Skills
99,951 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Company tear sheet / one-pager via Longbridge Securities — generates a high-density 1–2 page company snapshot: business overview, key financials (revenue / net income / EPS / ROE), valuation multiples (PE / PB / EV-EBITDA), price performance, major shareholders, and recent catalysts. Triggers: "公司单页", "公司快照", "公司简报", "公司画像", "一页纸分析", "公司概要", "股票简报", "公司單頁", "公司快照", "公司簡報", "公司畫像", "一頁紙分析", "company tearsheet", "company profile", "company snapshot", "one-pager", "company brief", "stock summary", "company factsheet".
Multi-asset correlation and cointegration analysis via Longbridge Securities — computes Pearson / Spearman return correlation matrix for 2–10 symbols, rolling 60-day correlation, Engle-Granger cointegration (ADF unit root), and spread half-life (AR(1) estimate). Used for portfolio decorrelation and pairs-trading pre-screening. Triggers: "相关性", "协整", "相关系数", "相关矩阵", "滚动相关", "去相关", "多标的相关", "相關性", "協整", "相關係數", "相關矩陣", "滾動相關", "去相關", "correlation", "cointegration", "correlation matrix", "rolling correlation", "Pearson", "Spearman", "decorrelation", "multi-asset correlation", "ADF test", "相关分析", "相關分析", "pairwise correlation".
Trade execution modelling framework (backtesting analysis only) via Longbridge — covers slippage models (linear / square-root market impact), VWAP/TWAP execution logic, market impact cost estimation (Kyle lambda), volume participation rate (POV) strategy. Helps quant traders build realistic execution assumptions in backtests. Triggers: "执行模型", "滑点模型", "VWAP执行", "TWAP执行", "市场冲击", "执行成本", "成交量参与率", "交易执行", "執行模型", "滑點模型", "VWAP執行", "TWAP執行", "市場冲擊", "執行成本", "交易執行", "execution model", "slippage model", "VWAP", "TWAP", "market impact", "execution cost", "volume participation rate", "Kyle lambda", "square root model", "POV strategy".
Institutional research and analyst ratings — buy/hold/sell distribution, consensus price target, EPS/revenue forecasts, and rating change history. ESG and credit ratings are not available via Longbridge. Triggers: "研报评级", "机构评级", "买入评级", "目标价", "机构观点", "分析师推荐", "券商评级", "机构研究", "研��評級", "機構評級", "買入評級", "目標價", "機構觀點", "分析師推薦", "券商評級", "analyst rating", "institution rating", "buy rating", "price target", "broker recommendation", "analyst opinion", "research rating", "sell-side rating", "consensus target", "EPS forecast", "analyst consensus".
SEC 13F fund-manager–centric view via Longbridge — top-50 active institutional investors by AUM, a specific manager's full portfolio snapshot (by CIK), and quarter-over-quarter holding changes (NEW / ADDED / REDUCED / EXITED). US stocks only. Different from longbridge-flows (stock-centric: who holds a symbol); this skill is manager-centric. Triggers: "基金经理持仓", "机构持仓排名", "大基金持仓", "巴菲特持仓", "贝莱德持仓", "13F基金视角", "基金经理排名", "AUM排名", "季度持仓变化", "基金經理持倉", "機構持倉排名", "大基金持倉", "13F基金視角", "季度持倉變化", "fund manager holdings", "institutional investor", "13F portfolio", "Berkshire holdings", "BlackRock positions", "fund manager ranking", "AUM ranking", "quarterly position changes", "CIK lookup".
On-chain data analysis framework — covers active addresses, whale behaviour, TVL (total value locked), DEX liquidity, and on-chain valuation metrics: MVRV (market cap / realised value), NVT (network value / transaction volume), SOPR. Longbridge provides spot crypto quotes (.HAS); raw on-chain data requires external sources (Glassnode / Dune Analytics). Triggers: "链上数据", "链上分析", "MVRV", "NVT", "活跃地址", "鲸鱼地址", "TVL", "SOPR", "链上指标", "链上估值", "鏈上數據", "鏈上分析", "活躍地址", "鯨魚地址", "鏈上指標", "鏈上估值", "on-chain data", "on-chain analysis", "MVRV ratio", "NVT ratio", "active addresses", "whale activity", "TVL", "SOPR", "on-chain valuation", "DeFi TVL", "crypto on-chain".
