Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Use to write one component's documentation entry from its code, stories and real call sites, such as "document the button", "write docs for Select", "what states does Toast have", or usage rules for a new or changed component. Not for foundations or pages that span components, which no skill here writes, nor for changing the component, which is build-design-system.
Your operations manager. Works out how the business actually runs on day one: suppliers and what they cost, who works when, the step-by-step routines for opening, serving or shipping and closing, the tools to run it, the licences and permits to check, and a risk register with what to do when each thing goes wrong. Feeds real costs back to the CFO. Use when the user says "how do I run this", "operations", "suppliers", "staffing", "SOPs", "what do I need to open", "permits", or "day one".
Generate an interactive single-file HTML visualization — mockup, wireframe, ERD, flowchart, chart, slides, architecture diagram, dashboard, timeline, mindmap, kanban, or table. Use when the user wants something rendered rather than described: a UI mockup or wireframe, a database schema as an ERD, business logic as a flowchart, data as a chart, or content as slides. Also use when they point at a file (schema, spec, data) and ask to see it visualized.
Generate a BYOD ownership preferences reference table for a customer. Walks through preference types, generates CSV, and provides upload instructions (UI, API, cloud storage, or Terraform). Use when asked about BYOD setup, preferences reference table, k9_ownership_preferences, or ownership customization.
Value investing screen via Longbridge — scan A-share / HK / US stocks for fundamentally strong but undervalued companies based on PE, PB, dividend yield, ROE, and margin of safety. Suitable for value investing strategy. Triggers: "低估值", "价值投资", "低PE", "低PB", "便宜股票", "安全边际", "高股息低估值", "被低估", "低估值", "價值投資", "低PE", "低PB", "便宜股票", "安全邊際", "高股息低估值", "value investing", "undervalued stocks", "low PE", "low PB", "margin of safety", "value screen", "cheap stocks", "bargain stocks".
Static UI mockups and wireframes on Moda: app screens, website pages, dashboard layouts — pictures of interfaces at real viewport sizes, exported png or pdf. Use for: mockup, wireframe, "design a screen/UI for X", app concept, page redesign concept. A mockup is a picture of an interface. NOT: a live hosted page → moda-website; flowcharts and boxes-and-arrows → moda-diagram.
When the user wants to handle pricing discussions, negotiate deal terms, or defend value against discounting pressure. Also use when the user mentions "pricing objection," "discount request," "negotiation," "value selling," "procurement," "contract terms," "deal structure," or "competitive pricing." For proposal writing, see proposal-writing. For competitive positioning, see competitive-selling
Implements and debugs browser Proofreader API integrations in JavaScript or TypeScript web apps. Use when adding Proofreader availability checks, monitored model downloads, proofread flows, correction metadata handling, or permissions-policy checks for built-in proofreading. Don't use for generic prompt engineering, server-side LLM SDKs, or cloud AI services.
Code commit, PR creation, merge, and issue closure workflow via GitHub CLI (gh). Triggers after a goal (GitHub Issue) implementation is complete — commit code, push branch, create PR, merge, then close the issue. Use when the user says "提交代码", "commit and merge", "创建PR", "合入", "关闭issue", "ship-it", or when a goal implementation is done and code needs to be shipped.
STM32 + FreeRTOS embedded development expert. Supports the full Cortex-M series, native FreeRTOS v10+ and CMSIS-RTOS v2 APIs. Use for creating tasks/queues/semaphores, integrating the standard library + HAL peripherals, memory optimization, low-power Tickless mode, STM32CubeMX configuration, and debug analysis (SEGGER SystemView / Percep TRACEalyzer).
Implements and debugs browser Translator API integrations in JavaScript or TypeScript web apps. Use when adding Translator support checks, language-pair availability flows, model download UX, session creation, translate() or translateStreaming() calls, input-usage measurement, or permissions-policy handling for on-device translation. Don't use for server-side translation SDKs, cloud translation services, or generic multilingual content pipelines.
