Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Rankup's dedicated skill for mini-game opportunities. Used to monitor game platform sitemaps, discover new game keywords within 24 hours, build multilingual keyword demand clusters, verify KD/SERP/7-day trends/standalone demand/playable supply, and generate a daily decision report; shared rules and scripts are committed with Rankup, while project-private results go into the Git-ignored .rankup/.
Open source project to make working with geospatial data in python easier. Extends the datatypes used by pandas to allow spatial operations on geometric types. Built on top of Shapely, Fiona, and Pyproj. Use for reading and writing spatial formats (Shapefile, GeoJSON, GeoPackage, KML), performing spatial joins, coordinate system transformations (reprojecting), geometric analysis (buffers, centroids, convex hulls), thematic mapping (Choropleth maps), calculating spatial relationships (contains, overlaps, touches, within), working with OpenStreetMap data or satellite-derived vector data.
Google Analytics 4 implementation and analysis reference. Use when querying live GA4 report data, setting up a GA4 property or data stream, installing gtag.js, designing event or ecommerce tracking, registering custom dimensions or audiences, sending server-side events via Measurement Protocol, linking GA4 to BigQuery and understanding the export schema, debugging with DebugView, or configuring Consent Mode and data retention. Do NOT use for general GTM container work such as triggers, variables, custom templates or server-side containers - use google-tagmanager; Google Ads scripting or ad reporting - use google-ads-scripts; writing or running SQL against GA4 export tables - use the bigquery skill; Universal Analytics or non-Google analytics tools.
Teaches an agent graph engineering — both halves. Knowledge graphs (ontology design, entity/relation/event extraction, fusion, GraphRAG/memory serving; distilled and translated from Southeast University's graduate Knowledge Graph course, npubird/KnowledgeGraphCourse, 4.4K stars) and task graphs (agent orchestration — parallel fan-out, verifier separation, the stop rule, human gates). Use when asked to build a knowledge graph, extract entities/relations from text, design an ontology, dedupe/merge entities, add graph memory or GraphRAG to an agent, orchestrate multi-agent workflows as a graph, or LEARN graph engineering — in teaching mode the agent explains each stage with worked examples and generates visual diagram artifacts.
Gravity and magnetic data processing and forward modelling using Fatiando a Terra. Use when the agent needs to: (1) Compute gravity forward models (point masses, prisms, tesseroids), (2) Apply terrain/Bouguer corrections, (3) Grid scattered potential field data with equivalent sources, (4) Perform upward/downward continuation, (5) Calculate magnetic anomalies from magnetized bodies, (6) Apply derivative filters (gradients, tilt angle), (7) Process regional or local gravity surveys.
Generates a single self-contained static HTML dashboard for a household finance JSON store, with embedded D3.js, inlined data, and six standard panels (net worth over time, monthly cash flow, recurring & subscriptions, goals progress, asset allocation, vigilance feed). Applies cognitive-design principles for visual hierarchy and visual-storytelling-design for narrative annotations. Use when emitting a weekly or monthly finance dashboard, or when user mentions weekly dashboard, household dashboard, finance HTML report, or static dashboard.
Huawei Cloud GaussDB distributed database (GaussDB for MySQL compatible edition and GaussDB for openGauss distributed edition) management and diagnosis skill. Provides 12 huawei_* actions across three capability tiers: (1) Query (R3, read-only auto-execute) — list/get instances, list flavors, list databases; (2) Analyze (R3, read-only auto-execute) — deployment-form analysis (shards/readonly nodes/engine version) and security configuration analysis (security group port/SSL); (3) Manage (R2/R1, preview + user confirmation) — create instance, create backup, add readonly node, add sharding node, update database permission, delete instance. Preserves 3 Critical Warnings: shard key is permanent once set, distributed GaussDB requires at least 3 nodes, and MySQL-compatible vs openGauss are separate products with pinned engine versions. Declares hcloud GaussDB CLI dependency; supports both AK/SK credentials and a locally configured hcloud profile. Triggers include: "GaussDB", "分布式数据库", "GaussDB(for MySQL)", "GaussDB(for openGauss)", "openGauss", "sharding", "分片", "添加分片节点", "只读节点", "readonly node", "GaussDB实例", "GaussDB备份", "数据库权限", "部署形态分析", "安全配置分析", "GaussDB诊断", "GaussDB运维", "HTAP", "GaussDB部署检查", "GaussDB安全基线".