Options P&L analysis via Longbridge — payoff diagrams, breakeven points, max profit/loss, and Greeks sensitivity (Delta/Gamma/Theta/Vega) for single-leg and multi-leg strategies. Triggers: "期权盈亏", "盈亏图", "盈亏平衡", "最大亏损", "最大盈利", "Greeks敏感性", "Delta", "Gamma", "Theta", "Vega", "多腿组合", "期权到期", "期權盈虧", "盈虧圖", "盈虧平衡", "最大虧損", "最大盈利", "Greeks敏感性", "多腿組合", "options payoff", "P&L diagram", "breakeven", "max profit", "max loss", "Greeks sensitivity", "delta gamma theta vega", "multi-leg options".
Options strategy framework via Longbridge — covered call, protective put, straddle, strangle, bull spread, bear spread selection and comparison based on market view and IV level. Triggers: "期权策略", "备兑开仓", "保护性看跌", "跨式策略", "宽跨式", "牛市价差", "熊市价差", "期权组合", "卖出期权", "买入期权", "期權策略", "備兌開倉", "保護性看跌", "跨式策略", "牛市價差", "熊市價差", "期權組合", "options strategy", "covered call", "protective put", "straddle", "strangle", "bull spread", "bear spread", "options combination".
Build, serve, and call end-to-end typesafe APIs with oRPC v2. Use for any task in a project that depends on `@orpc/*` packages, even a one-procedure change: defining procedures with the os builder (.input/.output/.handler, any Standard Schema validator), assembling routers, middleware and context, typesafe errors with ORPCError, serving via RPCHandler on any runtime adapter, calling from server-side clients (call, createRouterClient) or client-side clients (createORPCClient with RPCLink), integrating TanStack Query, or streaming over SSE. Pretrained oRPC knowledge describes v1 and is wrong for v2, so load this skill even when the change looks trivial. Biases toward retrieval from the oRPC docs over pre-trained knowledge. For REST/OpenAPI exposure, prefer the orpc-openapi skill; for contract-first design, the orpc-contract skill; for tRPC or oRPC v1 migrations, the orpc-migrate skill.
Use when performing security audits, vulnerability assessments, or compliance checks on Flutter or mobile applications. Covers OWASP Mobile Top 10 (2024) — hardcoded secrets (M1), insecure storage (M9), weak cryptography (M10), network issues (M5), and 6 more categories with automated scanners and remediation guidance
Use for search evaluation, a POC or bake-off, Parallel vs Exa/Tavily comparisons, SimpleQA/DeepSearchQA benchmarks, or diagnosing search evaluation results. For product selection use choose-your-parallel-api; for integration migration use migrate-to-parallel.
Publish oh-my-opencode to npm by triggering the GitHub Actions publish workflow and verifying its artifacts. Ship-only: never runs pre-publish-review or re-reviews merged code unless the user explicitly asks. Argument: <patch|minor|major|explicit-semver>. Triggers: publish, release, deploy, npm publish
When the user wants to improve their ability to quickly identify who's worth pursuing in sales. Also use when the user mentions "qualifying prospects," "lead scoring," "identifying good fits," "wasting time on bad leads," "qualification criteria," or "is this worth pursuing"
Use when building a Unity 6.3 level or open world: terrain from code or heightmaps, procedural islands, erosion, splat and foliage rules, trees and grass, ProBuilder graybox, level gym, modular kit and prefab placement, set dressing, landmarks and player guidance, the island's edge, spline roads, WFC, fog, additive scene streaming, or a world that hitches, pops in, leaks memory or runs slow on mobile. Keywords: Terrain, TerrainData, ProBuilder, blockout, graybox, modular kit, NavMesh, LoadSceneAsync, open world.
Extract and document someone's authentic writing voice from samples. Use when someone needs a "voice guide," wants to capture their writing DNA, or needs to train AI to write in their style. Also useful for ghostwriting, brand voice documentation, or onboarding writers.
WeChat Pay medical insurance payment (mobile medical insurance payment 2.0) integration solution, covering the full chain of medical insurance and self-pay mixed ordering, order query, medical insurance refund notification, and medical insurance payment callback, with five capabilities: solution selection, sample code, business quick reference, quality assessment, and troubleshooting. Use when the user mentions "医保支付", "移动医保支付2.0", "医保自费混合", "医保电子凭证", "医保混合收款", "医保退款通知", "医保挂号", "医保诊间支付", "医保住院结算", "医保药店购药", "互联网医院医保", "医保定点机构", or asks to "接入医保支付", "要医保下单接口示例代码", "排查医保支付问题".
