Paw Cra Design Brand logo

Paw Cra Design Brand

Organization
pawbytes
paw-cra-design-brand

Brand asset and flyer production pipeline. Use when user requests 'create logo', 'design brand asset', 'make flyer', 'generate icon', or 'create banner'.

Overview

Publisherpawbytes
Repositoryskill-suites
Skill namepaw-cra-design-brand
Stars
117
Forks
20
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by pawbytes on GitHub. Read the source before you install it.

Installation

Install the Paw Cra Design Brand AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/pawbytes/skill-suites/tree/main/src/creative/paw-cra-design-brand
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/pawbytes/skill-suites.git /tmp/skill-suites
mkdir -p .claude/skills
cp -r /tmp/skill-suites/src/creative/paw-cra-design-brand .claude/skills/paw-cra-design-brand
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paw Cra Design Brand in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Paw Cra Design Brand on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Paw Cra Design Brand is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

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:

json
{
  "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)

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Paw Cra Design Brand AI skill do?

Brand asset and flyer production pipeline. Use when user requests 'create logo', 'design brand asset', 'make flyer', 'generate icon', or 'create banner'.

Why use Paw Cra Design Brand on TypingMind?

Because you install it once and use it with any model. Paw Cra Design Brand is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Paw Cra Design Brand in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/pawbytes/skill-suites/tree/main/src/creative/paw-cra-design-brand. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Paw Cra Design Brand?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Paw Cra Design Brand?

As many as you like. As long as a model supports skills, you can use Paw Cra Design Brand with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Paw Cra Design Brand AI skill free?

Yes. It is published on GitHub by pawbytes under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