Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Run end-to-end product experiments from assumption to decision: translate assumptions into testable hypotheses and experiment briefs, select the right method among qualitative interviews, prototypes, concierge tests, fake doors, feature flags, and A/B tests, and produce readouts that update the roadmap and decision record. Do not use when a qualitative or prototype test is the clearly right answer without statistical measurement; do not prescribe A/B testing by default; do not treat statistical significance as the only decision criterion or hide ethical and guardrail considerations.
Query, search, and download public datasets and civic information for the City of Raleigh. Use for live ArcGIS Hub catalog discovery, ArcGIS FeatureServer and MapServer queries, ImageServer imagery exports, official Raleigh geocoding, GoRaleigh transit feeds, guest-public development records, public RaleighNC.gov content, eSCRIBE public meetings, Raleigh fire reports and inspections, and the Raleigh-Wake ECC active incident feed. Do not use for private data, authenticated operations, payments, submissions, bulk crawling, or non-public portals.
Diagnoses and resolves PostHog ingestion warnings — problems recorded while ingesting events (dropped events, rejected person merges, oversized payloads, invalid data). Use when a user asks why events are missing, dropped, or undercounted, why identify/alias calls don't work or accounts stay duplicated, why person or group properties aren't updating or profiles look inflated, why recordings have gaps, heatmaps are empty, LLM token counts are missing, why cookieless events vanish, or whenever the `ingestion_warning` health check fires. Explains severity triage (error = dropped, warning = modified, info = intentional) and routes all warning types — size limits and enrichment, merges and distinct IDs, high-volume distinct IDs, `$process_person_profile`, timestamps, cookieless, heatmaps, transformations, session replay — to per-issue reference files with code-level causes and per-SDK fixes.
Perform RFM (Recency, Frequency, Monetary) customer segmentation analysis on e-commerce data. Use when you need to analyze customer value, identify VIP customers, or create marketing segments. Automatically cleans data, calculates RFM metrics, applies K-means clustering, and generates visualization reports with Chinese language support.
Comprehensive SaaS architecture planner for Next.js + Supabase applications. Converts ideas into production-ready technical plans with database schemas, file structures, feature breakdowns, and week-by-week development roadmaps. Use when planning subscription-based applications, multi-tenant SaaS products, or building from idea to launch.
Use when a Roblox game saves or loads player data, or when players report data not saving, lost progress, rollbacks, duplicated items or a purchase granted twice. Triggers: DataStoreService, UpdateAsync, SetAsync, BindToClose, ProfileStore, ProfileService, DataStore2, session locking, data schema or migration, Developer Product ProcessReceipt, player trading, OrderedDataStore leaderboards, MemoryStore, MessagingService, TeleportService and reserved servers, DataStore budgets and throttling (errors 301 to 306), 'You must publish this place to the web to access DataStore', and testing data code in an unpublished place.
Use when the user asks to "design an experiment", "build a predictive model", "run A/B test analysis", "perform causal inference", "engineer features", "evaluate model performance", "set up MLOps pipeline", "analyze time series", "calculate sample size", or "deploy a model to production". Expert data science covering statistical modeling, experimentation, causal inference, feature engineering, ML deployment, and advanced analytics with Python, R, and SQL.
Use when deploying or operating SpacetimeDB on Maincloud or self-hosted infrastructure, configuring standalone services, rotating keys, viewing logs, filtering logs, or using PGWire. Triggers on: deploy, Maincloud, self-host, standalone, systemd, Nginx, key rotation, logging, spacetime logs, PGWire, psql.
SVG generation via DAX measures and extension measures with ImageUrl data category for inline visualizations in PBIR reports, including ready templates for matrix and table cells, new card images and per-button images on the new button slicer. Automatically invoke when the user mentions "SVG visual", "DAX sparkline", "SVG measure", "inline graphics with DAX", "ImageUrl data category", "extension measure", or asks to create any DAX-generated chart (progress bars, bullet charts, KPI indicators, data bars, gauges, donut charts, lollipop charts, dumbbell charts, status pills, overlapping bars, boxplots, IBCS bars, jitter plots, box-and-whisker charts).
