Best skills for Data scientist
For data scientists, data quality and computational scalability are non-negotiable. The AI coding skills in this directory zero in on two critical areas: historical data validation and HPC cluster management. Historical data validation tools automate the detection of inconsistencies, outliers, and sampling biases across large datasets—a must for building trustworthy models. Watch out for brittle validation pipelines: opt for smart approaches that flag issues without blindly discarding records. On the compute side, managing HPC clusters (like TACC Vista) lets you scale beyond a single workstation, accelerating not just training but also data preprocessing and hyperparameter tuning. The trick is to profile memory usage to avoid over-provisioning, and to orchestrate parallel jobs efficiently. These skills bridge the gap between raw data and production-ready insights, ensuring your models are both accurate and performant.
16 skills selected
Pointline Data Lake Research API
Data & AI
Reference for the Pointline data lake research API used by quant researchers. Covers querying event data (trades, quotes, orderbook, CN L2/L3 tables), symbol discovery/resolution, building time-series spines (clock, trades, volume, dollar bars), decoding fixed-point scaled integers, attaching PIT-correct symbol metadata, filtering by trading phase, and ingesting Bronze files into Silver. Useful when working with a PIT-accurate offline data lake built on Polars and Delta Lake.
Create Interactive Maps with kepler.gl
Data & AI
Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.
Polyclaw: AI news scanner & auto-trader
Data & AI
AI-powered news edge scanner and auto-trader for Polymarket. Ingests real-time news, matches markets, estimates probability shifts, detects edges, and auto-trades via CLOB API.
Online Covariance Estimation with Precise
Data & AI
A numpy-only library for online (incremental) covariance, correlation, and precision estimation, complementing sklearn.covariance.
PDF File Processing
Data & AI
Extracts text from PDFs, fills forms, and merges documents. Includes scripts for analyzing structure, extracting content, filling form fields, and validating outputs. Useful for automated PDF document processing.
LangChain Core Workflow: Chains & Prompts
Data & AI
Build LangChain chains and prompts using LangChain Expression Language (LCEL). This skill covers creating prompt templates, composing chains (sequential, parallel, branching), and output parsing. It helps when you need structured LLM workflows with reusable components.
Crypto Market Movers Scanner
Data & AI
Real-time detection and analysis of significant price movements and unusual volume patterns across cryptocurrency markets. This skill identifies top gainers, losers, and volume spikes.
ML Demo Interfaces with Gradio
Data & AI
Build interactive web demos for machine learning models using Gradio. Supports images, text, audio, and video inputs/outputs.
ML Experiment Tracker
Data & AI
Document and track your machine learning experiments in a structured way.
Optimizing Staking Rewards
Data & AI
Compare and optimize staking rewards across validators, protocols, and blockchains with risk assessment. Analyze PoS opportunities, calculate net yields, and maximize returns.
LangChain Agent Scaffolder
Data & AI
Generates a LangGraph ReAct agent with custom tools and OpenAI-compatible endpoint configuration.
LangChain/LangGraph Agent Development Expert
Data & AI
Expert guidance for building production-grade AI agents using LangChain 0.1+ and LangGraph, including RAG, memory systems, and multi-agent orchestration.
Iron Condor Strategy
Data & AI
Analyzes iron condor credit spreads with OTM puts and calls for range-bound trading. Profits from time decay and volatility contraction.
Taoguba Crawler
Data & AI
Skill to run Taoguba (tgb.cn) web crawlers for scraping forum articles and generating HTML outputs.
SHAP Model Explainability Skill
Data & AI
Skill for SHAP-based model explainability, including feature attribution, summary plots, and interaction analysis.
Opentrons Protocol Agent
Data & AI
Generates executable Python protocols for Opentrons OT-2 and Flex robots from natural language descriptions.
How to choose
- How are these skills selected?
- An algorithm picks them among the published skills that match this page's criteria, such as category, tags or compatible tools. It ranks them by the quality score a language model gave them. On ranking pages, it also weighs GitHub stars and the security rating. Nobody reviews them one by one.
- What do the security ratings mean?
- A language model reads the SKILL.md file, without running it, and gives it a rating. Safe means it sees no meaningful execution risk. Caution means the skill uses powerful tools such as bash, docker or the network for a legitimate purpose. Risky means it asks for destructive actions, for secrets to be sent out, or for obfuscated code to run; a skill rated Risky is never published. The rating does not replace your own reading of the file.
- How do I install a skill?
- Open any skill page and follow its install instructions for your tool — Claude Code, Cursor or Copilot. Each skill lists the exact steps so you can get it running in a couple of minutes.