Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Use when planning, funding, scoping, or synthesizing enterprise research across workstreams — clinical study design, R&D program finance, market sizing/surveys, or product/user research. Triggers on "design this clinical study", "what sample size", "R&D budget", "burn rate", "capitalize or expense", "TAM SAM SOM", "market sizing", "survey design", "segment the market", "plan user interviews", "usability test", "synthesize research insights". Forks context to route to one of four Research-Operations sub-skills (clinical-research, research-finance, market-research, product-research) and returns a digest. Distinct from ra-qm-team (regulatory submission), finance (corporate close/valuation), research/grants (funding discovery), product-team (persona/journey/live experiments), and marketing-skill (campaign analytics).
Use when a user wants to upgrade, update, or migrate a dbt-core project to the latest version — e.g. "upgrade my dbt project," "migrate this off dbt-core 1.5," "get this project running on the latest dbt," "bump the dbt-core version." Upgrades a dbt-core v1 project (on 1.3, 1.4, 1.5, 1.6, or 1.7) all the way to 1.12, applying the required breaking, behavior, and deprecated changes from a data-driven issue corpus. Inputs — starting_version (the project's current dbt-core minor, one of 1.3/1.4/1.5/1.6/1.7) and adapter_type (snowflake/redshift/bigquery/databricks/spark); both are normally supplied by the caller (e.g. the dbt VS Code extension), with fallbacks described in the skill.
Valkey (Redis-compatible) in-memory data store for caching, session storage, pub/sub, queues, and distributed locks. Use when configuring Valkey or Redis-compatible caching, choosing eviction policies, implementing rate limiting, setting up pub/sub or streams, writing Docker Compose services, migrating from Redis, or tuning performance. Use for valkey, redis, cache, session, pub/sub, streams, distributed-lock, rate-limit, sorted-set.
XYO Protocol 2.0 domain knowledge. Covers payloads, bound witnesses, schemas, the module system (archivist, diviner, witness, sentinel, node), accounts, wallets, and protocol best practices. Activates when building on XYO or working with @xyo-network packages.
Write, edit, and adapt PostHog Signals scouts: scheduled agents that scan a project and report findings. Use to change a canonical scout's scope, thresholds, schedule, or dry-run settings; add a scout for an uncovered surface; record structured output from scheduled LLM scoring; or give feedback through notes. Covers SKILL.md structure, report requirements, follow-up report checks, structured output, duplicate detection, scratchpad memory, scout notes, per-team skills-store and canonical repository edits, and private prompt trials with saved rubrics. Trigger on "write/edit/customize a signals scout", "new scout for X", "tune my scout schedule", "make a scout that watches <event>", "score/judge/measure X with a scout", "test/compare scout prompts", "generate scout rubrics", "structured output from a scout", "scout output to Slack", "leave a note for / give feedback to a scout".
Bounded research experiment loop that tries hypotheses, measures benchmark evidence, keeps what works, and records what fails. Use when the user asks to optimize a research metric, run an experiment loop, improve model/retrieval/evaluation performance iteratively, or benchmark a research hypothesis.
Tags harness-decomposed curriculum items (KUDs, LTs, criteria) with a school's developmental band metadata while preserving source voice and labels. Supply the band schema; the skill derives mapping rules from it.
GPU optimization for consumer NVIDIA GPUs (8-24GB VRAM) covering mixed precision, gradient checkpointing, XGBoost GPU, CuPy/cuDF migration, and torch.compile. Triggers on: "optimize GPU training", "speed up CUDA", "reduce OOM", "migrate NumPy to CuPy", "manage GPU memory", "benchmark PyTorch".
Analyze trends and patterns in health data over a period of time. Correlate changes in medications, symptoms, vital signs, lab results, and other health metrics. Identify concerning trends, improvements, and provide data-driven insights. Use when the user asks about health trends, patterns, changes over time, or "what's changed in my health?". Supports multidimensional analysis (weight/BMI, symptoms, medication adherence, lab results, mood and sleep), correlation analysis, change detection, and interactive HTML visualization reports (ECharts charts).
