Data Science & AI Research Skills
570 data science, AI research, and analysis skills for coding agents. Data pipeline, ML model dev, statistical analysis - pre-verified and MCP-ready.
Statsmodels
Statistical models library for Python. Use when you need specific model classes (OLS, GLM, mixed models, ARIMA) with detailed diagnostics, residuals, and inference. Best for econometrics, time series, rigorous inference with coefficient tables. For guided statistical test selection with APA reporting use statistical-analysis.
Statsmodels
Statistical modeling toolkit. OLS, GLM, logistic, ARIMA, time series, hypothesis tests, diagnostics, AIC/BIC, for rigorous statistical inference and econometric analysis.
Stock Liquidity
Analyze stock liquidity using bid-ask spreads, volume profiles, order book depth, market impact estimates, and turnover ratios via Yahoo Finance data. Use this skill whenever the user asks about liquidity, trading costs, bid-ask spread, market depth, volume analysis, slippage, market impact, turnover ratio, or how easy/hard it is to trade a stock without moving the price. Triggers: "how liquid is AAPL", "bid-ask spread", "volume analysis", "order book depth", "market impact of a large order", "turnover ratio", "slippage estimate", "can I trade 100k shares without moving the price", "liquidity comparison", "spread analysis", "ADTV", "Amihud illiquidity", "dollar volume", "execution cost estimate", "liquidity score", penny stocks, small caps, or thinly traded securities.
Structured Extraction
Extract structured data matching a JSON schema from websites. Handles complex nested schemas, arrays, pagination, and validation. Always outputs via formatOutput.
Svm
Explore Solana's architecture and protocol internals. Covers the SVM execution engine, account model, consensus, transactions, validator economics, data layer, development tooling, and token extensions using the Helius blog, SIMDs, and Agave/Firedancer source code.
Synthesize
Synthesize information across multiple sources into a structured document. Processes sources in batches across sessions to handle more data than fits in context. Discovers and queues related sources automatically. Use for research synthesis, topic deep-dives, or consolidating scattered notes. Triggers on "synthesize", "synthesis", "research [topic]".
Synthesize Research
Synthesize user research from interviews, surveys, and feedback into structured insights. Use when you have a pile of interview notes, survey responses, or support tickets to make sense of, need to extract themes and rank findings by frequency and impact, or want to turn raw feedback into roadmap recommendations.
Table Extractor
>
Task Researcher Instructions
Task research specialist for comprehensive project analysis - Brought to you by microsoft/edge-ai
Tavily
Tavily web search, content extraction, and research tools.
Tcm Constitution Analyzer
分析中医体质数据、识别体质类型、评估体质特征,并提供个性化养生建议。支持与营养、运动、睡眠等健康数据的关联分析。
Technical spike research mode
Systematically research and validate technical spike documents through exhaustive investigation and controlled experimentation.
Telegram Reader
Read Telegram channels and groups for financial news and market research using tdl (read-only). Use this skill whenever the user wants to read Telegram channels, export messages from financial Telegram groups, list their Telegram chats, search for news in Telegram channels, or gather market intelligence from Telegram. Triggers include: "check my Telegram", "read Telegram channel", "Telegram news", "what's new in my Telegram channels", "export messages from", "list my Telegram chats", "financial news on Telegram", "crypto Telegram", "market news Telegram", any mention of Telegram in context of reading financial news, crypto signals, or market research. This skill is READ-ONLY — it does NOT support sending messages, joining channels, or any write operations.
Tensorboard
Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML visualization toolkit
Timesfm Forecasting
Zero-shot time series forecasting with Google's TimesFM foundation model. Use this skill when forecasting ANY univariate time series — sales, sensor readings, stock prices, energy demand, patient vitals, weather, or scientific measurements — without training a custom model. Automatically checks system RAM/GPU before loading the model, supports CSV/DataFrame/array inputs, and returns point forecasts with calibrated prediction intervals. Includes a preflight system checker script that MUST be run before first use to verify the machine can load the model. For classical statistical time series models (ARIMA, SARIMAX, VAR) use statsmodels; for time series classification/clustering use aeon.
Timesfm Forecasting
Zero-shot time series forecasting with Google's TimesFM foundation model. Use for any univariate time series (sales, sensors, energy, vitals, weather) without training a custom model. Supports CSV/DataFrame/array inputs with point forecasts and prediction intervals. Includes a preflight system checker script to verify RAM/GPU before first use.
