Каталог навыков агентов

Convert UI screenshots and designs to working code. Use when translating visual designs, mockups, or screenshots into HT...

A framework for translating high-level product vision into actionable goals and execution steps. Use this when defining...

Pipeline that turns a big system idea into briefs for an agent fleet. Use when Arman says 'let's plan out X', 'build or...

Transform a user's builder vision into a complete, executable GSD mission package. Use this skill whenever a user has de...

Diagnose and fix the agent's OWN image-understanding (vision_analyze) when it 404s or "can't see" a sent image. Covers d...

Guide for using vision utilities in speedy_utils, including fast GPU image loading, memory-mapped datasets, and notebook...

> Last Updated: 2026-01-26

Strategic AI council for product vision, creative direction, and long-term planning. Multiple perspectives from Strategi...

Strategic AI council for product vision, innovation, and future planning

visionOS platform-specific development with spatial computing, RealityKit, immersive spaces, and volumes. Use when build...

visionOS skills — spatial design (layout ergonomics, eyes-and-hands input, motion comfort, immersion, environments) and...

Apple Human Interface Guidelines for Apple Vision Pro. Use when building spatial computing apps, implementing eye/hand i...

visionOS spatial computing fundamentals for Vision Pro, including windows, volumes, immersive spaces, RealityKit integra...

visionOS widget patterns including mounting styles, glass/paper textures, proximity-aware layouts, and spatial widget fa...

Visit a webpage and extract its content as markdown, or fetch images. Use for reading articles, documentation, or any we...

Separate an algorithm from the object structure it operates on, allowing new operations without modifying the classes.

Automate Visme tasks via Rube MCP (Composio). Always search tools first for current schemas.

Evaluates whether text-to-image models correctly render spatial relationships between objects mentioned in a prompt. It...

Define visual identity — colors, typography, logo usage, and imagery style

Turn the current work into one polished, self-contained HTML visual page — a recap of a branch's changes, a plan, a map...

Generate on-brand visuals and infographics for LinkedIn posts and newsletters using Nano Banana MCP (Gemini AI image gen...

提供平面设计、UI交互、PPT美化及品牌调性升级指引。

Verify composed ChatCut edits, compare source frames, locate visual changes, and build labeled contact sheets using the...

Use when analyzing images, screenshots, UI mockups, or visual content for extracting information, comparing designs, or...

Defines the visual aspects of the game and how the player observes the world. This includes map color-coding, screen eff...

Transform research papers into professional visual schemas. Analyzes paper logic, selects optimal layout patterns, and g...

Critique a generated image against its source storyboard shot and prompt, producing revision notes. Use when the user ha...

Generate research visuals (figures, diagrams) with constraints, evidence alignment, and confidence ceilings.

Use when you need to generate production-ready visual assets for a project — app icons, favicons, OG images, logos, word...

This skill should be used when creating visual assets for educational content. It provides professional creative brief m...

Create and manage visual assets. Use when creating graphics, icons, or images. Covers asset formats and optimization.

시각 자료 관리 스킬. 제안서 스크립트에 이미지, 차트/그래프, 출처 인용을 추가하고 JSON으로 변환합니다. Gemini가 HTML 슬라이드에 시각 자료를 렌더링할 수 있도록 구조화된 데이터를 제공합니다. 트리거:...

Define purposeful visual asset strategy.

Perform adversarial visual audit of Quarto or Beamer slides checking for overflow, font consistency, box fatigue, and la...

Comprehensive visual design audit using agent-browser. Takes screenshots of every page across desktop/mobile viewports a...

Adversarial visual-layout audit of a Quarto `.qmd` or Beamer `.tex` deck. Flags overflow, font inconsistency, box fatigu...

Define and maintain a film or story project's visual language, moodboard briefs, palette, contrast, lighting logic, text...

Extract brand visual system from a website or brand assets into a structured style guide

Extract visual branding (colors, typography, layout patterns) from a client's website and generate a style preset compat...

Generate a polished, **self-contained HTML brief** of a topic — session status, a plan, or a code walkthrough — saved to...

Measure the longest stretch of a rendered clip with NO visual change (the union of jump-cut/zoom/b-roll cuts) via ffmpeg...

Read a render output (and optionally a reference) using Claude's multimodal capability and produce a short qualitative i...

Choose, build and check the visual for a reply or page meant for a person: a table, a collapsed evidence block, a callou...

[Frontend] Auto-activated visual-to-code component finder. Matches screenshots to Angular components with >=85% confiden...

Use when creating branded presentations or carousels. Generates museum-quality visual output from canvas philosophy, enf...

Designs and directs the visual assets that carry content — carousels, infographics, quote graphics, diagrams, and social...

When the user wants to plan, create, or repurpose visual content (images, infographics, social post images) across chann...

Generates detailed text descriptions of medical images and charts for accessibility and manuscript writing.

Diagnose why an existing implementation differs from reference evidence using AE/SSIM, pixel, section, computed-style, a...

Use for screenshot-driven frontend visual debugging and implementation tasks where a target page must match a reference...

视觉演示工坊——用HTML做高保真原型、幻灯片、动画、可视化与专家评审，需求模糊时给设计方向。触发词：做原型、PPT、幻灯片、动画、设计风格、评审、做个HTML页面、UI mockup、导出MP4/GIF、做个好看的。生产级Web App/...

Generate style guides, component mockups, and visual assets using AI (Gemini 3 Pro Image, FLUX.2 Pro). Optional feature...