Read, search, summarize, and triage AgentMail inboxes through the connected MCP server. Use for ANY request to look at, search, or process mail — even a simple 'search my inbox for X' or 'any new mail?'; the read workflow applies regardless of task size. Also use to summarize conversations, inspect attachments, manage read/unread labels, or find messages needing a reply; do not use for sending or drafting (agentmail-send-email), inbox administration (agentmail-manage-inboxes), or MCP connection setup (agentmail-mcp).
Turn backend test ambiguity into one practical backend test packet. Use when the user needs API/service/repository/auth-flow coverage design, fixture or seed/reset strategy, container-vs-mock dependency choices, contract/API compatibility checks, or flaky backend-suite stabilization across local and CI.
Command-line interface for CloudAnalyzer — an agent-friendly harness for CloudAnalyzer, a QA platform for mapping, localization, and perception outputs. Supports 27 commands across 8 groups: point cloud evaluation, trajectory evaluation, ground segmentation QA, config-driven quality gates, baseline evolution, processing, visualization, and interactive REPL.
When the user wants to create or optimize a sales outreach sequence, follow-up cadence, or prospecting campaign. Also use when the user mentions "outreach sequence," "follow-up cadence," "prospecting campaign," "drip sequence," "touch pattern," or "outbound sequence." For individual email writing, see copywriting.
Create code-driven software product promos and release videos (product promo, release notes video, changelog promo). Set the direction based on real features and product design, then produce each video with real components, GSAP/Three.js animation, original music, and motion sound effects. Derive each video’s visual approach from the product itself rather than using templates.
Analyst EPS estimate time series for a listed stock via Longbridge — tracks how the consensus EPS forecast (high / low / mean / median / analyst count) has changed over time, and shows actual values where reported. Answers "have analysts been raising or cutting their estimates?" Complements longbridge-consensus (current snapshot) by focusing on the historical revision trajectory. Triggers: "分析师预测历史", "EPS预测趋势", "一致预期变化", "预期上调下调", "分析师预期轨迹", "分析师EPS", "预测时间序列", "分析師預測歷史", "EPS預測趨勢", "一致預期變化", "預期上調下調", "分析師EPS", "analyst estimate history", "EPS estimate trend", "consensus revision history", "estimate time series", "analyst forecast trajectory", "EPS upgrade downgrade history".
DeFi yield analysis framework — lending rates (AAVE / Compound), liquidity provision (LP) returns, staking yields, yield farming strategies, and risk-adjusted return comparison. Longbridge provides spot crypto prices (`.HAS` suffix) only; DeFi protocol data (APY/TVL) requires DefiLlama/CoinGecko via WebSearch. Triggers: "DeFi收益", "流动性挖矿", "质押收益", "借贷利率", "收益农耕", "LP收益", "AAVE", "Compound", "DeFi协议", "DeFi收益率", "流動性挖礦", "質押收益", "借貸利率", "收益農耕", "DeFi yield", "liquidity mining", "staking yield", "lending rate", "yield farming", "LP returns", "DeFi APY", "TVL", "DeFi protocol", "on-chain yield", "DeFi strategy".
Hedging strategy design framework — Beta hedge ratio (portfolio vs benchmark), option protection strategies (protective put / collar), tail-risk hedges (VIX-related / gold / treasuries), cross-asset hedges (currency risk), and hedge cost assessment (option premium vs protection value). Triggers: "对冲", "对冲策略", "Beta对冲", "保护性看跌", "领口策略", "尾部风险", "汇率对冲", "对冲比率", "對冲", "對冲策略", "Beta對冲", "保護性看跌", "領口策略", "尾部風險", "hedging", "hedge strategy", "beta hedge", "protective put", "collar strategy", "tail risk hedge", "currency hedge", "hedge ratio", "portfolio insurance".
