Agent Skillscalesthio/OpenMontage › visual-style

visual-style

GitHub

用于创建、提取和应用便携式视觉设计系统。支持从源头生成样式文件,或从网站/视频/PDF中提取风格,并可将其应用于HeyGen、Figma等工具,统一视觉语言。

.claude/skills/visual-style/SKILL.md calesthio/OpenMontage

触发场景

用户提及'visual style'、'design system'、'brand style'或'style guide' 需要为项目从头创建视觉风格指南 需要从URL、图片或视频中提取现有视觉风格 需要将定义好的视觉风格应用到具体设计工具中

安装

npx skills add calesthio/OpenMontage --skill visual-style -g -y
更多选项

非标准路径

npx skills add https://github.com/calesthio/OpenMontage/tree/main/.claude/skills/visual-style -g -y

不安装直接使用

npx skills use calesthio/OpenMontage@visual-style

指定 Agent (Claude Code)

npx skills add calesthio/OpenMontage --skill visual-style -a claude-code -g -y

安装 repo 全部 skill

npx skills add calesthio/OpenMontage --all -g -y

预览 repo 内 skill

npx skills add calesthio/OpenMontage --list

SKILL.md

Frontmatter
{
    "name": "visual-style",
    "description": "Create, extract, and apply portable visual design systems via visual-style.md files. Use when: (1) Creating a visual-style.md design system from scratch, (2) Extracting a visual style from a website URL, video, or PDF brand guide, (3) Applying a visual style to HeyGen videos, HTML slides, Figma, or paper.design, (4) Browsing the gallery of pre-built visual styles (Swiss, Saul Bass, Game Boy, etc.), (5) User mentions \"visual style\", \"design system\", \"brand style\", or \"style guide\", (6) Styling a HeyGen video with a consistent design language."
}

Visual Style

Create, extract, and apply portable visual design systems. A visual-style.md file defines colors, typography, layout, motion, and mood in one file that any AI tool can consume.

Quick Reference

Mode Trigger What it does
Create "Create a visual-style.md for..." Build a style from scratch via guided prompts
Extract "Extract a visual-style.md from [URL/image/video]" Analyze a source and generate a style file
Apply "Apply this visual-style.md to [tool]" Use a style with a specific connector
Gallery "Show me available visual styles" Browse and use example styles

Default Workflow

Create

  1. Gather vibe — Ask about mood, era, references, inspiration
  2. Define colors — Primary (2+), accent, neutrals with hex values and roles
  3. Set typography — Display, body, caption families + weight/style rules
  4. Layout & motion — Grid system, transitions, pacing
  5. Generate — Output complete visual-style.md using references/templates/minimal.visual-style.md or references/templates/full.visual-style.md
  6. Preview — Show a small HTML swatch or describe the visual result
  7. Optionally apply — Ask if user wants to use it with a connector

Questions to batch:

  1. What's the vibe? (mood keywords, era, references)
  2. Any specific colors? (or derive from the vibe?)
  3. Typography preference? (clean, editorial, technical, playful?)
  4. What tool will you use this with? (HeyGen, slides, paper.design, Figma?)

Extract

  1. Receive source — URL, image, video, or PDF
  2. Load extractor — Read the appropriate extractor reference file
  3. Analyze — Identify colors, typography, layout, motion, mood
  4. Generate — Output complete visual-style.md with source_url set
  5. Validate — Ensure all required fields are present

Apply

  1. Read the style — Load the visual-style.md file
  2. Ask which connector — Or detect from context
  3. Load connector — Read the appropriate connector reference file
  4. Transform — Map style fields to tool-specific format
  5. Generate output — Produce tool-ready instructions or code

Gallery

  1. List styles — Show available styles from references/gallery/
  2. Preview — Describe the selected style's visual character
  3. Load — Read the full visual-style.md
  4. Apply — Use with a connector

Format Quick Reference

Required fields

name: "Style Name"
version: "1.0"
style_prompt_short: "1-2 sentence elevator pitch"
style_prompt_full: "Detailed generation prompt — THE most important field"
colors:
  primary:
    - name: "Color Name"
      hex: "#000000"
      role: "how this color is used"

style_prompt_full is king. If a tool can only read one field, it reads this one. Everything else is structured data for tools that want finer control.

