Paw Cra Design Social logo

Paw Cra Design Social

Organization
pawbytes
paw-cra-design-social

Social post and carousel production pipeline. Use when the user requests to 'create social post', 'design carousel', or 'run social design workflow'.

Overview

Publisherpawbytes
Repositoryskill-suites
Skill namepaw-cra-design-social
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 Social 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-social
  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-social .claude/skills/paw-cra-design-social
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Paw Cra Design Social 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 Social 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 Social 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.

Social Design Workflow

Overview

This workflow produces production-ready social media posts and carousels -- the most common visual output in the Aria Creative Suite. It takes a brief (platform, format, content, brand) and delivers platform-correct PNG/JPG files plus a design-manifest.json.

Args: Accepts --headless / -H for autonomous execution without interaction.

Output: Visual assets at exact platform dimensions saved to .pawbytes/creative-suites/brands/{brand}/assets/ plus design-manifest.json.

Act as a visual production pipeline operator. This workflow is production-first -- it produces images, not documents. Every step exists to ensure the final visual asset is brand-correct, platform-correct, and upload-ready.

Design rationale: This workflow replaces the old standalone cra-design-review-gate by embedding brand and platform validation as steps 8-9 within the production pipeline. Review gates that live outside the production flow add friction without adding value -- the producer who generates the asset is best positioned to validate it immediately.

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 (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 for image generation (required)
  • {output_directory} (.pawbytes/creative-suites) -- base output path

Load shared agency memory from {project-root}/.pawbytes/creative-suites/index.md to understand active brands and campaigns. Load brand guidelines from .pawbytes/creative-suites/brands/{brand}/guidelines.md once the brand is identified.

Check {project-root}/.pawbytes/creative-suites/knowledge/index.md for previously researched platform specs and design knowledge.

Tool verification: Confirm fal_key is available before proceeding. Check for Puppeteer/Playwright availability (needed for template rendering). If tools are missing, inform the user of reduced capabilities but continue where possible.

If --headless, proceed through all stages without interaction using sensible defaults. Otherwise, confirm the brief with the user before production begins.

Pipeline

The workflow has three stages. Each loads its reference on entry.

Stage 1: Brief & Context

Load ./references/01-brief-and-context.md

Parse and validate the incoming brief. Load platform specifications and best practices. Resolve copy -- either from the brief or by invoking the Strategist. This stage produces a validated, complete brief with all parameters needed for production.

Progression: Move to Stage 2 when the brief is complete (platform, format, dimensions, copy, brand context all resolved). In headless mode, infer missing parameters from context and proceed.

Stage 2: Production

Load ./references/02-production.md

Plan the visual layout, generate AI imagery, and render text overlays. For carousels, maintain visual consistency across all slides. This stage produces the raw visual assets.

Progression: Move to Stage 3 when all assets are generated and saved to disk.

Stage 3: Validation & Export

Load ./references/03-validation-and-export.md

Validate assets against brand guidelines and platform specifications. Export to the correct location with proper naming. Write the design manifest and update status logs. This stage produces the final deliverables.

Progression: Workflow complete when design-manifest.json is written and daily log is updated.


Quick Reference

Supported Platforms

PlatformPostCarouselStory
Instagram1080x1350 (4:5)1080x1080 or 1080x13501080x1920
LinkedIn1200x6271080x1080 (PDF)1080x1920
TikTok1080x1920--1080x1920
X (Twitter)1200x675----
Facebook1200x6301080x10801080x1920

AI Model Selection

Use CasePrimary ModelFallback
Text-heavy postsNano Banana ProFLUX.2 [flex]
Photo-realisticFLUX.2 [pro]FLUX.2 [flex]
Rapid prototypingFLUX.1 [schnell]--
Carousel consistencyFLUX.2 [flex]Nano Banana Pro

Output Structure

.pawbytes/creative-suites/brands/{brand}/assets/{campaign}/social/
  {platform}_{format}_{date}.png
  {platform}_{format}_{date}_slide01.png  (carousel)
  {platform}_{format}_{date}_slide02.png  (carousel)
  design-manifest.json

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 Social AI skill do?

Social post and carousel production pipeline. Use when the user requests to 'create social post', 'design carousel', or 'run social design workflow'.

Why use Paw Cra Design Social on TypingMind?

Because you install it once and use it with any model. Paw Cra Design Social 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 Social 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-social. 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 Social?

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 Social?

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

Is the Paw Cra Design Social 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 👇