Torchdrug
Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets, for PyTorch-based ML on molecules, proteins, and biomedical graphs.
Torchdrug
PyTorch-native graph neural networks for molecules and proteins. Use when building custom GNN architectures for drug discovery, protein modeling, or knowledge graph reasoning. Best for custom model development, protein property prediction, retrosynthesis. For pre-trained models and diverse featurizers use deepchem; for benchmark datasets use pytdc.
Torch Geometric
Graph Neural Networks (PyG). Node/graph classification, link prediction, GCN, GAT, GraphSAGE, heterogeneous graphs, molecular property prediction, for geometric deep learning.
Torch Geometric
PyTorch Geometric (PyG) for graph neural networks — node/link/graph classification, message passing (GCN, GAT, GraphSAGE, GIN), heterogeneous graphs, neighbor sampling, and custom datasets. Use when working with torch_geometric, not for general NetworkX analytics or non-graph PyTorch models.
Trace
Analyzing session replays, extracting persona-based behavioral patterns, and storytelling UX issues. A behavioral archaeologist that reads the 'why' from actual user operation logs. Collaborates with Field/Echo for persona validation.
Trade Hypothesis Ideator
Generate falsifiable trade strategy hypotheses from market data, trade logs, and journal snippets. Use when you have a structured input bundle and want ranked hypothesis cards with experiment designs, kill criteria, and optional strategy.yaml export compatible with edge-finder-candidate/v1.
Trader Memory Core
Track investment theses across their lifecycle — from screening idea to closed position with postmortem. Register theses from screener outputs, manage state transitions, attach position sizing, review due dates, and generate postmortem reports with P&L and MAE/MFE analysis. Trigger when user says "register thesis", "track this idea", "thesis status", "review due", "close position", "postmortem", or "trading journal".
Tradingview Reader
Read TradingView desktop app for market data, news, alerts, watchlists, and screener results using opencli (read-only). Use this skill whenever the user wants quotes, options chains, options expiries, screener results across stocks/crypto/forex/futures/bonds, gainers/losers/movers, news headlines or full story bodies, alerts (active list, fire log, offline fires), watchlists including colored flag lists, symbol search/autocomplete, chart state, or screenshots from their local TradingView.app. Triggers include: "options chain for X", "IV on Y", "show me SNDK puts", "TV screener for Y sector", "screen oversold stocks", "TV gainers", "crypto by market cap", "TradingView news on AAPL", "show my watchlists", "red flag list", "list my alerts", "what alerts fired", "search TV for nvidia", "what symbol is on my chart", "screenshot NVDA chart", "TradingView IV skew", "TV expiries for X". This skill is READ-ONLY — it does NOT place trades, modify watchlists, or change chart layouts.
Training Check
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
Training Check
Interactively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
Training LLMs Megatron
Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
Train Sentence Transformers
Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval / pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.
Transcribe
Transcribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from recordings, or label speakers in interviews or meetings.
Transcribe Video
Generate subtitles (SRT/VTT) and plain text transcripts from video or audio files using AWS Transcribe. Use when creating captions, extracting spoken content, generating transcripts for notes, or making video content searchable.
Transformer Lens Interpretability
Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.
Transformers JS
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classification, object detection), audio (speech recognition, audio classification), and multimodal tasks. Works in browsers and server-side runtimes (Node.js, Bun, Deno) with WebGPU/WASM using pre-trained models from Hugging Face Hub.
Travel Health Analyzer
分析旅行健康数据、评估目的地健康风险、提供疫苗接种建议、生成多语言紧急医疗信息卡片。支持WHO/CDC数据集成的专业级旅行健康风险评估。
Tripadvisor
TripAdvisor Content API for hotel ratings, restaurant search, attraction reviews, rankings, and nearby locations. Use when evaluating hotels or researching destinations. 5K calls/month.
Troubleshooting Dbt Job Errors
Diagnoses dbt Cloud/platform job failures by analyzing run logs, querying the Admin API, reviewing git history, and investigating data issues. Use when a dbt Cloud/platform job fails and you need to diagnose the root cause, especially when error messages are unclear or when intermittent failures occur. Do not use for local dbt development errors.
