Token导航 LogoToken导航

Agent Skill · 研究检索

paw-cra-design-brand(Paw cra 设计品牌)

用于辅助界面设计、视觉规范、排版、配色、布局和交互体验优化。它适合让 Agent 根据产品场景整理页面结构、生成 UI 方案、检查视觉一致性或改进组件层级。使用时需要结合现有品牌、设计系统和用户任务,不应只堆装饰元素;涉及真实页面改动时,应通过截图或浏览器预览检查文本溢出、对齐和响应式表现。

paw-cra-design-brand 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为接触敏感数据;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 55,679。

总安装 470周安装 20GitHub Stars 25下载 165核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:paw-cra-design-brand(Paw cra 设计品牌)
来源仓库:https://github.com/pawbytes/skill-suites
仓库路径:skills/paw-cra-design-brand
安装命令:
npx skills add https://github.com/pawbytes/skill-suites --skill paw-cra-design-brand
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/pawbytes/skill-suites --skill paw-cra-design-brand

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

辅助界面设计、视觉规范和布局优化。适合生成 UI 方案、检查一致性或改进组件层级。使用时需结合品牌和设计系统,避免堆砌装饰元素。涉及真实页面改动时,应通过截图或浏览器预览检查效果。关注文本溢出、对齐和响应式表现。paw-cra-design-brand 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/paw-cra-design-brand

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/pawbytes/skill-suites --skill paw-cra-design-b…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

paw-cra-design-brand 怎么安装?

在终端执行 npx skills add https://github.com/pawbytes/skill-suites --skill paw-cra-design-brand。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

paw-cra-design-brand 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

paw-cra-design-brand 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

paw-cra-design-brand 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

paw-cra-design-brand 用的人多吗?

公开数据是累计安装 470 次,近一周安装 20 次,下载 165 次,GitHub 25 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

paw-cra-design-brand 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
paw-cra-design-brand

Paw cra 设计品牌 · 本页

47025接触敏感数据未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

Brand Asset & Flyer Production

Overview

This workflow produces brand assets (logos, icons, avatars, banners) and flyers from brief to finished files. It is the Designer's companion workflow for brand identity and promotional print/digital materials. Act as a visual production specialist who understands brand systems, vector aesthetics, and print production requirements.

Args: Accepts --headless / -H for non-interactive execution with sensible defaults.

Output: Production-ready assets in multiple formats (PNG + SVG for logos/icons, PNG/PDF for flyers at 300 DPI for print) plus a design-manifest.json cataloging everything produced.

Pipeline: Brief intake -> brand context load -> style direction -> AI generation -> brand validation -> multi-format export -> delivery with manifest.

Key constraint: Every output is verified against brand guidelines before delivery. Off-brand colors, fonts, or styles are caught and corrected before export.

On Activation

Load available config from {project-root}/.pawbytes/config/config.yaml and {project-root}/.pawbytes/config/config.user.yaml (root level and cra section). If config is missing, let the user know paw-cra-setup can configure the module at any time. Resolve and apply throughout the session (defaults in parens):

  • {user_name} (null) -- address the user by name
  • {communication_language} (English) -- use for all communications
  • {fal_key} (null) -- fal.ai API key (required for AI generation)
  • {output_directory} (.pawbytes/creative-suites) -- base output path
  • {default_brand} (null) -- default brand name

Load shared agency memory:

  • {project-root}/.pawbytes/creative-suites/index.md -- active brands and campaigns
  • {project-root}/.pawbytes/creative-suites/brands/{brand}/guidelines.md -- brand context (loaded after brand is identified)

Verify tool availability:

  • fal_key -- required for all AI generation
  • Puppeteer/Playwright -- required for flyer template rendering
  • ffmpeg -- optional, for format conversion

If --headless or -H is passed, execute the full pipeline without interaction using the brief provided. Otherwise, proceed interactively through the pipeline steps.

Pipeline

Step 1: Brief Intake

Parse the incoming brief (from user, Aria, or campaign brief file). Extract:

FieldRequiredDefault
Asset typeYes--
Brand nameYes{default_brand}
Style directionNoInferred from brand guidelines
DimensionsNoStandard for asset type
Content/copyFor flyers--
Output typeNoDigital

Asset types supported:

TypeModelsPrimary Output
Logo (pictorial, abstract, combination)Recraft V4 ProPNG + SVG
IconRecraft V4 ProPNG + SVG
Wordmark / LettermarkIdeogram V3PNG + SVG
AvatarFLUX or Recraft V4PNG (400x400)
BannerFLUX ProPNG at target dimensions
Flyer (digital)FLUX Pro + HTML/CSS overlayPNG
Flyer (print)FLUX Pro + HTML/CSS overlayPNG + PDF (300 DPI)

If interactive and the brief is incomplete, ask targeted questions to fill gaps. In headless mode, use sensible defaults and note assumptions in the manifest.

Step 2: Brand Context

Load brand guidelines from {project-root}/.pawbytes/creative-suites/brands/{brand-name}/guidelines.md.

Extract and keep available throughout the pipeline:

  • Color palette (primary, secondary, accent hex values)
  • Typography (heading font, body font)
  • Logo paths (if existing logos are referenced)
  • Voice/tone keywords (inform style direction)
  • Any existing asset conventions

If no brand guidelines exist, inform the user and offer to proceed with the style direction from the brief alone, or suggest running Aria's brand onboarding first.

Step 3: Style Direction

Load ./references/style-direction.md for model selection logic and prompt engineering guidance.

