Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Read and process ground-penetrating radar profiles using GPRPy. Use for sample-based dewow/background removal, auditable gain, time/depth scenarios, and radargram export with explicit acquisition units. SEG-Y input uses a separate segyio adapter; native GPRPy files are serialized sessions.
Observability visualization with Grafana and LGTM stack. Dashboard design, panel configuration, alerting, variables/templating, and data sources. USE WHEN: Creating Grafana dashboards, configuring panels and visualizations, writing LogQL/TraceQL queries, setting up Grafana data sources, configuring dashboard variables and templates, building Grafana alerts. DO NOT USE: For writing PromQL queries (use /prometheus), for alerting rule strategy (use /prometheus), for general observability architecture (use senior-software-engineer with infrastructure focus). TRIGGERS: grafana, dashboard, panel, visualization, logql, traceql, loki, tempo, mimir, data source, annotation, variable, template, row, stat, graph, table, heatmap, gauge, bar chart, pie chart, time series, logs panel, traces panel, LGTM stack.
Produce institutional-grade research reports and academic papers — industry reports, white papers, annual surveys, data insights, arXiv papers, and also 16:9 consulting deck-style reports (one conclusion per page). Define structure, write findings, build a chart and visual system. The standards are distilled from real-world testing of 2026 top-tier institutional reports. Not suitable for single articles or pure presentation PPTs (use design/slides instead).
Implement hybrid search combining vector and keyword retrieval for RAG systems. Use this skill when building RAG retrieval, combining semantic search with BM25, implementing reciprocal rank fusion (RRF), or optimizing retrieval accuracy. Activate when: vector search, keyword search, BM25, semantic search, hybrid RAG, retrieval optimization, search relevance, reranking.
Full lifecycle management of JeecgBoot Online forms (cgform) — automatically create/edit database tables and form configurations via API, supporting single tables, master-detail tables, tree tables, 26 control types, plus JS/Java/SQL enhancements, permission configuration, data CRUD, and Jimu report integration. Use this skill whenever the user's intent involves "Online forms", including but not limited to: creating or configuring database tables ("create a leave request table", "create an online table", "make a table with a dropdown", "low-code form", "online form", "configure a table"); modifying existing Online table fields ("add a field", "change a field type", "add a subtable", "delete a field"); configuring form enhancements ("JS enhancement", "custom button", "form linkage", "Java enhancement", "SQL enhancement"); configuring permissions ("field permission", "button permission", "data permission", "grant to role"); managing form data ("insert data", "query records", "export CSV", "generate test data"); and linking Jimu reports ("add a report to this table", "integrated printing"). Even if the user only describes business requirements without saying "online" (e.g. "build an employee information management feature with name, department dropdown, and hire date"), as long as it involves metadata-driven form configuration, this skill should be triggered. Note: do not confuse with the "designer form" (desform) — desform is a drag-and-drop form designer handled by the jeecg-desform skill; do not confuse with "Online report" (cgreport) or "Online chart" (onlchart) either — they are SQL-driven read-only displays.
Kaggle `kernel-metadata.json` setup and repair. PROACTIVELY activate for: (1) creating kernel-metadata.json, (2) fixing metadata validation errors, (3) setting `id`, `title`, `code_file`, language, or kernel type, (4) configuring private/public, internet, GPU, or accelerator behavior, (5) attaching dataset_sources, competition_sources, kernel_sources, or model_sources, (6) preparing metadata before `kaggle kernels push`, (7) converting script/notebook metadata. Provides: schema checklist, valid fields, source arrays, defaults, and push-readiness review.
Logseq Datascript schema, built-in properties/classes, and :db/ident discovery for composing or reviewing Datascript queries about blocks/pages/tags/properties/classes. Use whenever editing or reviewing Datascript pull selectors or queries, or any code that adds/removes attributes in pull patterns, or touches property namespaces/identifiers, or requires reasoning about property value shapes/ref/cardinality in Logseq.
Create, deploy, and operate Streamlit apps in PostHog via the streamlit-apps MCP tools — create an app, set its source, read and patch its code, start and stop its sandbox, poll status, list versions, delete, and share the app with humans via its PostHog URL. Use when asked to "create a streamlit app", "deploy a data app", "ship a dashboard app", "restart/stop my app", "why is my app not running", or "give me a link to the app".
