Skills
97,501 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Use a Bayesian intrinsic-growth valuation model to evaluate whether a company's market value sufficiently, excessively, or insufficiently prices its real 3-5 year growth. Use when the user asks for Bayesian valuation, intrinsic growth rate, implied growth, growth-hypothesis probabilities, FOMO versus fundamentals, or company analysis based on fundamentals, industry cycle, TAM, market share, margin, valuation multiples, and new information.
Portfolio rebalancing analysis for A-share wealth management portfolios. Analyzes allocation drift, generates rebalancing trades, and optimizes for tax efficiency. Adapted from the original portfolio-rebalance skill for Chinese portfolios. Triggers on "A股组合再平衡", "调仓", "rebalance China", "portfolio rebalance A-share", "rebalance portfolio", or "adjust allocation [client]".
IRR and MOIC analysis for China-focused private equity and investment funds. Adapted from the original returns-analysis skill for RMB/USD fund structures, China market conventions, and Chinese portfolio companies. Triggers on "A股基金回报", "IRR分析", "returns China", "MOIC analysis China", "基金业绩分析", or "portfolio returns review".
Use the Docyrus Architect MCP tools to manage data sources, fields, enums, apps, custom queries, and query data in the Docyrus platform. Use when the user asks to create, update, delete, or query data sources, fields, enum options, apps, or custom query templates via the docyrus-architect MCP server. Also use when building reports, dashboards, or performing data analysis that requires querying Docyrus data sources or running custom SQL templates with filters, aggregations, formulas, pivots, or child queries.
Protein language models (ESM3, ESM C) for sequence generation, structure prediction, inverse folding, and embeddings. Design novel proteins, extract ML features, or fold sequences. Local GPU or EvolutionaryScale Forge API. Use AlphaFold for traditional folding; RDKit for small molecules.
This skill should be used when the user asks to analyze SQL Server execution plans, .sqlplan files, ShowPlan XML, actual vs estimated plans, plan warnings, or operator costs. PROACTIVELY activate for: .sqlplan triage, ShowPlan XML inspection, high-cost operator ranking, scan vs seek review, residual predicate analysis, CONVERT_IMPLICIT warnings, bad row estimates, cardinality-estimation warnings, partition elimination verification, missing-index suggestions, unused-index warnings, spills, key lookups, sorts, hash joins, and plan-regression evidence gathering. Provides: plan triage workflow, operator-cost ranking heuristics, warning interpretation rubric, and rewrite/index recommendation gating.
Conducting systematic, scoping, and narrative literature reviews. Covers PRISMA/PRISMA-ScR protocols, search strategy (Boolean, MeSH), database selection (PubMed, Scopus, Web of Science, Embase), screening, data extraction, evidence synthesis (narrative, meta-analysis, thematic), and reporting. Use when planning or executing a formal literature review.
Analyze MD trajectories from GROMACS, AMBER, NAMD, CHARMM, LAMMPS. Reads topology/trajectory into Universe objects; supports RMSD, RMSF, radius of gyration, contact maps, H-bonds, PCA, and custom distance/angle calculations. Use for post-simulation structural analysis; use OpenMM/GROMACS for running simulations.
MySQL relational database. Covers queries, indexes, and optimization. Use when working with MySQL databases. USE WHEN: user mentions "mysql", "mariadb", asks about "AUTO_INCREMENT", "ON DUPLICATE KEY UPDATE", "GROUP_CONCAT", "mysql specific syntax" DO NOT USE FOR: PostgreSQL - use `postgresql` instead, MongoDB - use `mongodb` instead, Oracle - use `oracle` instead, SQL Server - use `sqlserver` instead
Analyze a Materialize environment via the MCP Developer endpoint, and/or configure an MCP client (Claude Code, Cursor, VS Code, Zed, Continue, Windsurf, Claude Desktop) to connect to the materialize-developer server. For analysis: check environment health, investigate performance, troubleshoot stale materialized views, diagnose memory pressure, find paused clusters holding back compaction, audit resource utilization, run EXPLAIN ANALYZE on user objects, and get optimization recommendations. For client connection: configure/connect/set up an MCP client to materialize-developer (Emulator, Cloud, or self-managed), control which user/role is used, and switch between identities. Trigger even if the user just says “check my environment,” “why is my MV stale,” “why is my cluster slow,” “what can I optimize,” “explain analyze my materialized view,” “how do I connect Claude Code to materialize-developer,” or “configure Cursor for the Materialize MCP.”
Tidy an OXYGEN Table: inspect duplicate columns, ordering, formatting, types, hide/archive candidates, and suspicious values; present findings by category; then apply only approved reversible fixes. This is table structure and cell formatting, not CRM record deduplication or merge.
Best practices for building performant, testable PySpark ETL pipelines with Spark SQL and Apache Iceberg. Use when writing or reviewing PySpark jobs, designing joins and window functions, working with map/array higher-order functions, or building idempotent cumulative/snapshot table merges.
This skill MUST be used when the user wants to infer product attributes from review files, score product quality, and deliver a Word (.docx) report, or explicitly requests review-scoring-docx. Triggers include 「評論評分 Word」、 「產品屬性比較報告」 with Word output, and reviews-to-scores-to-docx. It SHOULD be used for review-based product comparisons whose agreed deliverable is Word. It MUST NOT force Word output for general review analysis or substitute quality scores for attribute salience.
