设计技能

Applies the reasoning style of Kaiming He, computer vision pioneer and creator of ResNet. Use this skill whenever you are designing deep learning architectures, debugging neural network optimization, formulating generative AI problems, or bridging AI with other scientific domains. Trigger this skill for discussions on network depth, weight initialization, residual learning, flow matching, or when reframing discriminative tasks as conditional generation. It emphasizes simplicity in complex visual problems, end-to-end optimization, and viewing AI as a universal language for science.

中文简介正在准备中。当前显示原文说明。

Applies the rigorous deontological ethics, transcendental idealism, and political philosophy of Immanuel Kant (18th-century German philosopher, Critique of Pure Reason). Reach for this skill whenever the user is facing moral dilemmas, questions of duty, truth-telling, evaluating the limits of human knowledge, balancing civic obedience with free speech, or designing systems for global governance and peace. Use this skill to evaluate actions based on universalizability and human dignity rather than consequences, even if the user doesn't explicitly name Kant.

中文简介正在准备中。当前显示原文说明。

Use this skill whenever you are reasoning about public health policy, cancer prevention, epidemiological study design, clinical risk models, or weight management advice. This skill channels the thinking of Graham A. Colditz, epidemiologist at Washington University in St. Louis. Reach for this when evaluating lifestyle interventions, designing disease prevention programs, critiquing clinical prediction tools (e.g., AUC vs. clinical utility), or analyzing life-course risk accumulation. Apply his frameworks to bridge the "implementation gap" between scientific knowledge and societal action, prioritizing prevention over treatment and attainable weight maintenance over drastic weight loss.

中文简介正在准备中。当前显示原文说明。

Applies the behavioral genetics and twin-study methodologies of Dorret I. Boomsma (behavior geneticist, Vrije Universiteit Amsterdam). Use this skill when reasoning about heritability, genetic epidemiology, nature vs. nurture debates, psychiatric genetics, or longitudinal phenotyping. Trigger this whenever the user asks about the genetic basis of intelligence, lifestyle factors, educational attainment, or psychopathology, or when designing epidemiological studies. It helps deconfound environmental and genetic variables using extended family designs and discordant twin models.

中文简介正在准备中。当前显示原文说明。

Design rulebook and diagnostic layer for web UI, distilled from Refactoring UI by Adam Wathan and Steve Schoger. Use when building a new page or component, refining UI that looks off or amateurish, running a design review, or establishing design tokens (color shades, type scale, spacing scale, elevation, radius). Covers visual hierarchy, layout and spacing, typography, color and contrast, depth and shadows, images, and finishing touches, with Tailwind mappings throughout. Also triggers on non-English requests for the same things - for example Chinese: 页面/界面设计, 样式调整, UI 太丑, 设计评审, 视觉层级, 配色, 对比度, 间距, 排版, 阴影, 空状态, 设计规范, 设计系统. Not for backend logic, copy editing, or changes with no visual surface.

中文简介正在准备中。当前显示原文说明。

Suede-owned SMS and MMS marketing discipline. Use when evaluating SMS as a channel, designing consent-aware sequences, drafting messages, setting cadence, comparing number types or platforms, or defining measurement (TCPA consent, A2P 10DLC, quiet hours, cart-recovery and win-back texts. NOT FOR: email campaigns (use suede-emails), phone capture UX (use suede-site-alchemy), or legal certification) this skill does not give legal advice and never sends, schedules, imports, or registers.

中文简介正在准备中。当前显示原文说明。

Suede-owned referral and affiliate program discipline. Use when designing refer-a-friend mechanics, ambassador or partner incentives, fraud controls, attribution, payout logic, or viral-loop measurement. NOT FOR: executing payouts or changing billing, launch-wide packaging (use suede-launch-packaging), lifecycle messaging (use suede-emails), or reporting unverified referral lift.

中文简介正在准备中。当前显示原文说明。

Design, review, and visually QA web and app interfaces against explicit design laws so shipped screens look intentional instead of generic AI output.

中文简介正在准备中。当前显示原文说明。

Suede-owned prospecting and qualification discipline. Use when defining an ICP, sourcing and enriching a bounded lead list, finding early adopters or design partners, scoring account fit, or documenting disqualification evidence. NOT FOR: sending outreach (use suede-cold-email), changing CRM routing (use suede-revops), or profiling competitors instead of prospects (use suede-competitor-profiling).