Full spec: references/spec.md

Reference Files

Connectors (Apply mode)

Connector Use case File
HeyGen Video Agent AI video generation references/connectors/heygen-video-agent.md
HTML Slides Web presentations references/connectors/html-slides.md
paper.design Design documents references/connectors/paper-design.md
Figma Design tool styles references/connectors/figma.md

Extractors (Extract mode)

Source File
Website URL references/extractors/from-website.md
Video keyframes references/extractors/from-video.md
PDF / Brand guide references/extractors/from-pdf.md

Gallery (pre-built styles)

Style Era File
Müller-Brockmann Swiss 1950s–70s references/gallery/mueller-brockmann-swiss.visual-style.md
Neville Brody Industrial Late 1980s–90s references/gallery/neville-brody-industrial.visual-style.md
Saul Bass Cinematic 1950s–60s references/gallery/saul-bass-cinematic.visual-style.md
Game Boy Color 1998–2003 references/gallery/game-boy-color.visual-style.md
HeyGen AI Video 2020s references/gallery/heygen-ai-video.visual-style.md

Templates & Spec

Best Practices

  1. style_prompt_full is king — Always usable as a standalone generation prompt
  2. One style, one file — No multi-style bundling
  3. Assets are URLs — Never embed binary data
  4. Show, don't tell — Generate previews when creating styles
  5. Opinionated defaults, flexible extensions — Core schema is fixed; x_* for tool-specific config

版本历史

  • 0af32ce 当前 2026-07-24 22:26

同 Skill 集合

.agents/skills/3d-asset-generation/SKILL.md
.agents/skills/acestep/SKILL.md
.agents/skills/agents/SKILL.md
.agents/skills/ai-video-gen/SKILL.md
.agents/skills/atlas-cloud/SKILL.md
.agents/skills/azure-speech-to-text/SKILL.md
.agents/skills/azure-text-to-speech/SKILL.md
.agents/skills/beautiful-mermaid/SKILL.md
.agents/skills/character-animation-qa/SKILL.md
.agents/skills/comfyui/SKILL.md
.agents/skills/create-video/SKILL.md
.agents/skills/d3-viz/SKILL.md
.agents/skills/dashscope/SKILL.md
.agents/skills/doubao-tts/SKILL.md
.agents/skills/elevenlabs/SKILL.md
.agents/skills/faceswap/SKILL.md
.agents/skills/ffmpeg/SKILL.md
.agents/skills/fish-audio-tts/SKILL.md
.agents/skills/flux-best-practices/SKILL.md
.agents/skills/framer-motion/SKILL.md
.agents/skills/grok-media/SKILL.md
.agents/skills/gsap-frameworks/SKILL.md
.agents/skills/gsap-performance/SKILL.md
.agents/skills/gsap-plugins/SKILL.md
.agents/skills/gsap-react/SKILL.md
.agents/skills/gsap-scrolltrigger/SKILL.md
.agents/skills/gsap-timeline/SKILL.md
.agents/skills/gsap-utils/SKILL.md
.agents/skills/heygen/SKILL.md
.agents/skills/hyperframes-cli/SKILL.md
.agents/skills/hyperframes-core/SKILL.md
.agents/skills/hyperframes-creative/SKILL.md
.agents/skills/hyperframes-registry/SKILL.md
.agents/skills/kling-official/SKILL.md
.agents/skills/lottie-bodymovin/SKILL.md
.agents/skills/ltx2/SKILL.md
.agents/skills/lyria/SKILL.md
.agents/skills/media-use/SKILL.md
.agents/skills/minimax-h3/SKILL.md
.agents/skills/music/SKILL.md
.agents/skills/playwright-recording/SKILL.md
.agents/skills/pose-library-design/SKILL.md
.agents/skills/remotion-best-practices/SKILL.md
.agents/skills/remotion/SKILL.md
.agents/skills/seedance-2-5/SKILL.md
.agents/skills/setup-api-key/SKILL.md
.agents/skills/sound-effects/SKILL.md
.agents/skills/speech-to-text/SKILL.md
.agents/skills/svg-character-animation/SKILL.md
.agents/skills/synthetic-screen-recording/SKILL.md

元信息

文件数
0
版本
cd9f3c1
Hash
4d6b51fa
收录时间
2026-07-24 22:26

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-08-29 23:19
浙ICP备14020137号-1 $访客地图$