Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Creates an EF Core entity + runs the migration that creates its table in Postgres. CRUD drill Day 1 step 5. Trigger: 'day1 step5', 'create entity/table for up-api'. Use the entity name and columns exactly as user specifies — do not suggest or add columns.
Use when asked to turn a raw company list into a scored, evidenced prospect list — grade a base the client already has, enrich it from public sources, attach dated buying signals with proof, and output a ready-to-send file. Triggers include "run the list", "score these companies", "build the prospect list", "who do we write to first", "enrich this base".
Databricks Expert Engineer Skill - Comprehensive guide for data engineering, machine learning infrastructure, and permission design Use when: - Running databricks CLI commands (auth, api) - Executing SQL queries via Databricks SQL Warehouse - Working with Unity Catalog permissions - Managing Lakeflow Jobs or Delta Lake
Work with Data Commons, a platform providing programmatic access to public statistical data from global sources. Use this skill when working with demographic data, economic indicators, health statistics, environmental data, or any public datasets available through Data Commons. Applicable for querying population statistics, GDP figures, unemployment rates, disease prevalence, geographic entity resolution, and exploring relationships between statistical entities.
Use this skill to build, fix, or publish a standalone HTML page or report in DataLens. DataLens takes a whole self-contained HTML document — often an AI-generated report with tables, charts, and a CSV/download button — and renders it in a sandboxed, CSP-locked iframe, so normal web code silently breaks. Reach for it when generating such a page from scratch, and when one already in DataLens misbehaves: images, fonts, scripts, or CDN libraries blocked or throwing Content-Security-Policy errors; fetch/XHR/localStorage failing; charts blank; a download or Export button doing nothing; an upload rejected as too large or the wrong encoding; or the page needing to match the user's DataLens theme (light/dark) and language (ru/en); or embedding a Yandex map. Also covers which CDNs and hosts are allowed and making the page fully self-contained. Not for DataLens chart cells or HTML-markup table columns.
Pythonic wrapper around RDKit with simplified interface and sensible defaults. Preferred for standard drug discovery: SMILES parsing, standardization, descriptors, fingerprints, clustering, 3D conformers, parallel processing. Returns native rdkit.Chem.Mol objects. For advanced control or custom parameters, use rdkit directly.
Design and audit product experiments, A/B tests, feature rollouts, pricing tests, onboarding tests, lifecycle experiments, holdouts, guardrail metrics, sample plans, decision rules, and learning reviews. Use when testing product, UI, growth, monetization, retention, marketplace, or live-ops changes and the agent must avoid false confidence or harmful experiments.
Plan and audit mobile or PC game soft launches, test markets, cohort gates, economy balance, IAP, ads, retention, FTUE, live events, store listing tests, crash/performance health, community feedback, and scale/kill decisions. Use when preparing a game before global launch or evaluating whether to expand, iterate, or stop.
Google Ads campaign performance analysis using GAQL (Google Ads Query Language). Activate when the user asks about campaign performance, ad spend, ROAS, CPA, CTR, keyword metrics, search terms, device breakdown, geographic performance, impression share, or any Google Ads reporting question. Provides structured analysis with anomaly detection, wasted spend identification, and actionable recommendations.
Apply meta-analysis to synthesize effect sizes across multiple studies, assess heterogeneity, and evaluate publication bias. Use this skill when the user needs to combine findings from prior research, compare fixed-effect vs random-effects models, compute pooled effect sizes, or when they ask 'what does the overall evidence say', 'how do I combine results across studies', or 'is there publication bias'.
Provides the HuggingFace Tokenizers library (Rust core with Python and Node.js bindings) for training and using BPE, WordPiece, and Unigram tokenizers. Covers the pipeline of normalizers, pre-tokenizers, models, post-processors and decoders, padding and truncation, batch encoding, alignment tracking, and conversion to transformers PreTrainedTokenizerFast. Use when training a custom tokenizer or vocabulary on a new corpus, tokenizing large text corpora quickly, mapping tokens back to character offsets for NER or question answering, or configuring normalization and special tokens. Use when wrapping a custom tokenizer for transformers. For SentencePiece models or tiktoken, use those tools instead; for loading a pretrained tokenizer only, AutoTokenizer is enough.
Extracts structured, validated data from LLM responses using the Instructor Python library with Pydantic response models, including nested models, enums, custom validators, automatic retries with validation error feedback, and streaming of partial objects or iterables. Works with Anthropic, OpenAI, and local Ollama models. Use when pulling typed fields or entities out of free text, when classifying text into fixed categories, when an LLM must return JSON that passes schema validation, when failed extractions need automatic retry, or when streaming partial structured results. Not for prompt optimization (use DSPy) or building multi-step chains (use LangChain).
