Discover Agent Skills for data science & ml. Browse 61 skills for Claude, ChatGPT & Codex.
Queries official R Shiny framework documentation to build, debug, and deploy interactive web applications.
Accesses real-time R package documentation, vignettes, and task views across CRAN, tidyverse, and Bioconductor ecosystems.
Generates publication-ready methods and results sections for clinical prediction and machine learning papers using TRIPOD+AI standards.
Standardizes AI/ML delivery with end-to-end guidance on experiment design, model validation, and governance for production-grade AI.
Enforces rigorous academic integrity and adherence to international reporting guidelines for quantitative research manuscripts.
Identifies and verifies recurring structural patterns across diverse domains to validate novelty and discover universal insights.
Stress-tests research findings and syntheses through recursive adversarial testing to uncover hidden biases and overlooked evidence.
Analyzes information gaps and silences across multiple sources to reveal structural biases, funding influences, and hidden narrative frames.
Enables developers to programmatically build, design, and orchestrate autonomous AI agents using the Claude Agent SDK.
Manages a centralized catalog of AI coaching skills, TypeScript contracts, and safety guardrails for the Run-Smart platform.
Processes and manipulates Excel spreadsheets within the OpenClaw environment using native tool execution flows.
Optimizes AI workloads by intelligently routing tasks to the most suitable model profile based on quality, latency, and cost constraints.
Conducts data-driven market research, competitive analysis, and investor due diligence with verified source attribution.
Optimizes LLM workflows and pipeline architectures by balancing performance tradeoffs and operational costs through evidence-based decision making.
Optimizes structured text extraction by combining high-speed Regex patterns with LLM validation for complex edge cases.
Designs and optimizes AI agent action spaces and tool definitions to maximize completion rates and reliability.
Conducts deep market research, competitive analysis, and investor due diligence with verified sourcing and decision-ready summaries.
Performs specialized financial analysis and modeling using OpenClaw-native workflows and explicit verification.
Performs automated financial ratio analysis, DCF valuations, and rolling forecast construction for data-driven strategic decision-making.
Streamlines the implementation and verification of foundation models on local devices using OpenClaw-native workflows.
Architects and deploys production-grade computer vision systems for object detection, image segmentation, and visual AI tasks.
Optimizes AI agent action spaces and tool definitions to maximize completion rates and task reliability within Claude Code.
Optimizes AI agent tool definitions, observation formats, and action spaces to maximize task completion rates.
Provides senior-level computer vision expertise and deterministic guidance for OpenClaw-native development workflows.
Orchestrates AI agent behavior and infrastructure to ensure reliable, high-performance execution within the OpenClaw ecosystem.
Optimizes LLM prompts, evaluates RAG performance, and designs sophisticated agentic workflows for AI-driven applications.
Optimizes data extraction pipelines by evaluating and implementing regex-based versus LLM-driven parsing strategies.
Optimizes prompts, evaluates RAG performance, and designs complex agentic workflows for high-performance LLM applications.
Empowers Claude with senior-level data science expertise and engineering-grade execution patterns for complex data workflows.
Automates professional spreadsheet creation, financial modeling, and data analysis with dynamic formulas and industry-standard formatting.
Scroll for more results...