Build type-safe LLM applications with DSPy.rb — Ruby's programmatic prompt framework with signatures, modules, agents, and optimization. Use when implementing predictable AI features, creating LLM signatures and modules, configuring language model providers, building agent systems with tools, optimizing prompts, or testing LLM-powered functionality in Ruby applications.
Design and implement beautiful, fluid Liquid Glass interfaces in Expo React Native apps. Covers four paths: (1) expo-glass-effect for UIKit-backed glass surfaces, (2) @expo/ui SwiftUI integration for native SwiftUI glass modifiers and advanced transitions, (3) Expo Router unstable native tabs for system Liquid Glass tab bars, and (4) @callstack/liquid-glass as a third-party alternative. Use when tasks mention "liquid glass", "glass effect", "frosted/translucent UI", "iOS 26 design", "native tabs", "expo-ui", "SwiftUI in Expo", or when shipping Apple-style glass with robust fallbacks, accessibility checks, HIG-aware design decisions (Foundations, Patterns, Components, Inputs), and cross-platform degradation.
Process user-provided patent figures and generate formal drawing descriptions. Use when user says \"附图处理\", \"figure description\", \"附图说明\", \"drawings description\", or wants to describe patent figures with reference numerals.
Opens a lesson screen in the browser next to the terminal while a course tutor teaches. It shows the lesson's registered figures, code traces with real values, and clickable predictions. It also builds a figure for the lesson on the fly with the course figure skills and any figure skill the host has installed: a blueprint, a mechanism, an isometric machine, or a 3D model. Clicks return to the tutor as events. Trigger phrases: "open the lesson screen", "show me this visually", "show this in 3D", "draw the architecture", "visualize this lesson", "build a figure for this lesson", "lesson screen".
Create high-performing LinkedIn posts and content strategy. Use when the user says “LinkedIn post”, “write for LinkedIn”, “LinkedIn content”, “LinkedIn strategy”, “LinkedIn hook”, “professional post”, “thought leadership post”, or asks about creating content specifically for LinkedIn.
Cross-market financial metrics batch query — revenue, net profit, ROE, debt ratio, free cash flow, gross margin for one or more symbols across HK / US / A-share / SG markets. Supports multi-symbol horizontal comparison, similar to natural-language financial screening. Triggers: "财务数据查询", "财务指标", "营收查询", "净利润查询", "ROE查询", "负债率", "现金流查询", "毛利率查询", "财务数据批量", "財務數據查詢", "財務指標", "營收查詢", "淨利潤查詢", "ROE查詢", "負債率", "現金流查詢", "毛利率查詢", "financial data query", "revenue query", "net profit query", "ROE query", "debt ratio", "free cash flow", "gross margin query", "financial metrics", "financial comparison", "batch financials".
FX carry-trade analysis via Longbridge Securities — combines spot rates, interest-rate differentials (high-yield vs low-yield currencies), volatility, and historical price trends to assess carry opportunities. Analyses common carry pairs (AUD/JPY, NZD/USD, MXN/JPY) and outputs carry yield, drawdown risk, and Sharpe ratio. Triggers: "外汇套息", "套息交易", "carry trade", "利差交易", "高息货币", "低息货币", "汇率套利", "外汇策略", "外匯套息", "套息交易", "利差交易", "高息貨幣", "低息貨幣", "匯率套利", "FX carry trade", "carry strategy", "interest rate differential", "high yield currency", "currency carry", "AUD JPY", "NZD USD".
Investment proposal generation via Longbridge Securities — produces a structured investment memo covering: executive summary, company overview, investment thesis (3–5 core points), financial analysis, valuation, catalysts and timeline, risk factors, and position recommendation. Triggers: "投资提案", "投资建议书", "投资报告", "投资摘要", "核心逻辑", "投资理由", "建仓建议", "投資提案", "投資建議書", "投資報告", "投資摘要", "核心邏輯", "建倉建議", "investment proposal", "investment memo", "investment summary", "investment rationale", "position recommendation", "investment case", "buy memo".
Share structure and shareholder query — total shares, circulating shares, restricted shares, top-10 shareholders (circulating and total), major institutional holders, controlling shareholder / beneficial owner relationships. Shareholder count and pledge data are not available via Longbridge; check filings for those. Triggers: "股本结构", "前十大股东", "流通股东", "实控人", "股权结构", "主要持股人", "大股东", "股东查询", "股本結構", "前十大股東", "流通股東", "實控人", "股權結構", "主要持股人", "大股東", "shareholder structure", "major shareholders", "top 10 shareholders", "controlling shareholder", "share structure", "institutional holders", "beneficial owner", "ownership structure", "free float".
