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.
security-engineer
This skill audits AI-generated code for security vulnerabilities, offering both quick checks during development and comprehensive audits. It detects hardcoded secrets, SQL injection, XSS, and other common issues, generating actionable reports. It integrates with development commands to block critical issues before testing or deployment.
datacommons-client
Provides a Python client for accessing Data Commons, a unified platform for public statistical data from sources like census bureaus and health organizations. It enables querying population, economic, and environmental data, resolving entity IDs, and exploring the underlying knowledge graph. The documentation includes clear examples for common workflows like fetching time-series data and batch processing.
pyhealth
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
tech-stack-evaluator
Comprehensive technology stack evaluation and comparison tool with TCO analysis, security assessment, and intelligent recommendations for engineering teams
claw-team-builder
Agent Team 规划与配置工具。通过多轮交互澄清需求，自动创建 Agent 配置、工作空间、Bootstrap 文件。 触发场景： - 用户说"创建新 Agent" / "新建 bot" / "配置多个 bot" - 用户说"规划 agent team" / "我需要几个不同的 agent" - 用户说"添加一个 agent" / "帮我建一个新 agent" - 用户提到需要不同场景使用不同的 AI 角色 功能： 1. 需求澄清 - 引导用户描述使用场景和 Agent 定位 2. 配置读取 - 自动读取现有 openclaw.json，分析已有配置 3. 方案设计 - 推荐 Agent 配置方案，检测冲突 4. 自动创建 - 创建目录、文件、更新配置 5. 配置验证 - 确保配置正确可用
dask
Provides Dask integration for scaling pandas/NumPy workflows beyond memory limits. Includes DataFrames for tabular data, Arrays for numeric operations, and Bags for unstructured data. Covers scheduler selection, chunk optimization, and common patterns like ETL pipelines and iterative algorithms.
ai-mlops
Provides concrete patterns for deploying ML models to production, including data ingestion with dlt, batch/API deployment, drift detection, and incident response. Includes templates for common tasks and clear decision trees for choosing appropriate strategies. Covers both traditional ML and LLM/RAG security considerations.
multi-agent-patterns
Provides structured patterns for designing multi-agent LLM systems to overcome single-agent context limits. Covers supervisor, peer-to-peer, and hierarchical architectures with concrete implementation examples. Includes memory layers and coordination protocols for distributing complex tasks across specialized agents.
claude-agent-sdk
Build autonomous AI agents with Claude Agent SDK. Structured outputs guarantee JSON schema validation, with plugins system and hooks for event-driven workflows. Prevents 14 documented errors. Use when: building coding agents, SRE systems, security auditors, or troubleshooting CLI not found, structured output validation, session forking errors, MCP config issues, subagent cleanup.
Backend Migration Standards
Provides concrete guidelines for creating database migrations with reversible changes, proper naming, and zero-downtime strategies. Includes specific code examples for Alembic, Rails, and Sequelize, plus practical advice on index management, data migrations, and deployment safety.
data-transform
This skill provides local data transformation using pandas and numpy, compatible with any LLM. It covers cleaning, normalization, reshaping, and feature engineering with practical code examples and troubleshooting guidance.
financial-analysis
Perform comprehensive financial analysis including DCF modeling, ratio analysis, and financial statement evaluation for companies and investment opportunities
agentdb-optimization
Provides concrete optimization techniques for AgentDB vector databases, including quantization methods (binary, scalar, product) for 4-32x memory reduction, HNSW indexing for 150x faster search, caching strategies, and batch operations. Includes specific performance benchmarks and configuration examples.
seaborn
This skill provides comprehensive guidance for using Seaborn to create statistical visualizations in Python. It covers both function and object interfaces, explains when to use different plot types, and includes practical patterns for EDA and publication figures. The documentation addresses common troubleshooting scenarios and integrates well with matplotlib.
get-available-resources
Detects CPU, GPU, memory, and disk resources to provide data-driven recommendations for computational tasks. Outputs a JSON file with hardware specs and suggests appropriate libraries (Dask, PyTorch, etc.) based on available resources. Helps decide between parallel processing, GPU acceleration, or memory-efficient strategies before running intensive jobs.
pydicom
Provides guidance for using pydicom to read, write, and manipulate DICOM medical imaging files. Covers pixel data extraction, metadata handling, format conversion, compression, and anonymization. Includes installation instructions, code examples for common workflows, and troubleshooting tips for compression issues.
agent-evaluation
Provides a detailed framework for evaluating Claude Code agents and skills, covering evaluation methods, metrics, and practical implementation guidance. Focuses on outcome-based assessment rather than exact execution paths, with specific metrics for different evaluation scenarios.
molfeat
Molfeat provides a unified interface for molecular featurization, supporting 100+ methods from fingerprints to pretrained models. It offers scikit-learn compatible transformers, parallel processing, and clear guidance on choosing featurizers for different ML tasks like QSAR and virtual screening.
networkx
This skill provides Python-based graph and network analysis capabilities through NetworkX. It enables creating, analyzing, and visualizing complex networks with algorithms for shortest paths, centrality measures, and community detection. Supports multiple graph types and file formats for real-world network data.
pennylane
Hardware-agnostic quantum ML framework with automatic differentiation. Use when training quantum circuits via gradients, building hybrid quantum-classical models, or needing device portability across IBM/Google/Rigetti/IonQ. Best for variational algorithms (VQE, QAOA), quantum neural networks, and integration with PyTorch/JAX/TensorFlow. For hardware-specific optimizations use qiskit (IBM) or cirq (Google); for open quantum systems use qutip.
office
Generate Office documents (DOCX, XLSX, PDF, PPTX) with TypeScript. Pure JS libraries that work everywhere: Claude Code CLI, Cloudflare Workers, browsers. Uses docx (Word), xlsx/SheetJS (Excel), pdf-lib (PDF), pptxgenjs (PowerPoint). Use when: creating invoices, reports, spreadsheets, presentations, form filling, exporting data to Office formats, or troubleshooting "Packer.toBuffer", "XLSX.utils", "PDFDocument", "pptxgenjs" errors.
dwarf-expert
Provides expertise for analyzing DWARF debug files and understanding the DWARF debug format/standard (v3-v5). Triggers when understanding DWARF information, interacting with DWARF files, answering DWARF-related questions, or working with code that parses DWARF data.
codex-claude-loop
Implements a dual-AI engineering loop where Claude handles code implementation while Codex validates plans and reviews changes. Creates a self-correcting system with continuous feedback between two AI models to catch logic errors, security issues, and architectural flaws before deployment.
test-reporting-analytics
Comprehensive test reporting and analytics skill with excellent structure, practical templates, and clear guidance for different audiences and use cases.