Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Data & databases
Integrate Firecrawl `/map` into product code for URL discovery on a known site. Use when a feature needs to find pages before scraping or crawling, especially on large docs sites, blogs, or help centers where the exact target URLs are not known yet.
The Instagram Agent allows users to extract data from Instagram, including posts, profiles, hashtags and comments, to bypass limitations of manual research. Use this skill when the user needs Instagram Agent via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.
Retrieves, versions, and publishes scientific datasets with DataLad and git-annex, and captures computational provenance with datalad run, rerun, and containers-run. Use when cloning or fetching data from OpenNeuro, DANDI, datasets.datalad.org, or any DataLad dataset; when a file in a dataset reads as a broken symlink or a small pointer instead of real data; when an analysis needs a machine-readable record of how each output was produced so it can be re-executed; or when publishing a dataset to siblings such as a GitHub repository plus a storage remote. Also use to decide between DataLad and plain Git for a data-carrying repository.
Structured metadata search for Basic Memory: query notes by custom frontmatter fields using equality, range, array, and nested filters. Use when finding notes by status, priority, confidence, or any custom YAML field rather than free-text content.
Read Hyperliquid (app.hyperliquid.xyz) perp and spot market data through opencli and Hyperliquid's public info API: mark, oracle, and mid prices, 24h change, funding rates (hourly and annualized APR), open interest, volume, the L2 order book, OHLCV candles, funding history, and cross-venue funding comparisons (Hyperliquid vs Binance vs Bybit) for funding arbitrage. Use this skill whenever the user mentions Hyperliquid (HL, HL DEX, hyperliquid.xyz) or asks about its perps, spot pairs such as PURR, funding, open interest, order book, or candles. Read-only market data: no account, order, or transfer operations.
Call the Recoupable API from the sandbox to fetch artist data, socials, organizations, research, documents and any other platform resource — and to invoke external connector actions (Google Docs / Drive / Sheets edits, Gmail, TikTok, Instagram, etc.) via Recoupable's shared connections. Use whenever you're asked for Recoup data, a Recoupable platform resource, or to read/write something outside Recoup like a Google Doc URL or a spreadsheet. Triggers on phrases like "look up artist", "fetch from recoup", "artist data", "artist socials", "organizations", "artist report", "research", "create new artist", "create artist", "onboard artist", "add artist", "edit this Google Doc", "read this doc", "update the spreadsheet", "send an email", "post on TikTok", "save to Drive", or whenever the user pastes a docs.google.com / drive.google.com / sheets.google.com URL. Always load this before writing curl calls against api.recoupable.com.
Vector search with SurrealDB using HNSW indexes, KNN queries, and similarity scoring. Use when creating vector indexes, querying vectors with KNN distance operators, building semantic search or RAG pipelines, tuning HNSW parameters (EFC, M, M0, distance function, type), or implementing recommendation systems with SurrealDB. Triggers: HNSW, vector, embedding, KNN, cosine, euclidean, semantic search, RAG, vector::distance.
This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on strict analysis bundles, not Results-section prose.
Protocol-driven study screening for systematic, scoping and rapid reviews. Turns a proposal or PROSPERO protocol into confirmed eligibility rules, then screens titles/abstracts and full texts with two blinded AI reviewers and a third-reviewer adjudicator: ordered exclusion codes, no silent defaults, resumable batch runs, QC (seed studies, near-miss rechecks, kappa and PABAK), PRISMA 2020 counts, EndNote/Zotero RIS groups, an Excel log, a methods draft and a literature_corpus handoff to academic-paper. Reads RIS, PubMed .nbib, Web of Science and CSV exports; removes duplicates. 8 modes: protocol, quick, pilot, ta-screen, ft-screen, adjudicate, audit, report. Use it to screen records against eligibility criteria, pilot screening, resolve screening conflicts, audit exclusions or report the selection process. Triggers on: screen these papers, title/abstract screening, full-text screening, screening conflicts, inclusion criteria, PRISMA flow, غربالگری مقالات, اسکرینینگ عنوان و چکیده, معیارهای ورود و خروج.
Chan theory pattern recognition — automatically detects top and bottom fractals, strokes (up/down strokes), segments and central zones, and generates first, second and third buy signals and first, second and third sell signals. Depends on the czsc library. Triggers:
Full three-statement financials (IS / BS / CF) for listed companies via Longbridge — income statement, balance sheet, cash flow statement; annual / semi-annual / quarterly periods. Use this skill to fetch raw financial data. For deep analysis (DuPont, accruals, fraud flags) use longbridge-financial-analysis; for health scoring use longbridge-financial-checkup. Triggers: "财务报表", "三张表", "利润表", "资产负债表", "现金流量表", "三表模型", "季报", "年报", "财报数据", "財務報表", "三張表", "利潤表", "資產負債表", "現金流量表", "三表模型", "季報", "年報", "財報數據", "financial statements", "income statement", "balance sheet", "cash flow statement", "three financial statements", "annual report data", "quarterly financials", "TSLA.US financials", "700.HK balance sheet".
Shanghai-Shenzhen-Hong Kong Stock Connect capital flow analysis — tracks northbound (foreign capital buying A-shares) and southbound (mainland capital buying HK stocks) net flows, sector allocation, and AH-premium arbitrage signals. Triggers:
Comprehensive equity research snapshot — integrates analyst consensus estimates, company fundamentals (revenue / profit / valuation), 60-day price history, and recent major news to produce an investment research snapshot similar to a sell-side equity research brief. Triggers: "股票研究", "个股分析", "研究报告", "个股快照", "综合分析", "股票调研", "股票深度", "個股分析", "研究報告", "個股快照", "綜合分析", "股票研究", "stock research", "equity research", "stock analysis", "research snapshot", "investment brief", "stock deep dive", "comprehensive analysis", "NVDA research", "700.HK analysis".
Analyze LLM experiment results. Handles single or comparative experiments, exploratory or Q&A modes. Use when user says "analyze experiment", "compare experiments", "analyze against baseline", or provides one or two experiment IDs for analysis.
Company fundamentals via Longbridge — latest financial report KPIs (revenue / net income / EPS / ROE / margins / cash flow), YoY trends, dividend history, forward EPS consensus, analyst ratings, corporate actions. Three depth tiers (snapshot / standard / full). Triggers: "基本面", "业绩", "财报", "财务健康", "盈利能力", "营收", "净利润", "ROE", "毛利率", "分红历史", "EPS 预期", "研报评级", "業績", "財報", "財務健康", "毛利率", "分紅歷史", "fundamentals", "financials", "earnings report", "EPS forecast", "analyst rating", "ROE", "gross margin", "free cash flow", "dividend history", "company report".
Constructs deep-links and URLs for the AlphaGenome Atlas website. Supports generating single-variant exploration links (1-based VCF-style coordinates), genomic locus views (1-based closed chr:start-end), candidate summary tables, and AlphaGenome reference vs. alternate predictions. Use when visualizing, exploring, charting, or linking genetic variants and genomic loci on the AlphaGenome Atlas, or when asked to inspect, view, or link predictions for a genomic variant. Don't use for computing raw AlphaGenome variant predictions directly without Atlas URLs (use alphagenome-single-variant-analysis or alphagenome-variant-impact-score).
Generate grounded, verified, engine-agnostic database documentation with 100% parity with the actual schema. Introspects the live database as the source of truth and cross-validates against ORM models, migrations, generated types, seeds, and application queries, then proves completeness by diffing the documentation against the database. Produces ER diagrams (Mermaid), per-table data dictionaries, and a machine-readable schema.json. Works with PostgreSQL, MySQL, SQL Server, and SQLite with any ORM (Prisma, TypeORM, Drizzle, Sequelize, Knex, Django, Rails) or raw SQL. Use to document a database, produce an ERD or data dictionary, write db/schema docs, audit schema drift, or refresh existing DB docs.
Score, annotate, and analyze the functional impact of genetic variants using AlphaGenome Variant Impact (AVI) scores. Query variants in chr:pos:ref>alt format, annotate VCF/tabular callsets, perform saturation mutagenesis window scans (1-based closed chr:start-end), and extract GENCODE v46 GTF gene/exon/junction coordinates all via the AlphaGenome Atlas API.
Understands the Metabase Representation Format — a YAML-based serialization format for Metabase content (collections, cards, dashboards, documents, segments, measures, snippets, transforms, actions, and data apps). Use when the user needs to create, edit, understand, or validate Metabase representation YAML files, or when working with Metabase serialization/deserialization (serdes). Covers entity schemas, MBQL and native queries, visualization settings, parameters, and folder structure
Retrieves ClinGen gene-disease validity assertions for a public gene or disease, and reviews source-linked public evidence and literature for one supported GRCh38 germline nuclear SNV or simple indel through Folklore Clinical Variant Interpretation MCP. Used when a scientific agent must branch deterministically on resolved, ambiguous, not-found, invalid, unsupported, or unavailable variant outcomes; chain a resolved public variant into related literature or publication details; or preserve evidence provenance without accepting patient, phenotype, family, segregation, or private case data
A/H premium ratio for Mainland-Chinese companies dual-listed in Hong Kong and A-shares (e.g. 939.HK / 601398.SH, 1810.HK / 600519.SH-pair) via Longbridge Securities — historical premium time series (kline) or today's intraday premium curve. Only HK-side symbols of dual-listed pairs return data. Triggers: "AH 溢价", "A H 溢价率", "AH 折价", "AH 价差", "工行 AH", "建行 AH", "比价", "A 股贵还是港股贵", "AH premium", "A/H premium", "AH ratio", "AH 溢價", "A H 溢價率", "AH 折價", "AH 價差", "比價", "A 股貴還是港股貴", "dual listed premium", "Hong Kong A-share premium", "premium ratio", "939.HK", "1398.HK", "600519.SH 对应港股".
