Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Build reusable conversion models — funnel/step conversion rates, drop-off, and time-to-convert — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to model, define, or compute a conversion rate, funnel, step completion, drop-off, activation-funnel, signup-to-paid, or any "what % of users who did A went on to do B (within N days)" metric. Covers the funnel model (ordered steps, the conversion-window time-box, strict vs any-order), the person-vs-group aggregation unit, overall vs step-to-step conversion (two different numbers), breakdown attribution, and when a saved funnel insight beats a warehouse view. On PostHog, model funnels in HogQL with windowFunnel; in dbt, stage the event stream and compute an fct_conversion mart with tests. Read modeling-warehouse-foundations first for the view-vs-dbt mechanics; pairs with query-funnel for interactive analysis.
Design and roll out a price increase or packaging change without triggering churn. Segment the base by price sensitivity, model revenue and churn scenarios, decide grandfathering and notice strategy, and produce the full comms kit (customer email, in-app notice, sales talk track, support FAQ, objection handling). Use when raising prices, repackaging tiers, or moving customers to new plans.
Query usage stats for Zyte API requests that have already been sent, including cost, request volume, response times, status codes, filters, grouping, and pagination. Use this skill whenever answering the request requires looking up recorded Zyte API usage, spend, request counts, response times, grouped stats, or filtered stats—including projecting future spend or usage when the projection explicitly extrapolates from actual recorded usage (e.g. “based on this month's usage so far, project month-end spend”). Do not use it when the user asks what a spider, job, or workload might, would, or could generate—those are hypothetical estimates with no recorded data to query, even if a spider exists in the project. For a projection to qualify, the user must explicitly reference past or current recorded usage as the basis. Also do not use for dashboard setup, documentation, configuration, or account-help questions.
Expert SQL query writing, optimization, and database schema design with support for PostgreSQL, MySQL, SQLite, and SQL Server. Use when working with databases for: (1) Writing complex SQL queries with joins, subqueries, and window functions, (2) Optimizing slow queries and analyzing execution plans, (3) Designing database schemas with proper normalization, (4) Creating indexes and improving query performance, (5) Writing migrations and handling schema changes, (6) Debugging SQL errors and query issues
Population genetics analysis — allele frequencies (gnomAD, 1000 Genomes), Hardy-Weinberg equilibrium testing, Fst between populations, GWAS associations, evolutionary constraint scores. Use for cross-population variant comparison, ancestry-aware allele frequency lookups, and population-level evolutionary analysis.
Use when data needs statistical analysis. Runs reproducible Python/R code for Table 1, diagnostic accuracy, agreement, regression, survival, propensity score, survey-weighted and repeated-measures models, with publication tables. Sample size is /calc-sample-size; pooling studies is /meta-analysis.
Declare the pipeline from data source to predictor as a skrub DataOps graph. Stateless steps use `.skb.apply_func`. Stateful steps use `.skb.apply`. After the graph exists, attach the locked splitter and any non-default score. No fit, tune, persistence, or `skore.evaluate`. TRIGGER when writing or editing any link from data source to predictor (loaders, preprocessing, features, composition, the final estimator), including a pure-Python function on that path, a step added or reordered, a bare `sklearn.Pipeline` as the top-level, or a request to build a pipeline, classifier, or regressor. HOW TO USE: before the first declarative line and on every structural edit. Read the stops and emit Pre-flight before code. Confirm new names with `python -m skore_skills api get`.
Use this skill whenever the user wants Gate.info / Gate.news research via gate-cli: single-coin, market overview, multi-coin compare, TA, macro, or research+news. Trigger phrases include: analyze SOL, how is BTC, compare BTC and ETH, technical analysis, NFP impact, research with news. Info primary; news auxiliary. Delegate: gate-info-risk (safety), gate-info-web3 (on-chain primary), gate-news-intel (news-first). v0.7.6+ uses playbook shortcuts when available; legacy multi-step fallback below 0.7.6.
Classify directly valued Jinkō model inputs by evidence source and assign inputs needing calibration to explicit calibration steps. Use when the user wants to decide which parameters, categorical parameters, or species initial conditions should be calibrated and record the decision with `s::*` and `CalibIter::*` tags. Do not use for choosing datasets, estimating priors, drafting calibration plans, or running calibrations.
Extract or digitize reported biomedical values from papers, figures, tables, supplements, images, or web sources into traceable CSV/Markdown, optionally as a calibration-ready Jinkō data table. Use when numeric evidence must be transcribed, normalized, unit-converted, or bound to model observables. Do not use for literature discovery, evidence synthesis, or inventing values absent from the source.