Give cited public Splunk knowledge-object governance guidance and assess user-authorized inventory, ownership, orphan, ACL, naming, lifecycle, lookup, and search-head-cluster comparison evidence without changing a deployment. Use for shared lookups, sourcetypes, saved searches, macros, field extractions, aliases, props/transforms, CIM mappings, dashboards, reports, and related objects when an administrator needs a read-only hygiene report, safe review plan, or boundary route.
Filter Etsy products by multiple criteria using the EHunt MCP tool `_ehunt_productQuery` (display name: “Etsy Product Query”), including keywords/URLs, price, sales, favorites, reviews, listing date, category, handmade/vintage types, and Pick/Bestsell/Raving, among others. Trigger when users mention EHunt Etsy products, Etsy listings, Etsy product research, Etsy bestsellers, Etsy handmade, Etsy vintage, ehunt items, Etsy Product Query, or `_ehunt_productQuery`. Also trigger this skill when users search for products on Etsy, check sales, prices, or tags, or filter products, even if they do not mention EHunt.
openfootball (football.json) is a free, open, public domain collection of football (soccer) match data in JSON format. It covers major leagues worldwide including the English Premier League, Bundesliga, La Liga, Serie A, Ligue 1, World Cup, Euro, and Champions League. Use this skill to fetch historical and current season fixtures, results, and scores. No API key or authentication is required.
A high-performance analysis engine for Excel datasets of ten thousand rows or more. It provides openpyxl read_only streaming reads (iter_rows supports over 100,000 rows), Parquet conversion for speed, memory optimization, chunked processing, and large-file write mode. **Proactively use this skill in any of the following cases**: ① the row count ≥ 10k (triggered by the row-count assessment step of sn-da-excel-workflow); ② the user uses trigger words: 大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing; ③ using pd.read_excel() directly causes a timeout or memory overflow; ④ the user explicitly requests high-performance processing of a large-scale dataset. Not for: routine Excel analysis of fewer than 10k rows (just use sn-da-excel-workflow).
Mendelian randomization (MR) causal inference — does an exposure, risk factor, or biomarker CAUSALLY affect a disease/outcome, using genetic variants as instrumental variables (IEU OpenGWAS / EpiGraphDB MR-EvE). Use this whenever the user asks if X causes Y, whether an observational association is actually causal or just correlation, if a biomarker/trait is a causal risk factor, wants to triangulate epidemiology against genetic evidence, or mentions Mendelian randomization, instrumental-variable analysis, two-sample MR, or genetic causal evidence — even if they never say "MR" (e.g. "is LDL cholesterol actually causal for heart disease?", "does BMI cause type 2 diabetes or just correlate?", "is CRP a causal driver of stroke?"). Covers trait-label resolution, MR effect direction/magnitude, instrument quality (MOE score), method agreement (IVW vs MR-Egger vs weighted median), bidirectional MR for reverse causation, and distinguishing causation from genetic correlation. Not for plain GWAS association lookups (use the GWAS skills) or fitting your own instruments from raw summary statistics.
When the user wants to set up, improve, or audit analytics tracking and measurement. Also use when the user mentions "set up tracking," "GA4," "Google Analytics," "conversion tracking," "event tracking," "UTM parameters," "tag manager," "GTM," "analytics implementation," "tracking plan," "how do I measure this," "track conversions," "attribution," "Mixpanel," "Segment," "are my events firing," or "analytics isn't working." Use this whenever someone asks how to know if something is working or wants to measure marketing results. For A/B test measurement, see ab-test-setup.
Fetches web pages and converts them to clean markdown using a robust 3-tier chain (Firecrawl → Jina Reader → Scrapling stealth browser). Use this skill instead of WebFetch whenever the user provides a URL and needs the page's text content — especially for sites that block direct access: medium.com articles (paywalled/metered), WeChat public accounts (mp.weixin.qq.com, geo-restricted), documentation sites with bot protection, or any page where simple HTTP fetching might return a CAPTCHA or empty page. Triggers for: "read this URL", "summarize this article/page", "grab the content from", "extract text from", "what does this page say", "fetch this link", or any request to access and process a specific web page. Do NOT trigger for: building scrapers, checking HTTP status codes, parsing already-downloaded HTML files, answering conceptual questions about scraping tools, or monitoring page changes.