中文简介正在准备中。当前显示原文说明。

Suede AI design skill for making an interface feel intentional instead of templated: design tokens, color strategy, OKLCH ramps, type scale, fluid type, visual hierarchy, dark mode, spacing, component laws, motion, and source-to-implementation visual QA. Use when asked to design, restyle, polish, or audit a screen; pick colors or fonts; define, fix, or document design tokens; build or repair a dark mode; review a component or a whole design system; or compare a mock, Figma frame, or reference screenshot against a rendered implementation. NOT FOR: a full design-plus-copy build, launch surface, or reference-to-target restyle (use johnny-suede-design); conversion and funnel architecture (use suede-site-alchemy); writing the words themselves (use suede-copy).

中文简介正在准备中。当前显示原文说明。

Suede AI CI and branch-protection wiring for any repo and any stack: path-aware jobs, a single aggregator required check that cannot deadlock, lockfile hygiene, runtime pinning from the repo, and the exact branch-protection settings. Use when asked to set up CI, protect main, make CI block a bad merge, fix a required check that hangs pending forever, or repair duplicate or misfiring pipelines. Detects the repo's real apps, package managers, and runtime versions first; emits workflow files and settings, never pushes or flips protection itself. NOT FOR: reviewing or grading the change the gate is failing on (use suede-code); designing the AI eval cases to wire in (use suede-ai-eval); branch and worktree hygiene (a private Suede Labs companion, not in this pack).

中文简介正在准备中。当前显示原文说明。

Suede AI full-stack surface builder that runs design, copy, and visual QA as one pass: landing pages, brand surfaces, product UI, dashboards, campaigns, launch pages, and reference-to-target restyles (suedify). Use when a build needs layout and words together, when a redesign or launch surface has to ship end to end, when the request is 'make this site look like that one', or when design, copy, asset, and QA lanes have to move at once. NOT FOR: a design-token, dark-mode, or single-component decision (use suede-design); copy with no layout work (use johnny-suede-write, or suede-copy for one standalone conversion surface); conversion and funnel architecture (use suede-site-alchemy); multi-agent orchestration protocols, WIP protection, and rollback trees (use suede-agent-teams).

中文简介正在准备中。当前显示原文说明。

Size, colour, weight and position mark what matters most. Use when designing button groups, CTAs, cards, dashboards or any layout with a primary action.

中文简介正在准备中。当前显示原文说明。

Guided multi-step paths and wizards. Use when designing onboarding, checkout, setup sequences or any multi-step journey.

中文简介正在准备中。当前显示原文说明。

Ratio-based type scale where every size relates to the others. Use when defining font sizes or type tokens, or when typography feels arbitrary.

中文简介正在准备中。当前显示原文说明。

Modals, drawers, bottom sheets and popovers, each with its scope and blocking level. Use when designing dialogs, confirmations, side panels or action sheets.

中文简介正在准备中。当前显示原文说明。

Pipeline from a URL or DESIGN.md to tokens, decisions and a UI spec. Use when building UI for an existing brand, auditing a design system or fixing visual inconsistency.

中文简介正在准备中。当前显示原文说明。

Extract colours, typography, spacing, components and W3C design tokens from a live website with Dembrandt. Use when you need a site's real tokens or want to seed a design system from it.

中文简介正在准备中。当前显示原文说明。

Settings for experts who are not developers — domain language, sane defaults, grouping by professional concept. Use when designing settings panels, solver configuration or constraint editors.

中文简介正在准备中。当前显示原文说明。

Rebuild a live web page 1:1 from measurement into Figma, Penpot or code, then verify it. Use when reproducing a page or checking a rebuild against the original.

中文简介正在准备中。当前显示原文说明。

Rest, hover, active, focus, disabled and loading states, derived from the base colour. Use when designing buttons, links, inputs or any clickable component.

中文简介正在准备中。当前显示原文说明。

Currency, language, region and unit selectors live in a low-profile header or footer spot. Use when designing locale switchers or product-wide preference controls.

中文简介正在准备中。当前显示原文说明。

Cards, drawers, carousels and other patterns borrowed from the physical world. Use when designing layout patterns, gestures or navigation paradigms.

中文简介正在准备中。当前显示原文说明。

Few semantic colours, each meaning one thing, and errors with a way forward. Use when designing status indicators, validation, alerts or error states.

中文简介正在准备中。当前显示原文说明。