Produce tracking reports (daily/weekly/monthly reports, research notes and structured tracking analyses) for industries or individual stocks, based on the East Money database. Triggered when either condition is met: (1) the user explicitly requests a "report", "research note", "tracking analysis" or a periodic tracking document; (2) the user names an industry, sector, index or stock (by name or ticker) and expects a systematic, written progress review. Typical requests include "write an XX industry report", "track XX stock", "generate the XX daily report", "see how XX has been doing lately and write a report".
Kaggle runtime environment, paths, accelerators, and reproducibility. PROACTIVELY activate for: (1) `/kaggle/input` path errors, (2) `/kaggle/working` output placement, (3) local vs Kaggle notebook behavior, (4) GPU/TPU/accelerator selection, (5) internet enablement, (6) package/version pinning, (7) memory cleanup and timeout issues, (8) DEBUG flags for fast runs, (9) Kaggle Secrets usage guidance, (10) quota-consuming runtime settings. Provides: path conventions, runtime checklist, accelerator IDs, reproducibility patterns, and resource safeguards.
KQL language expertise for writing correct, efficient Kusto Query Language queries. Covers syntax gotchas, join patterns, dynamic types, datetime pitfalls, regex patterns, serialization, memory management, result-size discipline, and advanced functions (geo, vector, graph). USE THIS SKILL whenever writing, debugging, or reviewing KQL queries — even simple ones — because the gotchas section prevents the most common errors that waste tool calls and cause expensive retry cascades. Trigger on: KQL, Kusto, ADX, Azure Data Explorer, Fabric Real-Time Intelligence, EventHouse, Log Analytics, log analysis, data exploration, time series, anomaly detection, summarize, where clause, join, extend, project, let statement, parse operator, extract function, any mention of pipe-forward query syntax.
Installs and configures ktx, the open-source context layer for data agents — runs ktx setup non-interactively with hidden CLI flags, configures database connections and embeddings, installs agent integration, and verifies readiness. Use when the user asks an agent to add ktx to a project, connect data sources, install agent rules, ingest schema, or troubleshoot a local ktx install.
Search LinkedIn posts by keywords, sorted by engagement or date. Use when researching what people are saying about a topic on LinkedIn, finding high-engagement content, identifying thought leaders, or discovering warm leads through post engagement. Returns author, post text, reactions, comments, shares, post URL, and date. No LinkedIn cookies or login required.
Patterns for using blockedImage to process large images, harness parallel compute for image processing, and write custom adapters. Use when writing code that creates, processes, or visualizes blockedImage objects, when implementing images.blocked.Adapter subclasses, or when a user needs help with large image data. Always use this skill when working with TIFF,GeoTIFF, .svs, .ndpi, .czi or other WSI, satellite imagery or microscopy volume image formats.
Build reusable activation models — an activation-rate metric and a per-user/per-account activated flag — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to define, model, or measure activation, the "aha moment", onboarding success, or which early actions predict a user sticking around. The core idea this skill enforces: activation is NOT a single assumed event — it is a retention-validated combination of early actions, chosen by balancing reach (enough users hit it) against predictive power (those who hit it retain much better). Covers finding candidate actions, validating them against retention lift, count thresholds and action combinations, per-product and B2B group-level activation, and modeling the winning definition as a durable activated-flag + activation-rate model. Read modeling-warehouse-foundations first; composes modeling-product-usage-metrics for the retention validation.
Search OpenSearch documentation, blogs, and community forums. Use when the user asks about OpenSearch features, configuration, APIs, troubleshooting, k-NN, neural search, cluster settings, index mappings, query DSL, or any OpenSearch-related questions.
Use when auditing paper source-data tables and registered image assets for statistical signals or data inconsistencies, interpreting paperconan scan.json/report.html, preparing cautious PubPeer or research-integrity notes, or finding open supplementary data from a DOI/title. Trigger on 论文数据检查, source data audit, paper data audit, suspicious numeric tables, figure review, multimodal image review, PubPeer prep, research integrity, DOI/title data fetch. Covers .xlsx/.csv/.tsv, tables in .pdf/.docx, and adaptive image review by an external multimodal Agent; not chart digitization or autonomous semantic judgment.
Add, configure, bind data to, and bulk-manage visuals on Power BI PBIR report pages using pbi-cli. Invoke this skill whenever the user mentions "add a chart", "bar chart", "line chart", "card", "KPI", "gauge", "scatter", "table visual", "matrix", "slicer", "combo chart", "bind data", "visual type", "visual layout", "resize visuals", "bulk update visuals", "bulk delete", "visual calculations", or wants to place, move, bind, or remove any visual on a report page. Also invoke when the user asks what visual types are supported or how to connect a visual to their data model.