Fundamental factor stock screening — filter value or growth stocks using PE, PB, ROE, revenue growth, net-profit growth, and dividend yield across A-share, HK, and US markets. Outputs a candidate table ranked by composite factor score. Triggers: "基本面筛选", "因子选股", "价值选股", "成长选股", "低PE选股", "高ROE", "股息筛选", "PE筛选", "PB筛选", "多条件选股", "基本面因子", "量化选股", "基本面篩選", "因子選股", "價值選股", "成長選股", "低PE選股", "股息篩選", "factor screening", "value screen", "growth screen", "low PE filter", "high ROE screen", "dividend screen", "fundamental factor", "multi-factor stock screen".
Sector-rotation snapshot across A-share, HK, and US markets — point-in-time multi-factor scoring of momentum, capital flow, and valuation to rank sectors by current cycle strength. For ongoing 6–12 month cycle positioning and allocation recommendations use longbridge-sector-monitor. Triggers: "行业轮动", "板块轮动", "行业动量排名", "强势板块", "弱势板块", "行业资金流", "板块涨幅榜", "行業輪動", "板塊輪動", "行業動量排名", "強勢板塊", "弱勢板塊", "行業資金流", "板塊漲幅榜", "sector rotation", "sector momentum ranking", "leading sector", "lagging sector", "sector capital flow", "sector strength ranking".
In-depth financial statement analysis for listed companies via Longbridge — cross-statement reconciliation (IS↔BS↔CF), DuPont decomposition (ROE = net margin × asset turnover × equity multiplier), earnings-quality scoring (accrual ratio), and a 10-item financial fraud red-flag checklist. Builds on the raw data from longbridge-financial-report. Triggers: "三表勾稽", "杜邦分析", "杜邦拆解", "盈利质量", "应计利润", "财务造假", "财报深度", "财务红旗", "三表分析", "財務深度", "三表勾稽", "杜邦分析", "盈利質量", "應計利潤", "財務造假", "財報深度", "財務紅旗", "DuPont analysis", "accrual ratio", "earnings quality", "financial fraud red flags", "cross-statement reconciliation", "three-statement analysis".
Market anomaly scanner and price-by-volume distribution via Longbridge Securities — `anomaly` lists unusual price/volume movements across a market (HK / US / CN / SG) or for a specific symbol; `trade-stats` returns a single stock's intraday price-volume profile (where volume sat in the day's range). Read-only. Triggers: "异动", "今天哪些股票异动", "市场异动榜", "成交分布", "价格分布", "筹码分布", "今日筹码", "成交密集区", "盘中异动", "拉升", "跳水", "閃崩", "異動", "今天哪些股票異動", "市場異動榜", "成交分佈", "價格分佈", "籌碼分佈", "今日籌碼", "成交密集區", "盤中異動", "拉昇", "跳水", "anomaly", "unusual movements", "intraday alerts", "volume spike", "price spike", "price by volume", "trade distribution", "volume profile", "VWAP zone", "where the volume sat", "TSLA anomaly", "700.HK anomaly".
Execute read-only SQL queries against multiple Microsoft SQL Server databases. Use when: (1) querying MSSQL/SQL Server databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety.
The Amazon Agent is a high-performance tool designed to turn massive e-commerce datasets into structured, usable intelligence. Use this skill when the user needs Amazon via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.
Managed vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Low latency (<100ms p95). Use for production RAG, recommendation systems, or semantic search at scale. Best for serverless, managed infrastructure
Cross-symbol comparison (2–5 stocks) via Longbridge — valuation (PE / PB / PS / dividend yield), current price + change, latest financial KPIs (revenue / net income / ROE), market cap. Renders as a single matrix; flags cross-currency or cross-industry caveats. Triggers: "X 和 Y 哪个值得买", "X vs Y", "几只股票对比", "同行业谁最强", "X 跟 Y 谁更便宜", "几只哪个增速快", "科技七姐妹谁最强", "X 跟 Y 對比", "X 跟 Y 哪個便宜", "X vs Y", "compare X and Y", "peer comparison", "which is more expensive", "which has higher growth".
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.