Multimodal knowledge pipeline skill — ingest documents (PDF/image/video/Office) into a persistent knowledge wiki, supporting knowledge fusion, cross-source contradiction detection, multi-source aggregate queries, and knowledge graph construction. Trigger this skill when the user mentions ingesting documents, building a knowledge base, querying the wiki, checking consistency, building a knowledge graph, document analysis, multimodal understanding, data pipelines, and similar needs. Even if the user does not explicitly say pipeline or knowledge-pipline, this skill should trigger whenever the task involves turning documents into structured knowledge, cross-document analysis and comparison, or knowledge graph visualization.
This skill should be used when completing LBO (Leveraged Buyout) model templates in Excel for private equity transactions, deal materials, or investment committee presentations. The skill fills in formulas, validates calculations, and ensures professional formatting standards that adapt to any template structure.
Manage local Airflow environment with Astro CLI. Use when the user wants to start, stop, or restart Airflow, view logs, troubleshoot containers, or fix environment issues. For project setup, see setting-up-astro-project.
Generate comprehensive market research reports (50+ pages) in the style of top consulting firms (McKinsey, BCG, Gartner). Features professional LaTeX formatting, extensive visual generation with scientific-schematics and generate-image, deep integration with research-lookup for data gathering, and multi-framework strategic analysis including Porter Five Forces, PESTLE, SWOT, TAM/SAM/SOM, and BCG Matrix.
Extract features from 1D signals using signalTimeFeatureExtractor, signalFrequencyFeatureExtractor, and signalTimeFrequencyFeatureExtractor. Use when computing time-domain features (amplitude, energy, shape factors), frequency-domain features (spectral location, power, bandwidth, PSD), or time-frequency features (spectral shape, instantaneous, ridges, wavelet, EMD-derived) on a per-frame basis. Use when the user asks to "extract features", "compute spectral features", "build a feature table for a classifier", "get per-frame statistics", "run feature extraction on this signal", or describes a vibration / biosignal / radar / sensor signal needing features for downstream ML or analysis. Includes optional GPU acceleration via canUseGPU and gpuArray. Does not cover filter design, audio-specific feature extraction (use audioFeatureExtractor in Audio Toolbox instead), batch dataset orchestration, or 2D / image features.
Low-level plotting library for full customization. Use when you need fine-grained control over every plot element, creating novel plot types, or integrating with specific scientific workflows. Export to PNG/PDF/SVG for publication. For quick statistical plots use seaborn; for interactive plots use plotly; for publication-ready multi-panel figures with journal styling, use scientific-visualization.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
Comprehensive biosignal processing toolkit for analyzing physiological data including ECG, EEG, EDA, RSP, PPG, EMG, and EOG signals. Use this skill when processing cardiovascular signals, brain activity, electrodermal responses, respiratory patterns, muscle activity, or eye movements. Applicable for heart rate variability analysis, event-related potentials, complexity measures, autonomic nervous system assessment, psychophysiology research, and multi-modal physiological signal integration.
Builds Databricks data products from live web data, end to end: discovers the right Nimble web-data agents, scrapes into Delta tables, and produces an AI/BI dashboard and/or a deployed Databricks App — a table → dashboard → app workflow, for production data products or quick demos. Use whenever a request pairs live or scraped web data WITH a Databricks destination — e.g. "scrape Amazon/Walmart prices into a Delta table and build a dashboard", "load Zillow/Instagram/Maps/search results into Databricks and build a dashboard or app", "showcase Nimble + Databricks to a prospect". Prefer it over nimble-web-expert or competitor-intel when the data lands in Databricks. Do NOT use for one-off web fetches or CSV exports with no Databricks destination — use nimble-web-expert instead. Do NOT use for competitor or company research briefings — use competitor-intel or company-deep-dive instead. Do NOT use for generic Databricks work with no Nimble/web-data angle — use the official databricks-* skills instead.
When the user wants to apply NLP to supply chain, extract information from documents, analyze supplier communications, classify items, or process unstructured text. Also use when the user mentions "natural language processing," "NLP," "text mining," "document extraction," "supplier sentiment analysis," "product classification from text," "BERT," "transformers for text," or "chatbots for supply chain." For general ML, see ml-supply-chain.
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linking related objects, enforcing constraints, planning multi-step actions as graph transformations, or when skills need to share state. Trigger on "remember", "what do I know about", "link X to Y", "show dependencies", entity CRUD, or cross-skill data access.
Use the `om` CLI for market data, alerts, scalar metrics and indicators, event-watch journals, research studies, runner/service control, and OpenMarket chart workspace actions. Always use `om` commands instead of calling exchange APIs directly.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.