Skill that helps users discover and understand Dagster integration libraries. Used when users have requests related to integrating with other tools / technologies, or when have users have questions related to specific integration libraries (dagster-*).
Standalone infographics that explain data, processes, comparisons, and timelines as a shareable graphic, via HTML/CSS/SVG (default when numbers must be exact) or Gemini 3.1 Flash image generation (illustrative, low-text pieces). Covers color coding, stat highlights, SVG charts, and layout templates. Use for a one-piece visual explainer; for interactive app dashboards use dashboard-design, for a feed stat post use social-media-graphic. Trigger phrases: "create an infographic", "design a chart", "data visualization", "process flow", "comparison infographic", "timeline design", "stats graphic", "infographic design", "visualize data".
Filter Etsy stores across multiple dimensions using the EHunt MCP tool `_ehunt_storeQuery` (display name “Etsy Store Query”), including sales, favorites, reviews, opening date, country, main category, and Raving/stars. Trigger when users mention EHunt Etsy stores, Etsy store search, Etsy seller, Etsy store rankings, Etsy stores by weekly sales, ehunt stores, Etsy Store Query, or `_ehunt_storeQuery`. Also trigger when users want to find Etsy stores, filter store data, or analyze store performance, even if they do not mention EHunt.
Best practices for MariaDB replication and high availability — Galera Cluster, GTID replication, semi-synchronous replication, parallel replication, and application patterns for HA environments. Use when setting up replication, designing applications for HA, working with Galera Cluster, asking about MariaDB GTID, handling replication lag in application code, or choosing between replication topologies. IMPORTANT — MariaDB GTID format is incompatible with MySQL GTID, and Galera Cluster needs no server plugin to load but does require the separate galera wsrep provider library (galera-4).
Use when the user wants to generate or edit images with Google's Nanobanana/Gemini image models using the official Gemini API shape, or when they need publication-style scientific figures rendered exactly from data with the bundled Python plotting tool. Prefer this skill for text-to-image, image-to-image editing, multi-image reference workflows, attachment-based recreations, exact bar/trend/heatmap/scatter plots, or when the user wants publication-style figures such as materials-science paper schematics. Use it when the user asks for a materials-science figure, journal-style scientific illustration, graphical abstract, mechanism diagram, device architecture, processing workflow, or paper-ready materials figure.
OpenTelemetry Transformation Language (OTTL) expert for writing and debugging telemetry transformations in the OpenTelemetry Collector. Use when authoring or reviewing `transform`, `filter`, `tail_sampling` processor configs or `routing` connector configs, debugging OTTL syntax or semantics, transforming traces, metrics, logs, or profiles, or converting data-processing requirements into OTTL statements.
Guide for migrating to Polar from other payment platforms (Stripe Billing, Paddle, Lemon Squeezy, Gumroad). Use this skill when: (1) Planning a migration from another payment provider to Polar; (2) Migrating customer data and subscriptions; (3) Running parallel systems during transition; (4) Mapping products and pricing between platforms; (5) Handling payment method migration; (6) Communicating migration to customers; (7) Testing migration in sandbox before production.
Generate SQL queries from natural-language requirements using SELECT, JOIN, GROUP BY, window functions, CTEs, and subqueries. Use when the user needs a new query from a business question or schema; use query-optimization when an existing query or execution plan is slow.
Call POST /embeddings on Venice. Covers request shape (input, model, encoding_format, dimensions, user), text-only input (token arrays rejected), per-input and batch limits, per-model dimensions/privacy, the text-embedding-ada-002 alias, API-key privacy gating, OpenAI/LangChain compatibility, response compression (gzip/br), and practical usage for retrieval, clustering, and RAG.
Analyzes CockroachDB range distribution across tables and indexes using SHOW RANGES to identify range count, size patterns, leaseholder placement, and replication health. Use when investigating hotspots, uneven data distribution, range fragmentation, or validating zone configuration effects without DB Console access.
Audits optimizer table statistics for staleness, missing coverage, and data quality issues using SHOW STATISTICS. Use when diagnosing poor query performance, unexpected plan changes, or after bulk data changes to identify stale statistics requiring refresh via CREATE STATISTICS.
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.