Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Process multimodal inputs (images, video, audio, PDFs) with Gemini 3 Pro. Covers image understanding, video analysis, audio processing, document extraction, media resolution control, OCR, and token optimization. Use when analyzing images, processing video, transcribing audio, extracting PDF content, or working with multimodal data.
This skill should be used when viewing, previewing, or inspecting geospatial files from the command line. Covers interactive raster viewing (viewtif), interactive vector viewing (viewgeom), and non-interactive terminal-inline viewing (viewinline) for GeoTIFF, Shapefile, GeoJSON, GeoPackage, GeoParquet, CSV, HDF, NetCDF, and more.
GitHub repository analytics dashboard — stars, forks, contributors, issues, pull requests, recent activity, and top contributors. Use when the brief asks for a GitHub repo dashboard, open-source growth report, repository health page, or GitHub analytics view.
Spatial and spatiotemporal regression with GNNWR (Geographically Neural Network Weighted Regression). Use when the agent needs to: (1) Build spatially varying coefficient regression models, (2) Analyze geographic non-stationarity in spatial data, (3) Generate spatial coefficient maps for publication, (4) Run spatiotemporal regression with GTNNWR, (5) Scale geographically weighted regression to large datasets (N > 10k) with KNN mode, (6) Diagnose spatial model performance with F-tests, AIC, and residual maps.
Strategic analysis of Google Search Console data for startup founders and marketing leaders. Transforms GSC exports into actionable growth insights with revenue impact estimates, competitive positioning, and prioritized action plans. Use when a user provides a GSC zip/CSV for (1) Brand vs non-brand analysis with revenue implications, (2) SEO opportunities with business impact sizing, (3) Content gap analysis with funnel mapping, (4) Paid search strategy with budget allocation, or (5) Strategic summaries with prioritized recommendations.
REQUIRED when the user names a website and wants data from it, such as prices on allbirds.com, flights on kayak, or listings from zillow, or wants to add a new site to the Hermai registry. Supports self execution from open source schemas and hosted execution through Hermai Cloud. Covers discovery, session capture, schema authoring, push, and production fetch checks. SKIP when the task has no specific website or the user explicitly wants raw HTML of a one time page.
Retrieve Chinese market financial data and investment research information, covering 200+ interfaces for A-shares, Hong Kong stocks, funds, indices, financials, announcements, research reports, and macroeconomics. Use when: the user wants to check stock trends, fund NAV, index quotes, financial statements, valuation metrics, announcements and research reports, institutional views, macro data, sector themes, industry chains, or market statistics, or wants to pull, export, or compare structured financial data. Do not use when: the user wants direct buy/sell advice, automatic order placement, trade execution, non-financial data queries, system operations troubleshooting, or asks for fabricated conclusions when no data is available.
Kusto Query Language authoring, debugging, optimization, translation, and tooling for Azure Monitor, Sentinel, ADX, and Application Insights. USE WHEN user mentions 'KQL', 'Kusto', 'Log Analytics query', 'Sentinel query', 'hunting query', 'ADX query', 'Application Insights query', 'translate SQL to KQL', 'Splunk to KQL', 'optimize query', 'KQL performance', '.kql file', 'detection rule', 'analytics rule', 'threat hunting', 'Azure monitor query', 'log query', 'summarize operator', 'where TimeGenerated', OR any request involving querying Azure log/telemetry data. Even if the user doesn't say "KQL" explicitly — if they're asking about querying Azure logs, security events, or telemetry data, this skill applies.
Landscape evolution and surface process modelling in Python. Build 2D numerical models for erosion, hydrology, soil transport, and geomorphology. Use when the agent needs to: (1) Model landscape evolution over time, (2) Simulate river/stream erosion, (3) Route water flow across terrain, (4) Model hillslope diffusion processes, (5) Simulate weathering and soil production, (6) Analyze drainage networks, (7) Combine multiple geomorphic processes, (8) Load/save DEM data for modeling.
Light research integrity and ethics lifecycle always-on red-line gate: at research triage, approval, collection, change, analysis, submission, release, and post-publication, check risks including academic misconduct, data fabrication, statistical consistency, exaggerated conclusions, hallucinated or retracted citations, self-plagiarism, privacy, copyright, authorship and AI disclosure, software copyright and patent ownership, and paper-mill rewriting, turning "don't fabricate, don't exaggerate" from verbal advice into a machine-checkable, blockable, machine-readable gate aggregateable by the master run_checkpoint (produces light.findings.v1, Critical fail → exit 1). When to use: before submission or camera-ready, before releasing data or code, before filing software copyright, and when designing human-subjects or animal experiments — these are hard gates; plus background integrity scanning for any writing, analysis, or citation task. Trigger words: ethics / integrity / academic misconduct / fabrication / p-hacking / exaggeration / SOTA / retraction / plagiarism check / copying / privacy / IRB / informed consent / authorship / AI disclosure / paper mill / software copyright ownership. Core discipline: signal is not a verdict, and AI cannot self-assess → always "machine gate + human review"; when nothing is found, write "pending verification/UNRESOLVED", never fabricate; verify online throughout, zero local knowledge base, zero paid keys.