Manual for the marginaleffects R and Python package, and guide to the book "Model to Meaning". Use when users ask about predictions, comparisons, slopes, marginal effects, average treatment effects (ATE/ATT/CATE), hypothesis testing, contrasts, counterfactuals, risk ratios, odds ratios, causal inference with G-computation, or need help with marginaleffects functions like predictions(), comparisons(), slopes(), hypotheses(), datagrid(), avg_predictions(), avg_comparisons(), avg_slopes(), or plot functions.
Volcengine Market Insight assistant. Helps users obtain public content data about brands across major social platforms and media channels, use AI to filter out the information truly worth attention, and discover potential business opportunity leads. Use this skill when the user mentions any of the following scenarios: wanting to know whether anyone online has recently discussed their brand or product, wanting to see what competitors have been doing recently on social media, wanting to understand the discussion heat and trends of a topic or event online, wanting to regularly obtain industry news and trending content related to their business, wanting to connect the filtered content data to their own system for further analysis, wanting to view which monitoring tasks exist under their account or fetch the data of a task, wanting to understand online discussion of hot topics such as the latest Middle East situation, tariffs, trade wars, and AI large models, wanting to query business opportunity lead information to obtain ACOR assessments, competitive analysis, and company profiles, or mentioning Volcengine Market Insight, Volcengine Insight, PullPost, ListCustomSubsTask, QueryClueInfo. Even if the user does not directly mention "market insight", as long as the need involves brand voice tracking, understanding industry trends, online discussion of hot events, obtaining public content data, or querying and analyzing business opportunities, this skill should be triggered.
End-to-end collaborative workflow for the CUMCM national contest, MCM/ICM contests, and the Dian Gong Cup mathematical modeling competitions. Use when a user explicitly works on one of these modeling contests or asks to run/review a modeling-competition paper from problem selection through modeling, solving, robustness, writing, compliance, and final submission review. Provides 10 stages, persistent decision state, competition-specific rules/templates, deterministic scoring helpers, numbered decisions, and Codex/Claude Code handoff. Do not trigger for generic model selection, ordinary data analysis, or non-competition paper review.
Reads data from relational databases using MATLAB Database Toolbox pushdown capabilities. Use when importing data from JDBC/ODBC databases, filtering rows, selecting columns, excluding duplicates, joining database tables, using sqlread, fetch, sqlinnerjoin, sqlouterjoin, databaseImportOptions, or rowfilter.
Guides users through building a Meridian Marketing Mix Modeling (MMM) model. Use when a user wants to load data, map columns, configure ModelSpec, run Exploratory Data Analysis (EDA), fit a model, and save the model. Don't use for visualizing results or creating a scenario planner.
Normalize messy creator campaign metrics from multiple sources into a single clean table with standardized field names ready to merge into your master tracker. This skill should be used when cleaning up influencer metrics, standardizing campaign data from multiple platforms, normalizing creator performance numbers, merging metrics from Instagram and TikTok and YouTube into one sheet, formatting messy analytics exports, preparing campaign data for a master spreadsheet, converting raw platform stats into a consistent format, combining metrics from different reporting tools, deduplicating creator data from multiple sources, fixing inconsistent column names across exports, or cleaning up a metrics dump before reporting. For calculating engagement rates, see engagement-rate-calculator-benchmarker. For full campaign reports, see campaign-roi-calculator. For parsing a single Story screenshot, see story-metrics-screenshot-parser.
Migrates existing Nango TypeScript createSync implementations from nango.lastSyncDate, legacy incremental syncType, and non-resumable full refreshes to checkpoint-based syncs. Use when updating customer Nango sync code to define checkpoint schemas, call getCheckpoint/saveCheckpoint/clearCheckpoint after every batchSave (including inside paginate loops), test dryruns with --checkpoint, and fix deletion handling for checkpointed incremental or full syncs.