Use when creating posters, covers, social graphics, or other static visual designs. Covers composition, typographic hier...

This skill should be used when the user asks to "create mermaid diagram", "add visuals to slides", "suggest stock photos...

Use when choosing or reviewing how a screen, flow, or page looks — colour palette, typography, spacing, cards and surfac...

Inspect AIgent Resolve screenshots with native vision, produce a structured evidence-backed aesthetic critique, connect...

Apply typography, color theory, spacing systems, and iconography principles to create cohesive visual designs. Use when...

Choose and apply high-quality frontend visual direction for websites, apps, dashboards, redesigns, landing pages, portfo...

Procedures for creating visual designs and mockups.

视觉设计工具箱 - Canvas / Themes / Design System / Artifacts。The unified Visual Design Engine for Antigravity.

Compare a baseline URL against a dev or Storybook URL by taking Playwright screenshots at multiple breakpoints, running...

Visually compare two states of a web page with iris — before/after a change on the same URL, or two different URLs (A/B,...

Use when the question is how pages render on one git ref versus another: checking a design-system, tokens, typography or...

Multi-dimensional visual scoring using pixel-diff and structural analysis for design-to-implementation comparison

Open a running local app in Agent-Native Design. Use for visual editing, responsive review, or source handoff.

Interpret and act on batched visual edit requests produced by the Design Tweak app. Use when the user references a visua...

One sentence - what this skill does and when to invoke it

The most important actions and content in a UI should be visually prominent — through size, colour, weight, and position...

Extend and apply the Visual Experience Engine across landing pages, inspiration galleries, and demos using safe, persona...

Generate comprehensive invocation documents for scroll-driven visual essays. Use when the user wants to create a visual...

Анализирует скриншот сайта или приложения как визуальное доказательство, определяет вероятный продукт и страницу, ищет о...

当浏览器自动化或网页抓取工具失效时，通过检索并分析历史执行中的截图或视觉缓存提取关键信息。

Capture and inspect concise before/after evidence for significant UI or design changes, store up to three WebP compariso...

Gorgeous/cinematic requirements every delivered app's UI must meet — anti-slop premium bar, exact brand tokens, motion,...

Explain concepts visually using ASCII diagrams, flow charts, tables, and structural maps. Use when asked to explain, com...

Generate self-contained HTML visual explanations for systems, code changes, plans, data, and technical concepts. Use for...

Generate strikingly well-designed, visually pleasing HTML diagrams and reports. Use when the user asks for a diagram, ar...

Generate self-contained HTML pages that visually explain systems, data stories, investigations, editorial workflows, and...

Generate beautiful, self-contained HTML pages that visually explain systems, code changes, plans, and data. Use when the...

Use when a page emitted by kivo-creator must be proved against its design - rendering the block markup on the local site...

Create animated flow diagrams from articles, workflow notes, architecture sketches, or process descriptions using a JSON...

Curated image generation assistant covering 17 styles across 4 categories: character figures, scenes, products, and styl...

Rank and group elements so the interface communicates what matters at a glance.

Master visual hierarchy through size, weight, contrast, and whitespace. Learn to establish clear information hierarchy w...

Plan visual and hybrid books such as picture books, comics, graphic novels, photo books, cookbooks, travel books, catalo...

Produce a coherent visual identity (palette, typography, spacing, radius) from a brief and serialise to JSON for the des...

Defines the visual language of the brand, including color palette, typography, logo usage, and imagery guidelines.

Provides visual identity direction and creative briefing frameworks including Alina Wheeler's five-phase process, strate...

把用户上传的 Logo、人物头像、个人形象、IP 角色、插画、产品照片或标志性物件，扩展成一套统一的视觉身份提示词。用户提到一张图做品牌全案、个人品牌视觉、头像延展、IP 设定、品牌主视觉、包装周边、社交媒体视觉，或要求保持参考图一致性生成...

Reproduce visual or interactive defects whose correctness depends on browser rendering, timing, viewport, input sequence...

Self-scoring visual feedback loop for web UI polish. Use when user says 'iterate on design', 'polish UI', 'make it look...

Makes the first-second visual, the on-screen text and the spoken words say the same thing, using footage the creator alr...

当用户搜索或询问餐饮菜单设计、菜单排版、电子菜单、餐厅价目表、AI设计、品牌视觉、商业图片时使用。围绕分类、菜品、规格、价格、过敏原提示、图片与点单动线，面向餐厅、火锅、奶茶、咖啡、外卖和团购交付设计策略、基础视觉规则、2—3个概念方向、应...

This skill should be used when the user asks to 'mockup the layout', 'sketch the diagram', 'show me the layout before co...

Guidance for working on Remotion Studio Visual Mode, sequence identity, node paths, symbolicated stacks, override IDs, a...

High-density industrial mold counting and inventory tracking using YOLOv8/v11.

Build a visual novel: a branching script, character and background display, a text box with choices, save/load, backlog,...

图文运营创作器。从选题、撰写、配图到质检，一条龙完成运营文章生产。看到好文章能仿写，给个 Skill 能生成推广长文，写完正文能自动配图。内置写作质量管控与自动配图能力，图文一体交付。触发词："生成运营文章"、"链接仿写"、"对标分析"、"...

Build a visual sequence that proves, explains, and supports decisions.

Generate beautiful self-contained HTML pages that explain any concept visually