Twitter Reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my bookmarks", "who follows", "look up @user", "what's trending about", "market sentiment on Twitter", "what are people saying about AAPL", "recent tweets from @elonmusk", "show me @user's posts", "fintwit", any mention of Twitter/X in context of reading financial news or market research. This skill is READ-ONLY — it does NOT support posting, liking, retweeting, or any write operations.
TypeScript MCP Server Expert
Expert assistant for developing Model Context Protocol (MCP) servers in TypeScript
Umap Learn
UMAP dimensionality reduction. Fast nonlinear manifold learning for 2D/3D visualization, clustering preprocessing (HDBSCAN), supervised/parametric UMAP, for high-dimensional data.
Umap Learn
Use UMAP-learn for nonlinear dimensionality reduction, 2D/3D embeddings, clustering preprocessing, supervised or semi-supervised UMAP, DensMAP, AlignedUMAP, and Parametric UMAP workflows.
Understand Knowledge
Analyze a Karpathy-pattern LLM wiki knowledge base and generate an interactive knowledge graph with entity extraction, implicit relationships, and topic clustering.
Uniprot Database
Direct REST API access to UniProt. Protein searches, FASTA retrieval, ID mapping, Swiss-Prot/TrEMBL. For broader biological evidence lookup across databases, use bio-database-evidence. Use this for direct HTTP/REST work or UniProt-specific control.
Uptrend Analyzer
Analyzes market breadth using Monty's Uptrend Ratio Dashboard data to diagnose the current market environment. Generates a 0-100 composite score from 5 components (breadth, sector participation, rotation, momentum, historical context). Use when asking about market breadth, uptrend ratios, or whether the market environment supports equity exposure. No API key required.
User Research
Plan, conduct, and synthesize user research. Trigger with "user research plan", "interview guide", "usability test", "survey design", "research questions", or when the user needs help with any aspect of understanding their users through research.
Usfiscaldata
Query the U.S. Treasury Fiscal Data API for federal financial data including national debt, government spending, revenue, interest rates, exchange rates, and savings bonds. Access 54 datasets and 182 data tables with no API key required. Use when working with U.S. federal fiscal data, national debt tracking (Debt to the Penny), Daily Treasury Statements, Monthly Treasury Statements, Treasury securities auctions, interest rates on Treasury securities, foreign exchange rates, savings bonds, or any U.S. government financial statistics.
Using Dbt For Analytics Engineering
Builds and modifies dbt models, writes SQL transformations using ref() and source(), creates tests, and validates results with dbt show. Use when doing any dbt work - building or modifying models, debugging errors, exploring unfamiliar data sources, writing tests, or evaluating impact of changes.
Us Market Bubble Detector
Evaluates market bubble risk through quantitative data-driven analysis using the revised Minsky/Kindleberger framework v2.1. Prioritizes objective metrics (Put/Call, VIX, margin debt, breadth, IPO data) over subjective impressions. Features strict qualitative adjustment criteria with confirmation bias prevention. Supports practical investment decisions with mandatory data collection and mechanical scoring. Use when user asks about bubble risk, valuation concerns, or profit-taking timing.
Uspto Database
Access USPTO APIs for patent/trademark searches, examination history (PEDS), assignments, citations, office actions, TSDR, for IP analysis and prior art searches.
Vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.
Vaex
Use this skill for processing and analyzing large tabular datasets (billions of rows) that exceed available RAM. Vaex excels at out-of-core DataFrame operations, lazy evaluation, fast aggregations, efficient visualization of big data, and machine learning on large datasets. Apply when users need to work with large CSV/HDF5/Arrow/Parquet files, perform fast statistics on massive datasets, create visualizations of big data, or build ML pipelines that do not fit in memory.
Validate Healthcare Data
Comprehensive data quality validation for healthcare datasets. Use when validating patient records, medical codes, insurance data, or preparing healthcare data for production.
Validation
Use after creating or modifying ANY Honeydew object (metric, attribute, entity, domain). Provides type-specific validation logic to ensure objects work correctly and return sensible results.
Venice API Overview
High-level map of the Venice.ai API - base URL, authentication modes, endpoint categories, response headers, pricing model, error shape, and versioning. Load this first when starting any Venice integration.
