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.
obsidian-leaflet-mapping
This skill provides detailed guidance for using the Obsidian Leaflet plugin to create interactive maps directly within markdown notes. It covers real-world maps, image overlays, marker generation from note metadata, and troubleshooting common setup issues. The instructions are specific to integrating spatial data with a knowledge management workflow.
rls-patterns
Provides concrete patterns for implementing Row Level Security with Prisma using context wrappers. Enforces data isolation between users, admins, and system processes with clear code examples and forbidden patterns. Includes specific guidance for Next.js dynamic rendering requirements and testing procedures.
arboreto
Infer gene regulatory networks (GRNs) from gene expression data using scalable algorithms (GRNBoost2, GENIE3). Use when analyzing transcriptomics data (bulk RNA-seq, single-cell RNA-seq) to identify transcription factor-target gene relationships and regulatory interactions. Supports distributed computation for large-scale datasets.
histolab
Histolab provides Python tools for processing whole slide pathology images. It detects tissue regions, extracts tiles using random, grid, or scoring methods, and prepares datasets for computational pathology workflows. The skill includes sample datasets, multiple mask types, and detailed troubleshooting guides for common extraction issues.
aws-sdk-java-v2-bedrock
A comprehensive Java SDK skill for Amazon Bedrock with practical patterns for model invocation, streaming, embeddings, and Spring Boot integration, though security guidance could be enhanced.
langchain4j-rag-implementation-patterns
A comprehensive skill for implementing RAG systems with LangChain4j, providing practical code examples, configuration patterns, and best practices for Java developers building knowledge-enhanced AI applications.
deeptools
NGS analysis toolkit. BAM to bigWig conversion, QC (correlation, PCA, fingerprints), heatmaps/profiles (TSS, peaks), for ChIP-seq, RNA-seq, ATAC-seq visualization.
AgentDB Advanced Features
Master advanced AgentDB features including QUIC synchronization, multi-database management, custom distance metrics, hybrid search, and distributed systems integration. Use when building distributed AI systems, multi-agent coordination, or advanced vector search applications.
pinecone
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure.
mongodb-usage
This skill should be used when user asks to "query MongoDB", "show database collections", "get collection schema", "list MongoDB databases", "search records in MongoDB", or "check database indexes".
code-review
Enforces strict code review and verification protocols for AI-assisted development. Provides concrete rules for receiving feedback, requesting reviews via subagents, and preventing false completion claims. Focuses on evidence-based validation over performative responses.
pre-dev-data-model
A structured process for creating technology-agnostic data models before database implementation. It enforces separation of conceptual modeling from implementation details with clear rules, checklists, and validation gates.
frontend-dev-guidelines
Provides detailed React/TypeScript development guidelines focusing on modern patterns like Suspense, lazy loading, TanStack Query, and feature-based file organization. Includes practical checklists, import aliases, and code examples for common scenarios like forms, data fetching, and optimistic updates.
bulktrajblend-trajectory-interpolation
This skill bridges gaps in single-cell developmental trajectories by generating synthetic intermediate cells from bulk RNA-seq data. It trains a beta-VAE to create cells and a GNN to identify overlapping communities, then interpolates missing states to improve trajectory continuity. The workflow is detailed with specific code examples and troubleshooting tips.
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。
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.
memory-system
A comprehensive memory system for AI-assisted development that provides automatic context persistence with zero configuration, enforcing consistent workflow patterns across sessions.
gastown
Gastown is a Go-based multi-agent orchestration system for Claude Code that enables parallel task execution. It provides work tracking through beads, manages agent lifecycles via polecats and crew, and handles automated code merging through the Refinery. Requires Go installation and terminal access.
ai-voice-cloning
AI voice generation, text-to-speech, and voice synthesis via inference.sh CLI. Models: Kokoro TTS, DIA, Chatterbox, Higgs, VibeVoice for natural speech. Capabilities: multiple voices, emotions, accents, long-form narration, conversation. Use for: voiceovers, audiobooks, podcasts, video narration, accessibility. Triggers: voice cloning, tts, text to speech, ai voice, voice generation, voice synthesis, voice over, narration, speech synthesis, ai narrator, elevenlabs alternative, natural voice, realistic speech, voice ai
regulatory-templates-gate2
Gate 2 validation sub-skill for regulatory template workflows. Validates uncertain field mappings from Gate 1 using test data, enforces strict validation thresholds (>90% pass rate, 100% mandatory validation), and prevents incorrect mappings from reaching production templates. Acts as a quality firewall before template generation.
pufferlib
Provides tools for high-performance RL training with PPO, vectorized environment simulation, and custom environment development. Includes CLI commands, Python code examples for training loops, environment templates, and performance optimization techniques.
pyhealth
PyHealth provides a specialized Python toolkit for healthcare machine learning with clinical datasets, prediction tasks, and medical coding. It offers standardized interfaces for EHR data, implements healthcare-specific models like RETAIN, and includes fairness evaluation tools for clinical deployment.
ebfe-validator
A specialized validation tool for HEC-RAS eBFE/BLE models that systematically checks file references, path validity, and data accessibility to ensure models are runnable and automation-ready.
langchain4j-ai-services-patterns
A comprehensive skill for building type-safe, declarative AI services in Java using LangChain4j patterns, offering excellent practicality and maintainability for Java developers implementing AI features.