Best practices for integrating Terra API – the unified health & fitness data API for 500+ wearables (Garmin, Fitbit, Oura, Whoop, Apple Health, Strava, Dexcom). Use when building with Terra API or tryterra.co, handling terra-signature (X-Terra-Signature) webhooks, storing wearable health data (activity, sleep, daily, body, nutrition, menstruation, hormone), managing device connections, or merging data across multiple devices.
TQX (tqx.trade) HK/US stock quant: factor analysis, strategy backtests, and agent-driven trading (paper or live) via the TQX CLIs. Use when the user wants to run factor IC/IR analysis, backtest a Python trading strategy on Hong Kong or US stocks, or set up agent-automated trading on a paper or live account (e.g. "backtest a moving-average strategy on AAPL", "analyze a momentum factor on HK stocks", "let the agent trade my TQX account", "join the TQX trading competition").
Convert uncertain real-world choices into an auditable Bayesian evidence-to-action report with priors, evidence grading, posterior update, action thresholds, sensitivity checks, multi-turn decision logs, and Markdown plus bilingual HTML output. Do not use for Bayes theorem tutoring, homework, generic brainstorming with no report, or final licensed medical, legal, or financial advice.
Evaluate startup runway, burn, revenue, and profitability trajectory using the Default Alive / Default Dead framework. Do not use this skill for weekly growth experiments or operating growth decisions; use `yc-weekly-growth-compass` for those decisions.
A/B test design and experiment planning for paid advertising. Structured hypothesis framework, statistical significance calculator, test duration estimator, sample size calculator, and platform-specific experiment setup guides (Meta Experiments, Google Experiments, LinkedIn A/B). Use when user says A/B test, split test, experiment design, test hypothesis, statistical significance, sample size, or test duration.
Analyzes spatial transcriptomics with squidpy (1.8.x) on AnnData and SpatialData objects, routing platforms correctly: Visium spots use spatial_neighbors(coord_type='grid') and pair with deconvolution, while Xenium/MERFISH single-cell data use coord_type='generic'/Delaunay neighbors and spatialdata-io readers (xenium, visium_hd, merscope). Runs sq.gr.spatial_neighbors, nhood_enrichment, co_occurrence, spatial_autocorr (Moran's I for spatially variable genes), ripley, and ligrec. Use when the user wants spatial transcriptomics, squidpy, Visium/Xenium/MERFISH analysis, neighborhood enrichment, co-occurrence, or spatially variable genes; QC/clustering uses alterlab-scanpy and spot deconvolution (destVI/Tangram) uses alterlab-scvi-tools. Part of the AlterLab Academic Skills suite.
Score and enrich a CSV of B2B leads using Apify Actors. Takes a CSV with company URLs, free-text scoring rules, and an enrichment preference; runs BuiltWith (tech stack), Website Content Crawler (content classification), and Contact Info Scraper (company metadata) for scoring; enriches with either department-specific contacts (Contact Info Scraper + Bulk Email Finder fallback) or copywriter discovery (Google Search Scraper → AI Web Scraper → Bulk Email Finder). Outputs an enriched CSV with a numeric score and a per-lead outreach_hook column that personalizes cold email copy (e.g. "uses Shopify → send Shopify install guide"). Use when user asks to score leads, qualify leads, enrich a lead list, detect a company's tech stack for outreach, find marketing/sales/engineering contacts at a list of companies, hunt down blog copywriters for guest-post pitches, personalize cold email at scale, or turn a raw domain list into a ready-to-pitch account list.
Enforce the replication-protocol.md rule by cross-checking numeric claims in a manuscript against the actual R / Stata / Python outputs. Report PASS/FAIL per claim against tolerance thresholds. Use before submission and before releasing a replication package.
Populates the local Azure SQL Database container's database (appdb) with realistic sample/test data so a developer has something to build against. Use when the user says "seed the database", "add test data", "populate the dev database", "generate sample data", "fake data", "load fixtures", "insert test rows", "write a seed script", or "bulk load a CSV". This is the Azure SQL engine (EngineEdition 5), not the mssql/server SQL Server image. Distinct from azuresql-db-scaffold (which does a single seed.sql step while bootstrapping an app) and azuresql-db-import (which loads a .bacpac). Reach for this whenever an existing appdb needs volume, fixtures, or believable rows.