Venice Audio Music
Async music / audio-track generation via Venice. Covers the /audio/quote + /audio/queue + /audio/retrieve + /audio/complete lifecycle, lyrics vs instrumental, voice selection, duration, language, speed, model capability probing, and webhook-free polling.
Venice Audio Transcription
Transcribe audio files to text via POST /audio/transcriptions. Covers supported models (Parakeet, Whisper, Wizper, Scribe, xAI STT), supported formats (wav/flac/m4a/aac/mp4/mp3/ogg/webm), response formats (json/text), timestamps, and language hints. OpenAI-compatible multipart.
Venice Characters
Discover and use Venice public characters (persona-driven system prompts with a bound model). Covers GET /characters (search/filter/sort), /characters/{slug}, /characters/{slug}/reviews, the Character schema, and how to apply a character via venice_parameters.character_slug in chat completions.
Venice Embeddings
Call POST /embeddings on Venice. Covers request shape (input, model, encoding_format, dimensions, user), OpenAI compatibility, response compression (gzip/br), and practical usage for retrieval, clustering, and RAG.
Venice Models
Discover Venice models, their capabilities, constraints, and pricing. Covers GET /models (with ?type filter), /models/traits, /models/compatibility_mapping, the ModelResponse schema (capabilities, constraints, pricing per type), and how to use this to pick the right model programmatically.
Verify Sources
Captures human source verification for tracks, timestamps it, and updates track files. Use when sources need human review before generation.
Verl Rl Training
Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends.
Weather
Current weather and forecasts with web_fetch, falling back to wttr.in curl for locations, rain, temperature, travel planning.
Web Search
Formulate effective web search queries, analyze search results, and synthesize findings. Optimize search strategies for different types of information needs.
Webthinker Deep Research
Deep web research for VCO: multi-hop search+browse+extract with an auditable action trace and a structured report (WebThinker-style).
Weights And Biases
Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collaborative MLOps platform
What If Oracle
Run structured What-If scenario analysis with 4–6 branch possibility exploration (best, likely, worst, wild card, contrarian, second-order). Use when the user asks speculative what-if questions about uncertain futures, strategic forks, contingency planning, or stress-testing a decision before committing.
Whisper
OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes from tiny (39M params) to large (1550M params). Use for speech-to-text, podcast transcription, or multilingual audio processing. Best for robust, multilingual ASR.
Working With Dbt Mesh
Use when changing a dbt model in a way that could break its consumers — renaming, removing, or retyping a column, or changing a model that downstream models, exposures, dashboards, or BI tools depend on — to judge whether the change is breaking and who it affects. Also use when versioning a model (model versions, latest_version, latest_version_pointer, deprecation_date, migration windows), enforcing contracts, setting access or groups, or doing multi-project dbt Mesh work (cross-project refs via dependencies.yml, disambiguating similarly-named models, splitting a monolith). Covers single- and multi-project, and planning or advising as well as implementing.
Yfinance Data
Fetch financial and market data using the yfinance Python library. Use this skill whenever the user asks for stock prices, historical data, financial statements, options chains, dividends, earnings, analyst recommendations, or any market data. Triggers include: any mention of stock price, ticker symbol (AAPL, MSFT, TSLA, etc.), "get me the financials", "show earnings", "what's the price of", "download stock data", "options chain", "dividend history", "balance sheet", "income statement", "cash flow", "analyst targets", "institutional holders", "compare stocks", "screen for stocks", or any request involving Yahoo Finance data. Always use this skill even if the user only provides a ticker — infer intent from context.
Youtube Search
Search YouTube and return structured video results with metadata and engagement metrics using yt-dlp. USE WHEN youtube search, find videos, search videos, video research, youtube results, channel research, video metrics, trending videos, content research. Even if the user just says "search YouTube for X" or "find videos about X", use this skill.
Zarr Python
Chunked N-D arrays for cloud storage (Zarr-Python 3). Compressed arrays, parallel I/O, S3/GCS via fsspec, NumPy/Dask/Xarray compatible, for large-scale scientific computing pipelines.
示例: "燕麦粥 1杯 + 鸡蛋 1个 + 牛奶 250ml"
**技能名称**: Food Database Query **技能类型**: 数据查询与分析 **创建日期**: 2026-01-06 **版本**: v1.0