Find and shortlist ClinicalTrials.gov registry and posted-results records for biomedical modeling evidence. Use for NCT discovery, status/phase/results screening, endpoint and population inventory, comparator landscapes, and ongoing-trial intelligence. Do not use for PubMed publication discovery, quantitative extraction, protocol authoring, Jinkō trial execution, calibration, model building, or systematic reviews.
Build structured knowledge graphs from unstructured text by extracting entities, mapping relationships, generating graph triples, and visualizing the result. Use when the user requests knowledge graph creation or provides relevant inputs for this workflow.
Use when a paper needs publication-ready figures or a visual abstract. Makes ROC, forest, calibration, Kaplan-Meier and Bland-Altman plots, CONSORT/STARD/PRISMA flow diagrams, confusion matrices, pipeline diagrams and journal visual abstracts, checking the journal's AI-image policy first.
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.
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.
Build reusable revenue models — MRR, ARR, gross revenue, new/expansion/contraction/churn, ARPU, LTV, and per-customer/per-account revenue — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to model, define, or compute recurring revenue, monthly/annual recurring revenue, churn or retention of revenue, lifetime value, average revenue per user, or revenue by customer, cohort, product, or currency. On PostHog, build on the managed *_revenue_view views (revenue_item, mrr, customer, subscription, charge, product) fed by Stripe or custom revenue events — not raw Stripe tables — and normalize money with convertCurrency(). In dbt, stage the payment source and compute fct_mrr / fct_revenue_item / dim_customer marts with tests. Covers picking the right source, the subscription-config gotcha that leaves MRR empty, currency handling, and linking revenue to persons/groups. Read modeling-warehouse-foundations first for the view-vs-dbt mechanics.
Token-Oriented Object Notation (TOON) format expert for 30-60% token savings on structured data. Auto-applies to arrays with 5+ items, tables, logs, API responses, database results. Supports tabular, inline, and expanded formats with comma/tab/pipe delimiters. Triggers on large JSON, data optimization, token reduction, structured data, arrays, tables, logs, metrics, TOON.
Extract metadata and content from WeChat Official Account articles. Use when user needs to parse WeChat article URLs (mp.weixin.qq.com), extract article info (title, author, content, publish time, cover image), or convert WeChat articles to structured data. Supports various article types including posts, videos, images, voice messages, and reposts.
Generate reproducible analysis artifacts — SQL queries, Python visualizations, and summary tables — as you work through a BigQuery data analysis. Use when asked to conduct a deep dive, exploratory analysis, or investigation that goes beyond a simple data lookup.
Step-by-step orchestrator for building Domo App Studio apps with native KPI cards via community-domo-cli. Sequences app creation, pages, theme, hero metrics, native charts, filter cards, layout assembly, and navigation. CLI-first — no raw API calls.
Show AI coding usage insights: cost, tokens, session activity, and breakdowns by member, model, agent, project, product, or prompt quality. Also finds who on a Team (CawPlan product line) hasn't submitted their daily coding report, rolls up a Team's cost, flags high-cost/low-diff sessions, and flags a member's cost growth. Use when: the user asks about coding costs, AI usage stats, team session activity, model spend, agent usage, prompt quality, productivity metrics, which team members haven't submitted/committed a coding report, a Team's total coding cost, sessions with disproportionately high cost vs code changed, or whether someone's coding cost has grown notably. NOT for: submitting reports, creating tickets, product health metrics, or release tracking.
Generates Enonic XP scripts for bulk content operations—creating, updating, querying, migrating, and transforming content using lib-content and lib-node APIs. Covers the query DSL (NoQL), aggregations, batch processing, task controllers for long-running operations, and export/import workflows. Use when writing bulk content creation, update, or deletion scripts, querying with NoQL syntax, migrating content between environments, running long-running task operations, or working with aggregations and paginated retrieval. Do not use for Guillotine GraphQL frontend queries, content type schema definitions, single contentLib.get() calls, or non-Enonic data migration tools.
Stock screening and ranking for US equities using SEC EDGAR data. Use when asked to find stocks by sector or theme; rank stocks by valuation, growth, or quality metrics; surface investment ideas; screen for stocks meeting specific criteria; or find the best growth, value, or quality stocks in a group. Triggers: “best AI stocks”, “cheap healthcare stocks”, “fastest growing semiconductors”, “find me value stocks”, “screen for high-growth tech”, “rank these stocks by quality”, “which of these is the best growth stock”. Note: For side-by-side peer benchmarking with statistical analysis, use comps-analysis instead.
Build reusable dimension / lookup tables for a star schema — country/region, timezone, currency, date, plan/product, and other descriptive attributes — on either PostHog data-warehouse views (HogQL) or an external dbt project. Use when the user wants to model dimension tables, lookup tables, a star schema, conformed dimensions, or wants to enrich events/revenue/usage with country, region, timezone, plan, or currency attributes without repeating JOINs. Covers sourcing the dimension data (upload, warehouse source, or derive from events), shaping it into an aliased one-row-per-entity view (optionally materialized on a slow schedule since dimensions change rarely), and attaching it to facts via a saved or person join so its columns read as native fields. Key rule: for currency use the built-in convertCurrency() instead of a hand-rolled rate table. Read modeling-warehouse-foundations first; dimensions here are reused by the revenue, conversion, activation, and product-usage modeling skills.