Build evidence-traceable market research reports and assumption-driven market sizing or forecast scenarios. Use for market definition, industry and customer evidence, competitive landscapes, TAM/SAM/SOM reconciliation, forecast sensitivity, and auditable report scaffolds.
Loads a fitted Meridian model and runs budget optimization scenarios. Use when the user wants to load a saved model and find the optimal budget allocation or target ROI spending. Don't use for visualizing model performance (use meridian-result-visualization) or building/fitting the model (use meridian-model-building).
Generates Scenario Planner data from a fitted Meridian model and exports it for Looker Studio dashboard creation via Colab handoff. Use when the user wants to generate scenario planning data, budget grids, or Looker Studio dashboards from a saved model. Don't use for visualizing model results (use meridian-result-visualization) or running standard budget optimization (use meridian-budget-optimization).
Build reusable product-usage and engagement models — retention, stickiness, and lifecycle — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to model, define, or compute whether users come back (retention / churn), how frequently they engage (stickiness / power users / DAU-WAU-MAU ratio), or the composition of the active base (new / returning / resurrecting / dormant lifecycle). These three are one engagement family sharing a start-event/return-event vocabulary and an interval granularity; this skill treats them together and helps pick the right lens: retention for the return-rate cohort matrix, stickiness for the frequency distribution, lifecycle for growth quality. On PostHog, model them in HogQL (mirroring query-retention / query-stickiness / query-lifecycle); in dbt, build fct_retention / fct_stickiness / fct_lifecycle marts with tests. Read modeling-warehouse-foundations first; feeds the retention validation used by modeling-activation-metrics.
Shared foundations for building reusable data models in PostHog, on either of two stacks: PostHog-native data-warehouse views / materialized views (HogQL, via the view-* MCP tools), or an external dbt project (sources.yml + staging/marts + schema tests) run against your own or PostHog's managed warehouse. Read before authoring any specific business model — covers the PostHog-vs-dbt decision, the view-create → view-materialize → sync_frequency workflow and the HogQL column-aliasing rule, the dbt project skeleton and the honest "no native dbt integration" picture, warehouse joins and star-schema dimensions, currency conversion with convertCurrency(), and checking/registering models in the data catalog for reuse. Companion to the domain skills modeling-revenue-metrics, modeling-conversion-metrics, modeling-activation-metrics, modeling-product-usage-metrics, and modeling-dimension-tables. Use when the user asks how to build a view, materialized view, or dbt model in PostHog, or which of the two stacks to use.
Full-featured Microsoft Office support. Use when Claude needs to: (1) work with Excel spreadsheets (.xlsx) — formulas, formatting, data analysis; (2) create/edit PowerPoint presentations (.pptx); (3) work with PDF documents (.pdf) — extraction, merging, form filling; (4) work with Word documents (.docx) — editing, revision tracking, comments.
Performance profiling — measures code execution time, DB call time, and identifies bottlenecks at both the application and database layer. Use when asked to "profile performance", "measure execution time", "find bottlenecks", "check response times", or "why is this slow".
Generate realistic KPI benchmarks for an influencer campaign before launch based on industry, platform, creator tier, and budget. This skill should be used when setting performance expectations for a creator campaign, estimating reach engagement and conversion benchmarks before launch, building KPI targets for an influencer program, forecasting campaign performance by creator tier and platform, setting EMV and ROAS targets for a campaign brief, defining what good looks like for an upcoming creator activation, calibrating expectations for a gifting or paid campaign across Instagram TikTok or YouTube, or creating a benchmark framework to measure campaign success against. For calculating ROI after a campaign ends, see campaign-roi-calculator. For calculating engagement rates from actual post data, see engagement-rate-calculator-benchmarker. For building a full KPI framework tied to business objectives, see campaign-goal-to-kpi-framework-builder.
Identifies and fixes Rails performance issues including N+1 queries, slow queries, and memory problems. Use when optimizing queries, fixing N+1 issues, improving response times, or when user mentions performance, slow, optimization, or Bullet gem. WHEN NOT: Caching-specific patterns (use caching-strategies), adding new features, or general code quality improvements unrelated to speed.
Score each creator on a completed campaign across consistency, content quality, engagement rate, and brand alignment, then produce a ranked retention list for future campaigns. This skill should be used when grading creators after a campaign ends, evaluating influencer performance post-campaign, ranking creators by campaign performance, building a retention list of top creators, deciding which creators to rebook for the next campaign, scoring influencer deliverables after a launch, comparing creator performance across a campaign roster, auditing which creators delivered the most value, or tiering creators into re-engage versus one-and-done lists. For calculating engagement rates and benchmarking them by tier, see engagement-rate-calculator-benchmarker. For scoring niche fit before a campaign, see niche-fit-scorer. For building the full campaign report with ROI narrative, see campaign-roi-calculator-narrative-builder.
Auto-document Power BI semantic models by extracting metadata, generating documentation, and cataloging all model objects using pbi-cli. Invoke this skill whenever the user says "document this model", "what's in this model", "list everything", "data dictionary", "model inventory", "audit contents", "catalog", "describe the model", or wants to understand what objects exist in a semantic model.