Determine the generation approach based on asset type and brief:

Asset CategoryApproach
Logos / IconsVector-style via Recraft V4 Pro -- clean, scalable, minimal
WordmarksTypography-focused via Ideogram V3 -- precise letterforms
Flyers / BannersAI background via FLUX Pro + HTML/CSS text overlays
AvatarsCharacter/brand mark via best-fit model

Build the generation prompt incorporating brand colors, style keywords, and asset-specific requirements. For logos and icons, emphasize simplicity, scalability, and clean lines. For flyers, separate background generation from text content.

If interactive, present the style direction and model choice for approval before generation. In headless mode, proceed with the determined direction.

Step 4: AI Generation

Load ./references/generation-pipeline.md for CLI commands and model-specific parameters.

Execute generation using the fal.ai CLI (curl). Model endpoints:

ModelEndpointUse For
Recraft V4 Profal-ai/recraft-v4Logos, icons, brand marks
Ideogram V3Discover via fal.ai MCPWordmarks, text-heavy logos
FLUX.2 Profal-ai/flux-pro/v1.1Flyer backgrounds, banners, avatars

Generate 2-3 variations for interactive mode (user picks best). Generate 1 best-fit for headless mode.

Download all generated images to {project-root}/.pawbytes/creative-suites/brands/{brand-name}/assets/wip/ immediately -- never leave assets as URLs only.

Step 5: Flyer Template Rendering (flyers only)

Load ./references/flyer-rendering.md for template architecture and rendering pipeline.

For flyers and banners that need text overlays:

  1. Use the AI-generated image as background
  2. Build HTML/CSS overlay with headline, body copy, CTA, brand logo, and contact info
  3. Apply brand typography and colors from guidelines
  4. Render via Puppeteer/Playwright using element-specific screenshots (never fullPage: true)
  5. For print: render at 300 DPI equivalent resolution (A4 = 2480x3508px)

Critical: Use element-specific screenshots on .design-container to avoid white gaps. See template system reference for the correct rendering approach.

Step 6: Brand Validation

Before export, verify every produced asset against brand guidelines:

Color check: All brand colors used match the palette from guidelines. No unapproved colors introduced by AI generation.

Typography check: For flyers/banners with text overlays -- fonts match brand specs, sizes maintain hierarchy, contrast meets 4.5:1 minimum.

Style consistency: Visual style aligns with brand tone (e.g., minimalist brand should not get a maximalist logo).

Technical check:

  • Logo/icon assets work at both small (32px) and large (1024px+) sizes
  • Flyer content stays inside safety zones (3mm from trim for print)
  • Resolution meets requirements (300 DPI for print, 72+ DPI for digital)

If validation fails, note the issues and either auto-correct (e.g., color replacement) or flag for revision. In interactive mode, present issues to user. In headless mode, attempt correction and log any unresolvable issues.

Step 7: Multi-Format Export

Export approved assets to final location:

Logos and Icons:

  • Full color PNG (transparent background) at 512px and 1024px
  • SVG: Use Recraft V4 Pro's native SVG output when available. For raster-only sources, use potrace or vtracer CLI for bitmap-to-vector tracing — note that AI-generated raster images produce approximate SVG outlines, not true vector art. Flag in manifest as svg_source: "traced" vs svg_source: "native".
  • Monochrome variant
  • Reversed (white on transparent) variant

Flyers:

  • Digital: PNG at target dimensions, RGB
  • Print: High-res PNG (300 DPI) + PDF with bleed margins. For 300 DPI rendering in Puppeteer, set viewport to print dimensions at 300/72 scale (e.g., A4 = {width: 2480, height: 3508, deviceScaleFactor: 1}). Note: output is RGB — if CMYK is required for a professional print shop, inform the user that a post-export conversion via ImageMagick (convert input.png -colorspace CMYK output.tiff) or a dedicated prepress tool is needed. Flag in manifest as color_mode: "RGB" with a note when print output is requested.

Banners and Avatars:

  • PNG at exact target dimensions

File naming: {asset-type}_{descriptor}_{date}.{ext} Location: {project-root}/.pawbytes/creative-suites/brands/{brand-name}/assets/

Organize into subdirectories:

assets/
  brand-identity/
    logo/
    icons/
  flyers/
  banners/
  avatars/

Step 8: Manifest & Delivery

Write design-manifest.json to the brand assets directory:

{
  "workflow": "paw-cra-design-brand",
  "brand": "{brand-name}",
  "created": "ISO-8601 timestamp",
  "assets": [
    {
      "type": "logo",
      "description": "Primary logo, full color",
      "files": ["logo/logo-full-color-512.png", "logo/logo-full-color-1024.png", "logo/logo-full-color.svg"],
      "dimensions": "512x512, 1024x1024",
      "colorMode": "RGB",
      "status": "approved"
    }
  ],
  "validation": {
    "brandConsistency": "pass",
    "technicalSpecs": "pass",
    "issues": []
  }
}

Append activity to daily log at {project-root}/.pawbytes/creative-suites/daily/YYYY-MM-DD.md:

[Designer] Brand asset production for {brand-name}: {count} assets created. See design-manifest.json.

Present final summary with file paths and any notes.

References

ReferencePurposeLoaded When
./references/style-direction.mdModel selection, prompt engineering by asset typeStep 3
./references/generation-pipeline.mdfal.ai CLI commands, async generation, downloadStep 4
./references/flyer-rendering.mdHTML/CSS template architecture, Puppeteer renderingStep 5 (flyers only)

平台分布

Codex

34.83%
按下载量换算57

Claude

34.38%
按下载量换算57

Cursor

17.76%
按下载量换算29

Gemini CLI

9.28%
按下载量换算15

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

未通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills