Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Run and analyze molecular dynamics simulations with OpenMM and MDAnalysis. Set up protein/small molecule systems, define force fields, run energy minimization and production MD, analyze trajectories (RMSD, RMSF, contact maps, free energy surfaces). For structural biology, drug binding, and biophysics.
ORO GRAIL gold infrastructure for AI agents. Use when building agent integrations that involve: - Checking gold prices (via Pyth oracle) - Buying or selling gold (GRAIL tokens) - Managing user gold balances - Agent treasury/wealth features - Building fintech agents with gold savings, DCA, or rewards Based on Oro GRAIL API: https://docs.grail.oro.finance/
Step-by-step problem solving with detailed explanations. Uses structured approach (Identify, Plan, Execute, Verify) for math, physics, chemistry, and CS problems. Can provide hints before solutions. Use when solving academic problems, working through practice questions, or learning problem-solving methods. Triggers - solve problem, step by step, show work, explain solution, how to solve, problem help.
Vendor-agnostic lab automation framework. Use when controlling multiple equipment types (Hamilton, Tecan, Opentrons, plate readers, pumps) or needing unified programming across different vendors. Best for complex workflows, multi-vendor setups, simulation. For Opentrons-only protocols with official API, opentrons-integration may be simpler.
Cloud-based quantum chemistry platform with Python API. Preferred for computational chemistry workflows including pKa prediction, geometry optimization, conformer searching, molecular property calculations, protein-ligand docking (AutoDock Vina), and AI protein cofolding (Chai-1, Boltz-1/2). Use when tasks involve quantum chemistry calculations, molecular property prediction, DFT or semiempirical methods, neural network potentials (AIMNet2), protein-ligand binding predictions, or automated computational chemistry pipelines. Provides cloud compute resources with no local setup required.
Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.
Tiger Brokers (TigerOpen) — US/HK/A-share stocks. Account, positions, orders, quotes, history, and order placement (paper + live). Use when the user wants to check or trade a Tiger / 老虎证券 account (e.g. "Tiger account assets", "buy 100 700.HK on Tiger", "my Tiger positions"). Cloud API via the official tigeropen SDK, runs in the container.
Buy or sell XAUT (Tether Gold) on Ethereum. Supports market orders (Uniswap V3) and limit orders (UniswapX). Wallet modes: Foundry keystore or WDK. Delegates non-XAUT intents to registered skills (e.g. Polymarket prediction markets, Hyperliquid trading). Triggers: buy XAUT, XAUT trade, swap USDT for XAUT, sell XAUT, swap XAUT for USDT, limit order, limit buy XAUT, limit sell XAUT, check limit order, cancel limit order, XAUT when, create wallet, setup wallet, polymarket, prediction market, bet on, odds on, hyperliquid, perp, perpetual, long, short, open long, open short, close position, leverage.
DTC operations and supply chain — warehousing and logistics, inventory, 3PL, shipping times, suppliers, tariff costs. Triggers: 运营, operations, 供应链, 仓储, 物流, 库存, 3PL, 履约, 供应商, supply chain, fulfillment, inventory management, shipping times. Route complex questions through afa first.
Review board/stockholder resolutions for corporate authority, quorum, securities authorization, and execution. Triggers: (1) 'check resolutions' → checklist review, (2) 'advise' / 'review' → full consultation with playbook, (3) 'generate' / 'template' → Skala templates URL. Jurisdiction: Delaware, USA.
CHEETAH v7.0.0 — Multi-signal confluence sniper, senpi_runtime_helpers migration. Plumbing-only flip from openclaw-CLI subprocess + mcporter subprocess to in-process SenpiClient (direct HTTPS for MCP, direct HTTP POST to runtime /signals, long-lived producer_daemon). Thesis preserved verbatim from v6.1: refuses to trade unless ALL major signals align — SM consensus, velocity, acceleration, dual price confirmation, volume spike, quality-trader alignment, rank climb. Score 10/15 floor, score-scaled leverage (3x/5x/7x/8x), FEE_OPTIMIZED_LIMIT entries AND exits, held-asset dedup, post-close cooldown.
Assess an A-share portfolio company's AI readiness for China-focused private equity investments. Evaluates data infrastructure, technology stack, talent, and AI adoption opportunities in the Chinese market context. Triggers on "A股公司AI评估", "AI readiness China", "AI assessment portfolio company", "AI转型评估", or "artificial intelligence readiness [company]".
Tax-loss harvesting strategies for A-share portfolios. Adapts the original tax-loss-harvesting skill for Chinese tax rules, A-share market conventions, and domestic tax treatment. Triggers on "A股税务亏损抵扣", "亏损抵扣", "tax loss harvesting China", "税务优化", "亏损抵扣策略", or "harvest tax losses [portfolio]".
Diffusion-based docking that predicts protein-ligand poses without a predefined site. Use for blind docking, when traditional docking fails, or exploring multiple binding modes. Pipeline: prep protein (PDB) and ligand (SMILES/SDF), run inference, analyze confidence-ranked poses.
When the user wants to manage vehicle fleets, optimize fleet size, or plan vehicle acquisition and maintenance. Also use when the user mentions "fleet sizing," "vehicle lifecycle," "fleet utilization," "maintenance planning," "replacement strategy," "total cost of ownership," or "fleet optimization." For route planning within a fleet, see route-optimization. For last-mile operations, see last-mile-delivery.
