file removal operations using git rm. It enforces checks for uncommitted changes, provides clear decision trees, and prevents data loss by banning destructive commands like git reset --hard. Works alongside a git-reader agent for read operations.