Writes integration tests that run IN CODE against a real Azure SQL Database container, spun up per test or per suite with Testcontainers and torn down after. Use when the user asks for "integration tests against SQL", "Testcontainers", "spin up a database for tests", "an ephemeral test database", "a test database per test", "xUnit/Jest/pytest with a real database", or "a database fixture". Use this INSTEAD of the Testcontainers MsSql preset (mcr.microsoft.com/mssql/server), because this is the Azure SQL engine (EngineEdition 5). For wiring the engine into a CI pipeline via service containers or workflow YAML instead, use azuresql-db-ci.
Fetch and analyze WeChat Official Account hot articles / 公众号爆款文章 by sector or keywords. Use when the user asks for 爆款文章分析, 赛道爆款, 公众号爆款数据, reading counts, likes, shares, comments, title patterns, writing style, 爆款原因分析, or writing references for content creation.
How to use BGPT MCP to search scientific papers and retrieve structured experimental data including methods, results, sample sizes, conflicts of interest, limitations, reproducibility scores, and falsifiability criteria. Use this skill when the user asks to find scientific evidence, search the literature, evaluate research quality, check reproducibility, surface study limitations or conflicts of interest, retrieve raw experimental data, or build evidence-grounded AI workflows. Also trigger when the user references PubMed, arXiv, biorxiv, medrxiv, systematic reviews, evidence-based medicine, GRADE, or critical appraisal.
Use bigquery CLI (instead of `bq`) for all Google BigQuery and GCP data warehouse operations including SQL query execution, data ingestion (streaming insert, bulk load, JSONL/CSV/Parquet), data extraction/export, dataset/table management, cost estimation with dry-run, authentication with gcloud, data pipelines, ETL workflows, and MCP server integration for AI-assisted querying. Modern TypeScript/Bun implementation replacing the Python `bq` CLI with instant startup (~10ms vs ~500ms), automatic cost awareness with confirmation prompts, and native streaming support (JSONL). Handles both small-scale streaming inserts (<1000 rows) and large-scale bulk loading (>10MB files) from Cloud Storage.
Pre-write quality gate for content entering the brain. No raw copies: a bare cp/mv into the brain repo is a bug. Before any new page lands, resolve named entities registry-first (a vector score is a floor for prose, never a gate for named things), then run the read-the-top-hit dedup decision tree (clear-dup / plausible-dup / clear). Owns dedup; delegates enrichment to the shipped ingestion skills. Routing convention, not an operation-boundary enforcement
Author, edit, publish, and validate CARTO Builder maps. Use when the user wants to create a map from a natural-language request, edit an existing map (datasets, layers, styling, privacy, popups, widgets, SQL parameters), duplicate one, upload custom marker icons, or wire up an AI agent on a map. Routes to the CARTO MCP server's map tools (`create_map`, `update_map`, `validate_map`, `read_maps`, `view_map`) when attached, and to the `carto maps` CLI — `create`, `update`, `delete`, `publish`, `validate`, `schema`, `agents`, `screenshot`, `copy`, `datasets update` — for scripted/bulk authoring, cross-org copy, screenshots, or when the server isn't attached.
Change analysis, once the observations are comparable. Not for cases whose blocker is comparability itself: mixed sensors, product levels or processing baselines to remote-sensing-analysis, undocumented vertical datums to point-cloud-lidar, multi-decade archive trends over large areas to google-earth-engine. Matching product level does not prove comparability. Otherwise invoke for what, where or how much changed: two-scene comparison, deforestation, urban growth, disaster damage, parcel-change audits, bi-temporal differencing, post-classification comparison, adjusted area, break detection in a series in hand (BFAST/LandTrendr/CCDC). Seasonal mismatch is this skill's own confounder; a documented datum with a stated accuracy budget is settled comparability. Keep both.
Chart and data visualization libraries. Recharts, Chart.js, D3.js, Victory, Nivo, ECharts. Common chart types, responsive design, and real-time updates. USE WHEN: user mentions "chart", "graph", "data visualization", "Recharts", "Chart.js", "D3", "ECharts", "Victory", "bar chart", "line chart", "dashboard" DO NOT USE FOR: PDF report generation - use `pdf-generation`; data export - use `data-export`.
Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis
Discover all URLs on a website without fetching content — fast, low-cost URL inventory via sitemap.xml + link extraction BFS. Use when you need to know which pages exist before deciding what to scrape or crawl: "list all pages", "find URLs on this site", "discover links", "what pages does this site have", "map the site". Step 3 of the crw workflow ladder.
Parse a local or remote FILE (PDF) into markdown or structured JSON with fastCRW. Use when the source is a file on disk — "parse this PDF", "extract text from this document", "read this report", "convert PDF to markdown". Routing rule: URL → use crw-scrape; file on disk → use crw-parse. Step 5 of the crw workflow ladder.
Design, build, evaluate, govern, monitor, evolve, and retire digital twins and federated twin universes for software systems, engineering processes, agentic software factories, infrastructure, and cyber-physical operations. Use when a task involves digital-twin architecture, digital thread, simulation, predictive maintenance, twin health, agent authority, or dark-factory design. Do not use for ordinary observability dashboards, static dependency graphs, generic AI governance, or operating one named infrastructure tool without a twin-specific representation and feedback loop.
Diagnose and improve slow Django database-backed endpoints with evidence-first profiling, query-plan review, index selection, ORM loading fixes, batching, database-side computation, materialized views, and pagination choices. Use when a Django view, API, job, report, queryset, or database query is slow and the right optimization path is not obvious.
Process large Django querysets and write-heavy jobs with memory-safe reads, values/values_list, iterator chunking, set-based update/delete, bulk_create, bulk_update, F expressions, Func expressions, and batch sizing. Use when a Django command, task, migration, report, or loop reads or writes many rows and is slow, memory-heavy, or query-heavy.
Calculate engagement rates for creator posts and benchmark them against platform and tier averages. This skill should be used when calculating an influencer's engagement rate, benchmarking creator engagement against industry averages, evaluating whether a creator's engagement is above or below average for their tier, comparing engagement rates across platforms, checking if engagement rates suggest fake followers, auditing a creator's engagement quality before a partnership, analyzing engagement by content type (reels, stories, feed posts, TikTok videos), or assessing engagement trends across a creator's recent posts. For estimating fair market rates based on engagement, see creator-rate-estimator. For full creator vetting beyond engagement, see creator-vetting-scorecard. For scoring niche fit, see niche-fit-scorer.
Identify, measure, and exclude bot / crawler / AI-agent traffic in PostHog web and product analytics using the traffic classification surface (the isLikelyBot / getTrafficType HogQL functions and the $virt_* virtual properties). Use when the user asks to "exclude bots", "filter out crawlers", "remove bot traffic from my numbers", "how much of my traffic is bots / AI crawlers", "is GPTBot / ChatGPT / Claude hitting my site", "break down traffic by human vs bot", or wants clean human-only counts in an insight or dashboard. For the real-time Live tab bot tiles, use exploring-live-traffic instead.
When the user wants to perform a deep dive into a company's financial performance. Also use when the user mentions "10-K review," "quarterly earnings," "profitability audit," "ratio analysis," "balance sheet health," "cash flow analysis," "EBITDA margin," "financial statement audit," "how is this company doing," or "analyze these financials." Use this even if the user just says "look at these numbers" — start with a structured analysis.
Expert in Freshdesk helpdesk API for building integrations, extracting support data, managing tickets/contacts/companies, and automating support workflows. Use when working with Freshdesk, building helpdesk integrations, analyzing support ticket data, or creating customer support applications.
Invoke before recommending, training, or auditing a neural method for geospatial imagery, including vision transformers, U-Net/DeepLab/SegFormer, object detection, pixel classification, building/road extraction, and EO foundation-model fine-tuning. Also invoke for neural chip-split validity, IoU/accuracy claims, augmentation, imbalanced losses, spatial validation, or sliding-window inference. Use remote-sensing-analysis for non-neural methods and change-detection when temporal change is the deliverable.
Route genuinely ambiguous or multi-stage geospatial work across specialist skills while enforcing shared CRS, validity, leakage, units, verification, and reproducibility rules. Use for requests spanning multiple stages such as acquisition, imagery, modeling, analysis, and map delivery, or for an explicit end-to-end pipeline. Never invoke for one domain merely because a parameter is unclear. Code implementation/review, backend or platform choice, and production-readiness review are direct specialist tasks. Do not add this skill as a layer around one specialist.
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.