Industry / sector panorama report — generates a comprehensive industry overview covering market dynamics, competitive landscape, key players, thematic trends, valuation ranges, and catalysts/risks. Outputs industry sizing, growth rate, major-player market share estimates, and valuation bands. Triggers: "行业概览", "行业报告", "板块报告", "行业全景", "竞争格局", "行业分析", "板块分析", "行業概覽", "行業報告", "板塊報告", "行業全景", "競爭格局", "industry overview", "sector overview", "industry report", "sector analysis", "market landscape", "competitive landscape", "industry sizing", "sector deep dive", "semiconductor industry", "AI sector overview".
Implied volatility analysis for options via Longbridge — IV vs HV comparison, IV percentile rank, volatility smile and skew, options pricing assessment, strategy selection guidance. Triggers: "隐含波动率", "IV", "期权波动率", "波动率偏斜", "波动率微笑", "HV", "历史波动率", "IV百分位", "期权定价", "隱含波動率", "期權波動率", "波動率偏斜", "波動率微笑", "歷史波動率", "IV百分位", "期權定價", "implied volatility", "IV percentile", "volatility smile", "volatility skew", "HV vs IV", "options pricing", "vol surface", "TSLA.US implied vol".
Portfolio rebalancing via Longbridge — analyse weight drift (current vs target), generate a rebalance trade list, factor in transaction costs and tax impact, and output buy/sell recommendations with rationale. Triggers: 再平衡, 组合再平衡, 仓位调整, 目标权重, 权重偏移, 配置调整, 再平衡交易, 組合再平衡, 倉位調整, 目標權重, 權重偏移, 配置調整, rebalancing, portfolio rebalance, target weight, weight drift, allocation adjustment, rebalance trades, drift threshold.
Valuation methodology framework covering absolute (DCF / DDM / SOTP) and relative (PE-Band / PB-ROE / EV-EBITDA / PS) approaches — when to use each, pros/cons, common pitfalls, and practical application with Longbridge data. Triggers: "估值方法", "估值方法论", "DCF", "DDM", "SOTP", "PE估值", "EV/EBITDA", "绝对估值", "相对估值", "估值框架", "估值方法論", "絕對估值", "相對估值", "valuation methodology", "DCF model", "DDM", "SOTP", "PE band", "EV EBITDA", "absolute valuation", "relative valuation", "valuation framework".
macOS system migration assistant — two phases: first collect an inventory (JSON) on the old system, then restore it on the new system. Use when the user mentions system migration, switching computers, a fresh system install, Time Machine restore, data migration, reinstalling the system, migration, setup new mac, restore from backup, or system backup. Automatically detects whether the current system is the old one (collection mode) or the new one (restore mode). Prerequisite: make a full Time Machine backup first; Homebrew is the only software dependency.
Use when an app has to move onto a design system that already exists, such as "migrate the app to our design system", "move every screen onto the new components", a rollout, or an adoption audit. Not for making the system or for swapping raw values for tokens, which are build-design-system.
Moda meta, setup, and routing — the contract every moda skill assumes. Use for: install or update, auth and org/team switching, "what can Moda do?", which moda skill handles X, troubleshooting a failed Moda call, and any Moda ask no other moda skill clearly owns. Never for creating or editing an artifact — a matching format skill always wins.