MongoDB document modeling, aggregation pipeline optimization, sharding strategies, replica set configuration, connection pool management, and indexing patterns. Use this skill for MongoDB-specific issues, NoSQL performance optimization, and schema design
Structural pytest: prediction count must match the predict-grid row count. TRIGGER when an approved experiment needs its smoke test, `pytest tests/smoke/` fails on row count, the user asks why the smoke test is failing, a pipeline edit needs proof, or the experiment script changes pipeline shape. STOP when `status.setup.pending` is non-empty (load `setup-ml-project`), or when there is no approved design or no matching experiment script: explain and send the user to setup or stay in `build-ml-pipeline`. A declined git is not asked again. "Why is smoke failing?" stays here. This action does not cover regression tests or CV interpretation. Do not write `skore.evaluate`. HOW TO USE: `status`, read the journal and experiment, write `tests/smoke/test_NN_*.py`, then `python -m skore_skills smoke run --stem <stem>`. Red JSON means fix the pipeline in `build-ml-pipeline`. Do not loosen the assertion.
Gene regulatory network analysis — TF-target inference (JASPAR motifs, ChIP-seq), motif scanning, eQTL integration, perturbation evidence (knockout/overexpression). Use for 'which TF regulates gene X', 'which genes does TF Y target', regulatory pathway reconstruction. Distinguishes direct (binding) vs indirect (co-expression) regulatory evidence.
Generic playbook for extracting structured data from any website — hotel prices, flight fares, e-commerce listings, real estate, jobs, competitor product catalogues, anything where the goal is to turn one or more URLs into clean records on disk. Use this skill whenever the user mentions scraping, harvesting, extracting, or pulling data from a website; names a specific site or competitor they want data from; asks how to handle JavaScript-rendered pages, Cloudflare blocks, bot detection, Turnstile challenges, or Playwright; wants to monitor prices over time; needs to automate a copy-paste research task; or says things like "just get the data from X" or "I need a script that grabs N from site Y". Covers recon, picking the lightest extraction tool that works, surviving anti-bot defences, and writing clean JSONL output with a run manifest. Scope is scraping only — landing data in a database, scheduling, and downstream pipeline work are explicitly out of scope and live in other tools.
Alibaba Cloud Milvus full-stack Skill for two planes: control-plane instance management via aliyun CLI, and data-plane Milvus operations via pymilvus. Use when users want to create, inspect, scale, configure, network-enable, or whitelist Alibaba Cloud Milvus instances; or connect to Milvus and perform collection management, vector insert/search, hybrid search, full-text search, index management, partition/database management, or RBAC with Python.
Challenge an outbound campaign copy by benchmarking it against the user's existing campaigns — what worked, what didn't, what the winners do differently — and return a concrete verdict plus prioritized fixes. Use whenever the user wants to know if a campaign or sequence is good, compare a draft to past campaigns, audit campaign copy against real performance, pressure-test a sequence before launch, validate a sequence before going live, or asks 'is this campaign as good as my best ones'. Triggers on: 'challenge this campaign', 'benchmark this sequence', 'is this campaign good', 'audit my copy', 'pressure-test before launch', 'compare to my best campaigns', 'should I launch this'. Pulls existing campaign performance from the La Growth Machine MCP when connected; otherwise works from stats and copy the user pastes; falls back to a best-practice baseline when there is no campaign history. For SDR, RevOps, Growth, Head of Sales/Marketing, founders launching outbound. Maintained by La Growth Machine.
Rank outreach campaigns by real revenue impact — which campaigns actually generated deals, pipeline, or meetings — by cross-referencing the user's La Growth Machine campaign data with their CRM deal data (HubSpot today). Use whenever the user wants to know which campaigns drove pipeline, compare campaign ROI, see which campaigns to continue / stop / adapt, audit campaign impact, review attribution, asks 'which of my campaigns is actually working', or wants a campaign performance ranking by deals or revenue. Triggers on: 'which campaigns drove pipeline', 'rank my campaigns by deals', 'campaign ROI', 'campaign impact', 'which campaigns to stop', 'which to scale', 'attribution review', 'pipeline by campaign'. Pulls live data from the La Growth Machine MCP and the HubSpot MCP when connected; works from pasted exports otherwise. For RevOps, Heads of Sales/Marketing, founders and growth leads doing campaign performance reviews. Maintained by La Growth Machine.