Creates Prowler Attack Paths openCypher queries using the Cartography schema as the source of truth for node labels, properties, and relationships. Covers Prowler-specific additions (Internet node, ProwlerFinding, internal isolation labels), $provider_uid scoping, and list-property item nodes with typed `HAS_*` edges that run efficiently on both Neo4j and Amazon Neptune sinks. Trigger: When creating or updating Attack Paths queries.
Geochemistry data analysis and visualization for igneous, metamorphic, and sedimentary rocks. Use when the agent needs to: (1) Create ternary diagrams for compositional data, (2) Plot REE spider diagrams with normalization, (3) Build TAS or other classification diagrams, (4) Apply log-ratio transforms to compositional data, (5) Calculate CIPW norms, (6) Generate Harker variation diagrams, (7) Compute element ratios and anomalies.
Guides Qdrant monitoring and observability setup. Use when someone asks 'how to monitor Qdrant', 'what metrics to track', 'is Qdrant healthy', 'optimizer stuck', 'why is memory growing', 'requests are slow', or needs to set up Prometheus, Grafana, or health checks. Also use when debugging production issues that require metric analysis.
Read this BEFORE writing, modifying, debugging, or explaining any Scrapy or web-poet code — spiders, page objects, pipelines, settings, selectors — down to a one-line fix, or scaffolding/configuring a Scrapy project, scrapy-poet, scrapy-zyte-api, or browser rendering. These libraries moved on since your training cutoff; invoke this FIRST. NOT for building a scraper for a given site (scrape), a saved HTML file (scrape-analyze-page), or Scrapy Cloud deploy/jobs (zyte).
Model and analyze Semantic Spacetime (SST) graphs, distances, trajectories, drift, and model files. Do not use this skill for promise-theory vocabulary and fundamentals without SST modeling; use `promise-theory` for the substrate concepts.
A world-class data science skill for statistical modeling, experimentation, causal inference, and advanced analytics. Expertise in Python (NumPy, Pandas, Scikit-learn), R, SQL, statistical methods, A/B testing, time series, and business intelligence. Includes experiment design, feature engineering, model evaluation, and stakeholder communication. Use when designing experiments, building predictive models, performing causal analysis, or driving data-driven decisions.
Use when starting a SpacetimeDB project, installing the CLI, logging in, understanding architecture, or following quickstarts for TypeScript, React, Angular, Vue, Svelte, Next.js, Nuxt, Remix, TanStack, Browser, Node.js, Bun, Deno, Rust, C#, or C++. Triggers on: install SpacetimeDB, quickstart, getting started, architecture, state mirroring, FAQ, new app.
Index coverage and N+1 review aids for SQLite/D1 schemas with a sqlc catalog. Surfaces unused indexes (with FK CASCADE awareness so cascade-load-bearing indexes are not flagged), queries that scan tables without index help, and `for`-loops calling generated SQL fns.
Comprehensive guide for SymPy - Python library for symbolic mathematics. Use for symbolic expressions, calculus (derivatives, integrals, limits, series), equation solving (algebraic, differential, systems), linear algebra, simplification, matrix operations, special functions, code generation, and mathematical proofs. Essential for analytical mathematics and computer algebra.
Review traction experiment results and recommend whether to double down, iterate, repeat Bullseye, or pivot. Use when analyzing growth test data, comparing channel performance, deciding if a channel moved the needle, or reassessing startup traction strategy.
The Stock Screener. Checks a list of companies against the user's own rules (revenue growth, margins, EPS, P/E, earnings yield, sector, anything in the metrics file), says exactly which rule each company passes or fails and by how much, and ranks the ones that pass into a shortlist. Reads the metrics /trader-analyst writes from SEC filings, or any CSV. Use when the user says "screen for stocks", "find me companies that", "filter my watchlist", "which of these pass my rules", "shortlist candidates", "rank these stocks", or "growing companies under 30 times earnings".
Tiered LLM extraction pattern for large corpus processing (email archives, document dumps, transcript libraries). A utility-tier model triages and classifies at speed; the reasoning tier does the default deep read; the deep tier is the escalation for the highest-value content. Prevents spending deep-tier money on noise while ensuring the important content gets the best eyes. A deterministic privacy wall runs before any LLM call.
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.