ScyllaDB CQL data modeling patterns and anti-patterns, including compaction strategy choice, TTL-based expiration, tombstone management, and lightweight transactions. Use when designing tables, reviewing schemas, migrating from SQL or MongoDB, setting data retention, troubleshooting performance issues caused by schema problems or deletes, or writing conditional (LWT) statements. Vector and full-text indexes go to scylladb-vector-search; DynamoDB API tables go to scylladb-alternator. Triggers on "design schema", "ScyllaDB data model", "partition key", "clustering column", "primary key", "CQL table design", "ALLOW FILTERING", "large partitions", "hot partitions", "query-first design", "secondary index", "materialized view", "schema review", "wide partition", "tombstones", "time series", "BATCH", "paging", "fetch size", "TTL", "default_time_to_live", "compaction strategy", "TWCS", "gc_grace_seconds", "tombstone_gc", "LWT", "lightweight transaction", "IF NOT EXISTS", "LOCAL_SERIAL"
Google SEO APIs: Search Console (Search Analytics, URL Inspection, Sitemaps), PageSpeed Insights v5, CrUX field data with 25-week history, Indexing API v3, and GA4 organic traffic. Provides real Google field data for Core Web Vitals, indexation status, search performance, and organic traffic trends. Use when user says "search console", "GSC", "PageSpeed", "CrUX", "field data", "indexing API", "GA4 organic", "URL inspection", "google api setup", "real CWV data", "impressions", "clicks", "CTR", "position data", "LCP", "INP", "CLS", "FCP", "TTFB", or "Lighthouse scores".
Use when you need to turn supplied social performance data into a decision about what to keep, test, change, or stop. Trigger phrases include "report on this campaign", "what worked on social?", "analyse these post results", "make a weekly social report", and "what should we do next from these metrics?". Do not use this to invent data access, claim causation from a dashboard, or replace a campaign brief; use campaign-brief to define success before launch and launch-retrospective for the broader after-action review.
Use when you need to turn a supplied set of comments, DMs, reviews, community posts, or call notes into an evidence-backed picture of what people ask, resist, and repeat. Trigger phrases include "what are people saying about this?", "mine these comments", "what language should we use?", "find recurring objections", and "summarise this community feedback". Do not use this to scrape platforms, infer demographics, or write positioning from a handful of anecdotes; use agent-reach to collect public evidence first, audience-personas to group people, and positioning-audit to decide the message.
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries. Use when debugging slow queries, designing database schemas, or optimizing application performance.
Implements the Syncfusion dotnet Calculate Library for parsing and evaluating formulas using CalcEngine, ICalcData, CalcQuickBase, and ExcelLikeComputations. Supports formula computation, custom functions, cross-sheet references, and XlsIO formula evaluation. Trigger when implementing formula calculations, expression parsing, workbook formula evaluation, or custom function registration.
Time-series database implementation for metrics, IoT, financial data, and observability backends. Use when building dashboards, monitoring systems, IoT platforms, or financial applications. Covers TimescaleDB (PostgreSQL), InfluxDB, ClickHouse, QuestDB, continuous aggregates, downsampling (LTTB), and retention policies.
Use when the user needs to WRITE a marketing report someone else will read — a one-page weekly for a CEO, a full monthly, or a quarterly strategy report with TL;DR, results versus target, insight, decisions needed, and next actions with owners. Trigger on 'marketing report', 'monthly report', 'weekly update for my boss', 'report for the client', 'quarterly summary', 'turn these numbers into a report'. Also use when the user says a stakeholder is asking how marketing is doing. Not for — diagnosing why the numbers are bad, see `03-performance-eval-global`; turning a raw export into insight, see `13-data-analysis-global`; a closed campaign retrospective, see `63-campaign-retrospective-global`.
Transform Claude Code into an AI Scientist that orchestrates research workflows using tree-based hypothesis exploration. Triggers on "research project", "scientific experiment", "run experiments", "AI scientist", "tree search experimentation", "systematic study".
Query ChEMBL (2M+ compounds, 19M+ bioactivity measurements, 13K+ targets) via the public REST/JSON API with plain `requests` — no SDK install required. Search compounds, retrieve IC50/Ki/EC50 bioactivities, find target inhibitors, run SAR, access drug mechanism/indication data.
Screen and evaluate A-share investment opportunities. Adapts the original deal-screening skill for Chinese market data sources, A-share screening criteria, and domestic deal origination. Triggers on "A股标的筛选", "标的筛选", "screening China", "deal screening A-share", "筛选投资标的", or "screen for [criteria]".
Accretion/dilution and merger consequences analysis for A-share M&A transactions. Adapted from the original merger-model skill for Chinese GAAP, CAS accounting, and China market transaction structures. Triggers on "A股并购分析", "并购模型", "accretion dilution China", "merger model A-share", or "M&A consequences [company]".
Audit multi-tenant data isolation — tenant model fit (shared rows vs schema vs database), missing or unenforced tenant scoping, the tenant_id-leading composite index/key requirement, and cross-tenant leak risk where queries or constraints omit the tenant boundary. Module M9. Feeds both the Design & Integrity (Seguridad) and Performance & Scale (Escala) scores.
Guides DBeaver usage for database connection management, SQL development, data import/export, and ER diagram generation across MySQL, PostgreSQL, Oracle, MongoDB, and other databases. Use when the user needs to configure DBeaver connections, write queries in the SQL editor, export data, or generate ER diagrams.
Parse, convert, chunk, and analyze documents using Docling. Use this skill when the user provides a document (PDF, DOCX, PPTX, HTML, image) as a file path or URL and wants to: extract text or structured content, convert to Markdown or JSON, chunk the document for RAG ingestion, analyze document structure (headings, tables, figures, reading order), or run quality evaluation with iterative pipeline tuning. Triggers: "parse this PDF", "convert to markdown", "chunk for RAG", "extract tables", "analyze document structure", "prepare for ingestion", "process document", "evaluate docling output", "improve conversion quality".
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.