Apply, inspect, and compare Power BI report themes and conditional formatting rules using pbi-cli. Invoke this skill whenever the user mentions "theme", "colours", "colors", "branding", "dark mode", "corporate theme", "styling", "conditional formatting", "colour scale", "gradient", "data bars", "background colour", "formatting rules", "visual formatting", or wants to change the overall look-and-feel of a report or apply data-driven formatting to specific visuals.
Sync your Beehiiv audience to a local database and answer growth questions offline in one command. Trigger phrases: `check my beehiiv growth`, `subscriber sources`, `which send time works best`, `compare my publications`, `lookup subscriber email`, `use beehiiv`, `run beehiiv`.
Linear operators for large-scale inverse problems with matrix-free representations. Use when the agent needs to: (1) Define linear operators for forward/adjoint operations, (2) Solve inverse problems (deconvolution, imaging, tomography), (3) Apply signal processing transforms (FFT, convolution, derivatives), (4) Compose operators for complex workflows, (5) Perform regularized inversion with smoothness or sparsity constraints, (6) Process seismic or image data at scale.
Blockchain RPC and data access via Quicknode. Use when an agent needs to read onchain data (balances, token prices, transaction status, gas estimates, block data) across Base, Ethereum, Polygon, Solana, or Unichain. Supports both API key access and x402 wallet-based pay-per-request access with no account needed. Triggers on mentions of RPC, blockchain data, onchain queries, token balances, gas estimation, block number, transaction receipt, Quicknode, or x402.
Read-only R code review protocol for `.R` scripts. Checks code quality, reproducibility, domain correctness, tidyverse idioms, and professional standards; produces a report without editing. Use when user says "review this R script", "check the R code", "audit the analysis code", "code review on the R", or when an R file is touched as part of a paper submission. NOT for running the code — pair with `/audit-reproducibility` for numeric verification.
Email engagement tracking for sales — open tracking, click tracking, attachment views, real-time notifications, follow-up timing, and engagement analytics. Use when you can't tell if prospects are opening emails, open data looks inflated or unreliable (Apple MPP, pixel blocking), you don't know when to follow up based on engagement, tracking isn't set up yet and you need to pick a tool, or click/attachment tracking isn't working as expected. For Yesware-specific help, use /sales-yesware. Do NOT use for email deliverability (use /sales-deliverability), cadence design (use /sales-cadence), buying intent signals beyond email (use /sales-intent), SendGrid-specific config (use /sales-sendgrid), Postmark-specific config (use /sales-postmark), Customer.io-specific config (use /sales-customerio), Mailgun-specific config (use /sales-mailgun), Klaviyo-specific config (use /sales-klaviyo), or ActiveCampaign-specific config (use /sales-activecampaign).
Machine learning in Python with scikit-learn. Use for supervised learning (classification, regression), unsupervised learning (clustering, dimensionality reduction), model evaluation, hyperparameter tuning, preprocessing, or building ML pipelines. Provides comprehensive reference documentation for algorithms, preprocessing techniques, pipelines, and best practices.
Populates and maintains a project's data catalog (semantic layer): canonical metrics, trust marks (certifications) on warehouse tables/views, and reviewed table relationships. Use when asked to set up / seed / bootstrap the data catalog or semantic layer, to catalog a project's metrics, to certify or deprecate data sources, to propose or review table joins, or to work through the proposal review queue. To *use* an existing catalog to answer a business-number question, see querying-posthog-data instead. Trigger terms: data catalog, semantic layer, canonical metric, certify table, deprecate source, relationship proposal, metric drift, review queue.
Parse raw text from an Instagram or TikTok Story insights screenshot and format it into a clean, spreadsheet-ready row with labeled fields. This skill should be used when parsing Story metrics from a screenshot, formatting Story insights for a spreadsheet, extracting metrics from a pasted Story screenshot, cleaning up Story analytics data, converting Story insights text into structured data, turning a Story performance screenshot into a row for the tracker, logging Story metrics into a spreadsheet, normalizing Story screenshot data, pulling numbers from a Story insights paste, organizing Story metrics from creator screenshots, processing a batch of Story screenshots into rows, building a Story metrics tracker from screenshots, or entering Story data from a screenshot into a sheet. For normalizing metrics from multiple sources into a unified table, see metrics-normalization-formatter. For calculating engagement rates and comparing to benchmarks, see engagement-rate-calculator-benchmarker.
Ingest all sustainability journal RSS entries into a dedicated RSS SQLite database first, keyed by DOI, then mark relevance and prune non-relevant rows to DOI-only. Use when building a DOI-first ingestion pipeline with mandatory full ingestion before topic filtering.
Implements the Syncfusion Grouping Engine for data grouping, sorting, filtering, and summarization in Windows Forms applications. This skill provides comprehensive data manipulation capabilities for managing and displaying tabular data from IList sources. Use when working with Syncfusion.Grouping namespace, Engine class, TableDescriptor, or advanced data organization features in Windows Forms.
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.