Movement and trajectory analytics from GPS/GNSS tracks: cleaning, stop/trip detection, road-network map matching, speed/direction, flow aggregation, and origin-destination construction. Use for fleets, human mobility, animal tracking, AIS, or sports tracks. Trigger on GPS points, GPX, trajectories, stop detection, map matching, or timestamped positions per moving object. Also invoke for privacy, aggregation, de-identification, or release of individual trajectories. Use network-accessibility-analysis for hypothetical routes, isochrones, or static OD costs without observed tracks.
Read and validate magnetotelluric transfer functions with MTpy-v2. Use for EDI import, impedance uncertainty, apparent resistivity/phase, documented tensor rotations, response plots and preparation for modelling. External inversion solvers and raw time-series processing require separate tools and validation.
Governs Microsoft Fabric OneLake catalog health, protection, and trust through Fabric Admin, Core, and Power BI REST APIs. Use for tenant or owner-scoped audits and guarded remediation of domains, workspace assignment, capacity, labels, tags, descriptions, refresh, and item identity. Catalog item discovery belongs to search-consumption-cli.
Build, configure, deploy, and troubleshoot durable blockchain indexers with the Subsquid Pipes SDK (EVM, Solana, Tron, Bitcoin, Hyperliquid) when Portal MCP or curl previews are insufficient for backfills, recurring syncs, joins, app-owned data, or production analytics.
Reproduce any academic paper figure from an uploaded image using accumulated style experience. Use when: user uploads/attaches a paper figure and asks to reproduce or recreate it; user says "复现这个图", "reproduce this plot", "match this figure", "照着这个图画"; or user provides a paper figure PNG/screenshot and wants Python matplotlib code that generates it. Includes analysis workflow for font detection, color extraction, proportion matching, and mapping to 8 pre-built styles or creating a new style from scratch.
Blazingly fast DataFrame library written in Rust. Features a multi-threaded query engine, lazy evaluation, and efficient memory usage via Apache Arrow. Designed for high-performance data processing on a single machine. Use for large datasets (1GB-100GB+), fast data transformations, Parquet/CSV processing, complex query pipelines, memory-efficient operations, and when speed is critical (10-100x faster than pandas).
Troubleshoot Power BI model performance, trace query execution, manage caches, and verify the pbi-cli environment using pbi-cli. Invoke this skill whenever the user says "pbi not working", "setup issues", "connection failed", "slow query", "performance", "profiling", "tracing", "health check", "model audit", "pbi setup", or encounters any pbi-cli error. This is the first skill to check when something goes wrong with pbi-cli.
Create and manage Power BI semantic model structure using pbi-cli -- tables, columns, measures, relationships, hierarchies, calculation groups, and date/calendar tables. Invoke this skill whenever the user says "create table", "add measure", "add column", "create relationship", "date table", "calendar table", "star schema", "mark as date table", "add hierarchy", "calculation group", or any model-building task. Also invoke when creating multiple measures at once -- the skill contains critical guidance on multi-line DAX expression handling.
Analyzes a Qlik app via MCP and optimizes it for AI use (Qlik Answers and Qlik MCP) using a 5-Layer Model. Use this skill whenever the user wants to: assess or improve how well a Qlik app works with Qlik Answers or MCP, check AI readiness, fix field naming or grouping issues for AI, improve Master Item descriptions, reduce field noise, audit date fields for time-based questions, create synonym mappings, or prepare an app for AI consumption. Also trigger when: user says "AI-ready", "optimize for Answers/MCP", "Qlik AI Health Check", "AI Readiness", "prepare app for AI", "Answers isn't working", "Answers gives wrong results", "Master Items not showing", "fields not visible to AI", or mentions ungrouped items, noisy fields, or missing descriptions. Always use this skill even if the user only mentions one layer, one issue, or one field — the full assessment provides context for targeted fixes.
Transforms raw campaign performance data into a structured quarterly business review document with wins, misses, trend analysis, and recommended pivots for the next quarter. This skill should be used when building a QBR for a creator program, writing a quarterly influencer marketing review, summarizing multiple campaigns into a single quarterly report, presenting creator program results to leadership at the end of a quarter, analyzing quarter-over-quarter trends in influencer performance, preparing a board-level summary of the creator marketing program, identifying what worked and what to cut from the creator strategy, building a strategic plan for next quarter's creator campaigns, or reviewing the full roster performance over a quarter. For single-campaign ROI analysis, see campaign-roi-calculator. For weekly status updates, see campaign-status-dashboard-digest. For individual creator scoring, see post-campaign-creator-scorecard.