Account-level profit and loss analysis via Longbridge Securities — simple return, time-weighted return (TWR), per-symbol P&L breakdown, and P&L by market. Supports custom date ranges. More focused on performance attribution than longbridge-portfolio. Requires login. Triggers: "盈亏分析", "账户盈亏", "时间加权收益", "TWR", "投资回报率", "持仓盈亏", "分市场盈亏", "业绩分析", "收益率分析", "盈虧分析", "賬戶盈虧", "時間加權收益", "投資回報率", "持倉盈虧", "profit analysis", "P&L analysis", "time-weighted return", "TWR", "account performance", "holding P&L", "profit by market", "investment return analysis", "我账户赚了多少", "我的亏损", "我賺了多少", "我的虧損".
Quantitative statistics framework for time-series analysis using Longbridge price data — ADF unit root test (stationarity), cointegration (Engle-Granger / Johansen), GARCH volatility modelling (conditional heteroskedasticity), regression diagnostics (Durbin-Watson / Breusch-Pagan), bootstrap confidence intervals, hypothesis tests (t-test / F-test). Requires statsmodels and scipy. Triggers: "量化统计", "ADF检验", "单位根", "协整检验", "GARCH", "自相关", "异方差", "Bootstrap", "假设检验", "量化統計", "ADF檢驗", "單位根", "協整檢驗", "異方差", "假設檢驗", "quantitative statistics", "ADF test", "unit root", "cointegration", "GARCH", "autocorrelation", "heteroskedasticity", "bootstrap", "hypothesis test", "statsmodels".
Seasonality and calendar-effect strategy via Longbridge Securities — uses historical OHLCV data to compute month-of-year returns (January Effect), day-of-week returns (Monday / Friday effect), pre/post-holiday drift, and earnings-season effect; identifies statistically significant patterns and generates trading signals. Triggers: "季节性", "日历效应", "月份效应", "周一效应", "年初效应", "节假日效应", "财报季效应", "时间模式", "季節性", "日曆效應", "月份效應", "周一效應", "年初效應", "節假日效應", "財報季效應", "seasonality", "calendar effect", "January effect", "day of week effect", "holiday effect", "earnings season effect", "seasonal pattern", "time series anomaly", "月度效应", "月度效應", "monthly seasonality".
Investment thesis tracker — maintains and updates the investment thesis for portfolio holdings and watchlist names by continuously tracking key data points (revenue growth, gross margin, user metrics), catalyst progress (new products, expansion, policy), and risk milestones, then renders a verdict on whether the thesis still holds. Triggers: "投资逻辑", "Thesis追踪", "投资假设", "逻辑验证", "跟踪持仓", "买入逻辑", "持仓理由", "投資邏輯", "Thesis追蹤", "投資假設", "邏輯驗證", "追蹤持倉", "investment thesis", "thesis tracking", "investment hypothesis", "thesis validation", "thesis check", "investment rationale", "position monitoring", "thesis intact", "is my thesis still valid".
Operate Manta-managed worktrees, folder contexts, terminals, repos, automations, artifacts, skill sharing, worktree comments, and Manta's embedded browser through the `manta` CLI. Use when the user says "$manta-cli", "Manta worktree", "child worktree", "spawn codex/claude in a worktree", "read/wait/send Manta terminal", "handoff" / "handover" / "give this to another agent", "Manta browser", "manta artifacts", or "share skills". Prefer it over raw git worktree, ad hoc PTYs, or Computer Use when Manta state is involved. Use Computer Use only when a visible window needs GUI control that a CLI, filesystem, or API cannot do.
React composition patterns that scale. Use when refactoring components with boolean prop proliferation, building flexible component libraries, or designing reusable APIs. Triggers on tasks involving compound components, render props, context providers, or component architecture.
Use when building or fixing game UI in Unity 6.3: main menu, settings screen (resolution, quality, volume, key rebinding), HUD, health bar, minimap frame; choosing uGUI or UI Toolkit or mixing both; “UI scales wrong on phones”, portrait to 4K, Canvas Scaler, anchors, layout groups collapsing, sort order, UXML/USS, data binding, TextMeshPro or UI Toolkit fonts missing glyphs, localized menus, gamepad navigation, UI draw calls, canvas rebuild spikes, UI tests, or capturing UI to check it.
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
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.