Claude Skills by artherahq

The generation-time discipline for an AI producing UI code — not a UI category (see `terminal-software-design` for dashboards, `conversational-ui-restraint` for chat) but the self-critique process that separates a considered design from a templated one. Trigger for "this looks AI-generated", "make this feel less generic/templated", "why does every AI-built page look the same", "make this look considered/deliberate", or — proactively — before finalizing any UI generation task, as a self-check ...

Validate whether a backtest result is trustworthy before drawing any conclusion from it. Trigger for "回测这个策略", "这个策略过拟合吗", "夏普这么高可信吗", "加上手续费还赚钱吗", "样本外表现", "validate this backtest", "is this strategy overfit", or whenever the user (1) presents or produces backtest results and wants a judgement, (2) asks whether an edge is real, (3) compares strategy variants and picks the best one, or (4) is about to deploy/paper-trade a strategy based on historical performance. Fire even when the user only ...

Validate a model/strategy governance manifest before it goes to a counterparty, investor, or internal reviewer doing real due diligence. Trigger for "尽调清单", "due diligence", "model governance", "compliance audit trail", "机构接入前会问什么", "这个系统靠不靠谱", "写一份治理文档", "risk control 真的在跑吗", "audit trail", "监管合规", or whenever the user is about to claim a system is validated/production-ready/risk-managed to someone outside the team, or is drafting the kind of document that answers "how is this validated, is ...

Build or review a chat/copilot/assistant interface — message list, composer, streaming responses, conversation sidebar, canvas/side-panel for structured output. Trigger for "make this chat UI look like ChatGPT/Claude", "为什么我的 对话界面看起来很乱", "streaming response feels janky", "conversation sidebar needs work", "this looks AI-generated", or when reviewing a chat/assistant screen before shipping it. This is a DIFFERENT problem than dense dashboards — a chat UI's job is to get out of the way of the c...

Produce comprehensive, evidence-backed public-equity research reports with market, filing, fundamental, valuation, technical, risk, catalyst, scenario, and source analysis. Use when the user asks for "全面分析报告", "股票研报", "深度分析公司", "完整个股分析", "comprehensive equity report", or requests analysis of a stock, company, or equity thesis with current auditable data.

Convert a trading signal into a sized, risk-gated PAPER order intent — or a refusal with reasons. Trigger for "这个信号该买多少", "帮我算仓位", "凯利公式下注多少", "现在要不要加仓", "position sizing", "how much should I buy", "simulate this trade", or whenever the user (1) has a signal/decision and asks for the size, (2) wants a trade checked against limits before acting, (3) asks about stops or exposure, or (4) another skill hands over a strategy/rebalance that needs execution shape. Fire even for casual "梭哈吗". Do NOT ...

Evaluate whether a cross-sectional factor genuinely predicts returns. Trigger for "这个因子有效吗", "算一下IC", "动量因子在A股还有效吗", "帮我评估这个选股信号", "factor IC", "is this signal predictive", "compare momentum vs value factors", or whenever the user (1) proposes or computes a ranking/score across assets and asks if it works, (2) asks which factor explains recent moves, (3) wants factors screened/ranked before building a strategy, or (4) hands a signal to strategy construction. Fire even for informal phrasing ("...

Compute or review a Gamma Exposure (GEX) / dealer-hedging-behavior estimate from options open interest before it gets reported as if it were an observed fact. Trigger for "GEX", "gamma exposure", "gamma squeeze", "gamma wall", "zero gamma flip", "dealer positioning", "做市商对冲", "伽马敞口", "波动率压制/放大", "0DTE flows", "净伽马", or whenever the user is inferring options-dealer hedging pressure from open interest and implied volatility, building a GEX chart/panel, or about to state a GEX regime call ("deal...

Pick a concrete visual direction for a website or app in a specific industry — which aesthetic, which palette, which font pairing, which page structure — from a library of 95 industry profiles, 57 defined styles, 96 palettes, 57 font pairings, and 30 landing structures. Trigger for "design a landing page for a dental clinic", "帮我设计一个餐厅网站", "what should a fintech app look like", "给这个 SaaS 产品定一套 配色和字体", "我要做一个电商网站，用什么风格", or whenever someone needs a starting direction for a product whose indust...

An alternate visual style for aria-code's own generated exports — report covers, PPTX title slides, single-chart share images, Canva one-pagers — built on heavy negative space, one accent color, and restrained serif/monospace type, instead of the default dense institutional/dashboard look. Trigger for "极简", "杂志风", "editorial", "zine", "less corporate", "make the cover page quieter", "one number, lots of white space", or when the user wants a report/deck/chart export that reads as considered r...

Compile a minimal editorial/zine-poster prompt for a theme, sentence, mood, or brief from ANY domain aria-code touches — a financial story, a real-estate listing highlight, a sports recap, a general subject — not tied to financial-report styling. Trigger for "做一张极简海报", "zine风格的海报", "minimal poster for [subject]", "给这个故事配一张海报", or when the user wants a standalone poster-style creative asset rather than a data export. Produces a ready-to-use image-generation prompt and, when an image backend is...