Aggregate CawPlan product insights: user feedback and critical issues. Use when: the user asks for a product health overview, user feedback trends, or a combined product insights summary. NOT for: date-range activity reports, ticket creation, single-metric queries, user activity, or device/app adoption metrics (installations, crash rate -- that public endpoint has been retired, no longer available via CLI).
Query A-share and Chinese financial market data via multiple data sources. Tier-1 paid source is iFind (同花顺, covers stocks/funds/macro/bonds/HK-US/ESG/index-sectors). Tier-2 free source is AkShare (行情/财报/行业/指数). Use whenever the agent needs Chinese financial data — compatible with 沪深 A 股, 科创板, 创业板, 北交所, and 港股通 stocks.
Set up end-to-end Change Data Capture (CDC) pipelines on Confluent Cloud using Debezium source connectors, Flink for transformation, and Tableflow for data lake integration. Supports JSON_SR, Avro, and Protobuf formats. Handles schemaless topics (plain JSON without SR) and multi-event topics. This skill handles the complete workflow from database to Iceberg/Delta tables. Use this skill when users want to capture database changes and materialize them into Iceberg or Delta Lake tables via Confluent Cloud Tableflow. Trigger phrases include "CDC to Tableflow", "database to Iceberg", "database to Delta Lake", "stream database changes to data lake", "set up Tableflow pipeline", "schemaless topic to Tableflow", or "multi-event topic to Iceberg". Do NOT trigger for general CDC, Debezium, or database replication requests that do not involve Tableflow or Iceberg/Delta Lake as the destination.
Scaffolds Drizzle ORM + SQLite boilerplate: a new `drizzle.config.ts`, a singleton client with the right pragmas, per-table schema files with explicit primary keys/indexed foreign keys/relations()/inferred types, per-table repository modules with `.returning()` + `inArray()` + `.onConflictDoUpdate()`, or drizzle-zod validators. Produces convention-enforced templates for three drivers (better-sqlite3, libsql/Turso, bun:sqlite). Trigger even when the user doesn't say "scaffold" — phrases like "add a table for X", "set up Drizzle in this project", "wire up SQLite", "create a CRUD module for X", or "bootstrap the DB layer" should pull this in. Pairs with the `drizzle-sqlite` skill, which covers the 45 rules these templates encode — read it when an exception is required
Only for ordinary spreadsheets (Sheet) and multidimensional tables (Bitable/Base); not a general entry point for all data or JSON requests. Use when the user asks to read or write cells, import or export sheets, set styles/filter views/conditions/dropdowns/native cell images/floating images, or operate Bitable tables, fields, records, views, roles, collaborators, dashboards, forms, workflows, and data aggregation. This Skill is also required for --as bot cron/unattended Bitable scenarios. Explicitly do not use for document permissions/collaborators, message/event subscriptions, or generic passthrough of unwrapped OpenAPI; use feishu-cli-storage, feishu-cli-messaging, and feishu-cli-platform for those, respectively. For Markdown tables within documents, use feishu-cli-docs; for data chart display, use feishu-cli-visual
Gate partner affiliate data and application skill. Use when the user asks about partner commissions, referral volume, or applying for the affiliate program. Triggers on 'my affiliate data', 'partner earnings', 'apply for affiliate', 'commission'.
Huawei Cloud RDS (Relational Database Service) full-scenario intelligent service covering all database engines (MySQL, PostgreSQL, SQL Server, MariaDB, GaussDB for MySQL, TaurusDB). Provides six capability domains: (1) Basic intelligent Q&A for RDS product features, best practices, and specifications; (2) SQL statement performance optimization with slow log analysis, top SQL, execution plan guidance, and index recommendations; (3) Database instance daily O&M including health inspection, restart, flavor resize, disk expansion, primary-standby switchover, and read replica management; (4) Online fault localization and troubleshooting via error logs, replication status, connection diagnostics, and recovery time window; (5) Parameter tuning with parameter group management, modification suggestions, and performance parameter adjustment guidance; (6) Backup and recovery guidance including backup policy management, manual backup creation, restore to new/existing instance, and point-in-time recovery. Uses CLI→SDK→API three-level fallback for maximum compatibility. All mutating operations require explicit user confirmation. Triggers include: “RDS,” “关系型数据库,” “数据库实例,” “慢SQL,” “SQL优化,” “数据库运维,” “数据库故障,” “故障排查,” “参数调优,” “备份恢复,” “数据库巡检,” “RDS诊断,” “数据库诊断,” “DBA,” “数据库性能,” “主从延迟,” “连接数,” “数据库备份,” “数据恢复,” “RDS智能服务,” “database instance,” “RDS troubleshooting,” “slow query,” “SQL performance,” “database backup,” “parameter tuning,” “RDS ops,” “database diagnose.”
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.