Longbridge / LongPort (长桥证券) — US/HK/A-share stocks. Account, positions, orders, quotes, history, and order placement. Use when the user wants to check or trade a Longbridge / 长桥 account (e.g. "Longbridge balance", "buy 100 700.HK on Longbridge", "my 长桥 positions"). Cloud API via the official longport SDK, runs in the container.
Evaluate and manage suppliers using weighted scorecards across quality, delivery, price, and service dimensions. Use this skill when the user needs to assess supplier performance, compare vendors for selection, design a supplier rating system, or manage supplier development — even if they say 'which supplier should we choose', 'rate our vendors', 'this supplier keeps delivering late', or 'build a vendor evaluation system'.
Cross-chain bridging, swapping, and bridge+call via Relay through the OpenFinance backend. Use whenever the user wants to move tokens across chains, swap EVM same-chain with a token change, or run a destination-chain tx funded from another chain. `recipient` may be the caller's own wallet OR any external address — Relay treats them the same. Routing rule — SAME-chain transfer with NO token change → `openfin-onchain` POST /agent/onchain/send (faster, cheaper than a bridge). Solana SAME-chain swap (SPL ↔ SPL / wSOL) → `openfin-onchain` onchain_jupiter_order + onchain_jupiter_execute (native SPL routing, better pricing than Relay). Everything else (EVM same-chain swap with token change, any cross-chain) → Relay. Triggers — "bridge X from Y to Z", "move USDC to Base / Arbitrum / Optimism / Polygon / Solana", "swap ETH for USDC on Base", "cross-chain swap", "bridge and call", "how do I get to / back from Solana", "my USDC is stuck on Solana", "send USDC to 0x… on another chain", EVM↔EVM, EVM↔Solana, Bitcoin bridge, gas topup, native-token sentinel `0x0`, intent status. Covers POST /agent/relay/quote, POST /agent/relay/execute, GET /agent/relay/status. Includes the chainId cheatsheet (1/137/8453/10/42161/… and Solana 792703809), tradeType (EXACT_INPUT / EXACT_OUTPUT / EXPECTED_OUTPUT), why topupGas auto-disables on Solana routes, bridge+call (`txs` array). When the user names a token by symbol (not address), run the pre-swap checklist in `openfin-onchain` (resolve via /token/search on the destination chain, DexScreener link, mcap, warn-on-thin, confirm). Pair with openfin-setup (API key) and openfin-troubleshooting (Blockhash not found, Custom:101, 412 setup-incomplete on Solana origin).
ORCA v4.0.0 — Gen-1 Vanilla Striker, senpi_runtime_helpers migration. Plumbing-only flip from openclaw cron + mcporter subprocess to in-process SenpiClient + long-lived producer_daemon. Thesis preserved verbatim from v3.0: pure FIRST_JUMP detection + base Striker scoring + volume confirmation. DSL exit managed by plugin runtime via runtime.yaml.
Search Alaska Airlines flights and check Atmos Rewards balance from the terminal, with offline-cached airports and agent-native JSON output. Trigger phrases: `search alaska flights`, `atmos rewards balance`, `alaska shoulder dates`, `alaska airport lookup`, `use alaska-airlines`.
Use this skill to design new products, iterate on product ideas, or develop product specifications. Triggers: "design product", "new product idea", "product concept", "product development", "product spec", "iterate on product", "product design", "invention", "prototype spec", "product requirements", "product engineering", "develop product" Outputs: Product specification, BOM estimate, feature breakdown, differentiation analysis.
Capture snapshots from Xiaomi cameras. Use this skill when the user needs to view a Xiaomi camera live feed, get a camera snapshot, monitor camera footage, or mentions "Xiaomi camera", "camera snapshot", or "camera feed". Supports listing cameras, fetching an image from a specified camera, and custom file names.
API + Python SDK for ordering cell-free protein expression and binding assays. Submit sequences for expression (10–100 µg), measure binding affinity (KD) against targets, track status, and retrieve results programmatically — no wet-lab setup. Built for ML-guided directed evolution and antibody/nanobody optimization. Requires Adaptyv account and API key.
Predicts protein-ligand binding poses with DiffDock diffusion-based molecular docking from PDB structures and SMILES, producing pose confidence scores for virtual screening and structure-based drug design. Use when docking ligands into a protein, generating binding poses, or screening compounds against a target; not for binding affinity prediction. Part of the AlterLab Academic Skills suite.
Runs and analyzes molecular dynamics simulations with OpenMM and MDAnalysis — setting up protein and small-molecule systems, assigning force fields, running energy minimization and production MD, and analyzing trajectories (RMSD, RMSF, contact maps, free energy surfaces). Use when simulating protein or ligand dynamics, equilibrating a system, or computing trajectory metrics for structural biology, drug binding, or biophysics. Part of the AlterLab Academic Skills suite.
Apply Lean and Six Sigma principles to eliminate waste and reduce process variation. Use this skill when the user needs to improve operational efficiency, identify the seven wastes (TIMWOOD), run DMAIC improvement projects, or streamline workflows — even if they say 'our process is too slow', 'where are we wasting resources', or 'how do we reduce defects'.
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.