Correct for multiple hypothesis testing before calling any factor, sub-period, or parameter sweep "significant" — and check whether a claimed set of "independent" signals or bets is actually a smaller number of correlated ones wearing a disguise. Trigger for "测了8个因子哪个显著", "筛选因子", "factor screen", "parameter sweep", "which of these signals is real", "p-hacking", "data snooping", "统计显著性", "breadth", "多重检验", "这些信号真的独立吗", or whenever the user has run more than one significance test in a batch and...

Verify an operator's or tenant's self-reported revenue before it is used to settle a revenue-share, guarantee, or performance clause. Trigger for "核实流水", "商户流水是不是真的", "这个月分账对不对", "怀疑商户漏报流水", "能耗和流水对不上", "verify operator revenue", "tenant underreporting sales", "revenue share settlement check", or whenever a payout depends on a number the counterparty reported themselves. Do NOT trigger for public-market or securities analysis — declared-revenue verification for a private operator is a differe...

Enforce point-in-time data discipline for any quant research task. Trigger for requests such as "回测策略", "因子IC", "检查前视偏差", "量化选股", "验证夏普比率", or "point-in-time backtest". Also trigger this skill whenever the user: (1) backtests a strategy or factor, (2) asks for a Sharpe / alpha / IC / return — even as a quick one-liner ("just give me the Sharpe", "run this backtest"), (3) reviews or asks you to confirm / audit / validate quant or backtest code ("is my code PIT clean?", "confirm this is correct...

Produce defensible portfolio weights from return history, and check whether the optimizer earns its complexity. Trigger for "帮我优化组合权重", "风险平价配置", "怎么配这几只资产", "降低组合波动怎么调仓", "optimize my portfolio", "risk parity allocation", "rebalance weights", or whenever the user (1) holds several assets and asks how much of each, (2) wants lower volatility/drawdown via allocation, (3) asks equal weight vs something smarter, or (4) receives strategy signals that need converting into weights. Do NOT trigger f...

Decompose and judge the risk of a portfolio, strategy, or single position from its actual history. Trigger for "我的组合风险大吗", "最大回撤会有多深", "如果市场跌20%我亏多少", "该不该降仓", "组合太集中了吗", "portfolio risk", "VaR", "stress test my holdings", or whenever the user (1) holds or proposes a set of positions and asks how risky it is, (2) asks what a market drop would do to them, (3) asks whether to reduce/hedge/diversify, or (4) receives a strategy from another skill and needs its risk characterized before acting. Fi...

Turn approved footage, posters, charts, and image assets into a platform-ready short-form video package: edit plan, captions, publish copy, and delivery manifest. Use when creating social clips, product explainers, market recaps, or finance videos that need platform specifications, asset provenance, subtitle, and release checks.

Turn a natural-language trading idea into a disciplined, testable strategy spec and implementation. Trigger for "帮我生成一个动量策略", "写一个BTC均值 回归策略", "设计多因子选股", "做一个ETF轮动", "generate a momentum strategy", "build me a trading strategy", "turn this idea into code", or whenever the user (1) describes a trading idea and wants it made concrete, (2) asks for strategy code, (3) wants strategy variants compared, or (4) asks to improve an existing strategy. Fire even for vague asks ("有什么好策略推荐吗" — the answer ...

Build or review UI for a terminal, IDE, trading/data dashboard, admin/ops tool, or any dense data-driven desktop/web app — as opposed to a marketing site or landing page. Trigger for "review my sidebar", "why does this look unfinished", "dashboard feels too sparse/too dense", "Electron window has a weird line at the edge", "make this table easier to scan", "这个侧边栏要怎么改", "为什么这个终端界面看起来不对", or when reviewing a finished screen/component in one of these product categories before shipping it. Portab...

Build or review a trading/investing-app component against the specific conventions of X (timeline post, action bar), TradingView (watchlist row, technical rating gauge), or Trading212 (order ticket, holdings row). Trigger for "make this look like TradingView/X/Trading212", "watchlist row like TradingView", "order ticket like Trading212", "technical rating gauge", "做一个像 TradingView 一样的自选股列表", "参考 X 的帖子卡片样式", or when reviewing a finished component against one of these reference patterns before ...

Source the actual assets a website or app needs — icons, imagery, logos, avatars, empty-state art — without hallucinating SVG paths, shipping emoji as icons, or dropping in stock photos that fight the palette. Trigger for "what icons should I use", "给这个网站配图", "add icons to this UI", "generate a hero image for this landing page", "这个空状态要放什么插图", "need a logo for this brand", or whenever a design direction exists and the remaining gap is the visual material to fill it. Names which icon set fits ...

Help the user build and enforce *their own* design system — capture their brand/aesthetic decisions into a portable design-tokens.json, then keep every UI they generate consistent with it. Trigger for "帮我建立设计系统", "把我的品牌色定成规范", "make my UI consistent", "set up design tokens", "check this screen matches my design system", "为我的 app 定一套配色和圆角规范", "review my components against my tokens", or whenever the user is building UI and wants coherence across screens rather than one-off styling. Do NOT trig...

Replace this with one or two sentences that say exactly when to trigger the skill, in the words a user would actually use. Name the concrete situations. Add a "Do NOT trigger for …" clause if the skill is easy to over-fire. This field is the only thing the model sees when deciding whether to load the skill.