Get PostHog data into a canvas correctly: the host-injected `ph` SDK (loadInsight, query, capture, state, connectors, openExternal, navigate), the data hierarchy (saved insights first, typed query nodes second, inline HogQL last), verifiability (insight-backed metrics link their saved insight in PostHog; ad-hoc queries expose the exact query that ran), per-insight-type result shapes, progressive per-query loading, date-range wiring, live third-party data through the viewer's own connections (ph.connectors), and event capture from a canvas. Use whenever a canvas shows metrics, charts, tables, any PostHog data, or data from GitHub or an MCP server, or needs to send analytics events.
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.
Connect an arbitrary REST API to the PostHog data warehouse as a Custom source by authoring a JSON manifest, with no per-source code. Use when the user points at an API that has no built-in PostHog connector — "import data from this REST API", "sync my internal API", "connect this API from its docs", "build a custom data warehouse source" — and gives a docs URL or a natural-language description of the endpoints. Walks through drafting the RESTAPIConfig manifest (auth — bearer, API key, HTTP basic, or OAuth2 client credentials / refresh token — pagination, record path, incremental cursor, parent/child fan-out), validating it, test-reading live rows to verify the field mappings, and creating the source. If the API already has a native PostHog connector, use setting-up-a-data-warehouse-source instead — this skill checks the connector registry first and only handles APIs with no native connector.
Apply causal inference methods — counterfactual framework, instrumental variables, propensity score matching, and difference-in-differences — to estimate causal effects from observational data. Use this skill when the user needs to determine if X caused Y from non-experimental data, evaluate program/policy impact without a randomized trial, or control for confounders — even if they say 'did this change cause the improvement', 'how do we measure the impact without an experiment', or 'is this correlation or causation'.
Contributing to the Twenty codebase itself (twentyhq/twenty server internals), not for building apps on top of Twenty. Create cache services and transformation utilities for syncable entities in Twenty. Use when implementing entity-to-flat conversions, input DTO transpilation to universal flat entities, or cache recomputation for syncable entities.
Backtest trading strategies on historical data and interpret performance metrics. Provides run_backtest (crypto strategies) and run_prediction_market_backtest (Polymarket strategies). Fast execution (20-60s), minimal cost ($0.001). Returns Sharpe ratio, max drawdown, win rate, profit factor, and trade statistics. Use this skill after building or improving strategies to validate performance before deploying. NEVER deploy without thorough backtesting (6+ months recommended).
Scrape TikTok user collection folders and their video links with full metadata (plays, likes, comments, shares). Use when user asks to get, scrape, fetch, extract, or download TikTok collections, favorites, saved videos, bookmarks, or collection folder contents for any TikTok account. Accepts any user identifier — username, @username, profile URL, video URL, short link (vm.tiktok.com), user_id, or secUid. Zero external API dependency, no paid service needed, only requires curl_cffi. Works without login cookies for public collections (~80% coverage). Also use for TikTok competitor analysis, content research, viral video discovery, or building video databases.
Converts engineering analytics (PR / CI) data into saved PostHog insights, dashboards, and subscriptions, and explains how to query the product data directly with SQL. Covers discovering per-team GitHub warehouse tables via engineering-analytics-sources, replicating curated column semantics in HogQL, reading exposed engineering_analytics_* warehouse views where product logic is involved (CI cost, fingerprinted failure lines, commit attribution), saving queries with insight-create, and scheduling delivery with subscriptions-create. Use when asked to "save this as an insight", "put CI health / merge times on a dashboard", "email me PR throughput weekly", "chart CI cost", "track time to first review", "subscribe to these numbers", "alert on CI success rate", or "what data/tables/views does engineering analytics read". For ad-hoc CI and merge questions use diagnosing-ci-and-merge-bottlenecks; to investigate one specific CI failure use investigating-ci-failures.
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.