This is the main on-chain DeFi skill. Use it for ALL of the following:\nStrategy discovery: 'how to make money on-chain', 'any profitable strategies', '链上有什么赚钱机会', '有什么盈利机会', '有什么套利机会', '怎么赚钱', '有什么好的策略', '帮我理财', '有什么收益机会', 'yield opportunities', 'how to earn', 'investment strategy', 'DeFi 策略推荐', '有什么自动化策略', 'automated strategies', 'passive income on-chain', '链上怎么赚币', '怎么玩链上', '怎么玩DeFi', '链上有什么玩法', '有什么赚钱项目', '推荐一些策略'.\nPlugin/project discovery: 'Plugin商店有什么', '有什么Plugin', '有什么项目', '什么项目最火', '最热门的项目', '有哪些工具', '推荐一些项目', 'what plugins are available', 'show me plugins', 'what projects are hot', 'trending projects', 'plugin marketplace', 'Plugin市场', '有什么好用的Plugin'.\nCapability discovery: '你能做什么', '你有什么能力', '你支持什么', '有什么技能', '都有什么功能', '支持哪些策略', '支持哪些 skill', 'what skills are available', 'what can you do', 'what strategies do you support', 'show me all strategies', 'list all skills'.\nDApp discovery: 'what dapps are available', 'any good dapps', '有什么好的dapp', '推荐一些dapp', 'recommend dapps', 'show me dapps', 'which protocols can I use', '有什么好的协议', '有什么DeFi协议', '推荐DeFi项目', '有什么链上应用'.\nPlugin management: 'install a plugin', 'uninstall a plugin', 'list plugins', 'search plugins', 'update plugins', 'show installed', '安装Plugin', '卸载Plugin', '更新Plugin'.\nPlugin development: 'I want to create a plugin', 'how to submit a plugin', '我想开发一个Plugin', '怎么提交Plugin', '如何贡献', 'contribute a plugin', 'build a plugin', 'create a skill', '创建Plugin', '开发Plugin', 'hackathon', 'submit my project', '提交我的项目'.\nAlso activates when the skill has just been installed and the user has not yet chosen a direction.
Use when an RFP, RFI, RFQ or security or vendor questionnaire arrives. Parses mandatory vs weighted requirements with rfp_parser.py, drafts proof-point answers with response_drafter.py and estimates win chance with winrate_predictor.py
An SEO agent skill for quick, lightweight, default single-page SEO audits. Performs basic on-page and site-level checks and outputs a structured basic SEO audit report. Use when the user asks for "SEO audit", "SEO check", "check my page SEO", "page analysis", or wants a first-pass review of a URL. If the user requests "deep audit", "full report", "technical SEO audit", or "advanced SEO", use seo-audit-full instead.
Upgrade Solidity smart contracts using OpenZeppelin proxy patterns. Use when users need to: (1) make contracts upgradeable with UUPS, Transparent, or Beacon proxies, (2) write initializers instead of constructors, (3) use the Hardhat or Foundry upgrades plugins, (4) understand storage layout rules and ERC-7201 namespaced storage, (5) validate upgrade safety, (6) manage proxy deployments and upgrades, or (7) understand upgrade restrictions between OpenZeppelin Contracts major versions.
Implement or review a Remotion 5 breaking change while the v4 and v5 release lines still share code. Use when v4 behavior and public types must remain compatible on main, but flipping the central v5 flag should activate a new runtime behavior, default, or TypeScript API.
Add volumetric underwater god rays to a Three.js scene, marching one drifting swell field along every view ray at half resolution so the light shafts converge on the sun, parallax with the camera and carry rippling caustic streaks, with a shimmering surface underside, a sun that wobbles through the ripples, and the same light dappling fish as they swim through the beams. Use for underwater scenes, oceans seen from below, aquariums, reefs, kelp forests, diving and shipwreck scenes, schools of fish, sunbeams or light shafts through water, caustics, "rays of light shining through the ocean", or watery ripples on a background. Includes a reusable module and the Blue Hour sardine-school demo.
Use Gemini Omni Flash Preview through AnyCap for practical short-video editing workflows. Trigger when a user wants to edit or refine an existing video with natural-language instructions, especially product replacement, object removal or replacement, relighting, restyling, preserving a person/scene while changing one element, or using reference images with a source video. Covers model/schema discovery, prompt construction, AnyCap CLI command patterns, scenario-specific templates, video QA, and retry strategy for `gemini-omni-flash-preview` / `edit-video`
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.