Design And Templates logo

Design And Templates

Organization
social-media-skills
design-and-templates

The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using a design tool (Canva/Adobe Express/Figma). For social, consistency + speed beat bespoke. Uses the BRAND framework. Reads brand-profile first. The agent designs the SYSTEM (brand-kit tokens, template set, hierarchy rules, workflow); a design tool or the image tools produce the actual graphics; the finished asset enters the WoopSocial flow (WoopSocial publishes -- it does NOT design or generate). Honest about the ~70-80% on-brand ceiling and AI copyright limits. Distinct from brand-profile (the identity source), thumbnail-design + pinterest-pin-design (single asset types), carousel-writer (copy vs visual frame), and image-prompt + the image tools (generation vs layout).

Overview

Publishersocial-media-skills
Repositoryskills
Skill namedesign-and-templates
Stars
215
Forks
44
Bundled files
5
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.

  • 5 bundled files

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

  • Open source

    Published by social-media-skills on GitHub. Read the source before you install it.

Installation

Install the Design And Templates 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/social-media-skills/skills/tree/main/skills/design-and-templates
  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/social-media-skills/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/skills/design-and-templates .claude/skills/design-and-templates
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Design And Templates 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 Design And Templates 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 Design And Templates 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.

design-and-templates

The reusable on-brand template-system skill — a brand kit + a small set of reusable templates + the rules + the workflow that let a non-designer ship consistent on-brand graphics fast. The agent designs the system; a design tool or the image tools produce the graphics; the finished asset enters the WoopSocial flow.

The POV: consistency + speed beat bespoke

For social, the win isn't one beautiful design — it's six versions that still look like the same campaign, produced fast by a non-designer. The lever is a small reusable template system anchored in a brand kit, which prevents both brand drift and generic "template energy." Brand-kit-first makes the first draft ~80% on-brand instead of ~20%. The honest ceiling: tools get you ~70–80% on-brand — a human eye finishes the hero work. The agent designs the system; a design tool (Canva/Adobe Express/ Figma) or the image tools produce the graphics; WoopSocial publishes the finished asset.

Read these first

  1. brand-profile — the identity source this operationalizes.
  2. the recurring content needs — what you actually post.

The framework: BRAND

(Depth: references/the-brand-framework.md.)

  • B — Build the brand kit: lock the tokens (colors, fonts, logo, spacing) — the consistency anchor (brand-kit-first = ~80% on-brand drafts).
  • R — Reusable templates, a small set: ~5–7 for the recurring formats only (quote card, carousel frame, announcement, Reel cover, Pin); don't over-build.
  • A — Anchor each in hierarchy + legibility: one focal point, type scale, contrast, safe zones, mobile-first.
  • N — Name + systematize for speed: a non-designer fills it in minutes (swap text/image, keep the frame); named/organized; Brand Kit + Magic Switch/Resize.
  • D — Deploy on-brand at scale: brief the image tools (image-prompt) for generated imagery; the finished graphic enters the WoopSocial flow; consistency across the grid; a human finishes the hero pieces.

The reality (verify-quarterly)

Design fundamentals (hierarchy/contrast/legibility) are timeless; the tools move. Canva (Magic Studio) = social-first default (Brand Kit, Magic Design, Magic Switch/Resize, Dream Lab, Bulk Create; Pro ~$15/mo; ~70% "Canva-style" ceiling + AI credit limits; raw AI generally not copyrightable; Canva Shield indemnification Enterprise-only). Adobe Express+Firefly = premium, brand-safe licensed AI + IP indemnification. Figma = master design systems/governance (not daily social). Combine by strength zone; brief the image tools (image-prompt) or Dream Lab/Firefly for generated imagery: references/design-tools- 2026-reality.md. The brand-kit spec, the starter template set + specs, the hierarchy/legibility rules, the production workflow + worked examples: references/building-the-system.md.

Honest scope (never violate)

  • The agent designs the system (brand-kit tokens, the template set, hierarchy rules, the workflow) — it specs/advises, it doesn't render.
  • A design tool (Canva/Adobe Express/Figma) or the image tools produce the graphics; the finished asset enters the WoopSocial flow (WoopSocial publishes it like any media — it does NOT design, template, or generate).
  • Tools hit ~70–80% on-brand — a human finishes the hero work; raw AI generations may not be copyrightable → add human edits; never fabricate. (Scope, distinctions + connections: references/scope-and-connections.md.)

Distinct from its siblings (route correctly)

design-and-templates (this) = the reusable template SYSTEM + brand kit · brand-profile = the identity source it operationalizes · thumbnail-design / pinterest-pin-design = single asset types (templates in the system) · carousel-writer = the copy/narrative (this is the visual frame) · image-prompt + the image tools = generation (this is layout/templates) · profile-optimization = the profile assets.

Where this connects

Reads first: brand-profile + the recurring content needs. Feeds the format siblings: thumbnail- design, pinterest-pin-design, instagram-reels-publishing (cover), carousel-writer (the frame its copy fills), story-writer — each a template in the system. Briefs for imagery: image-prompt → ideogram/flux/nano-banana (or Dream Lab/Firefly). Publishes via: the finished asset → scheduling-and-queue → WoopSocial (post/Pin/cover/carousel media). Design + generation stay in the design tool / image tools; WoopSocial only publishes.

Definition of done

A reusable system: a brand kit (locked colors/fonts/logo/spacing) plus a small set (~5–7) of named templates mapped to the real recurring formats, each with one focal point, a clear type scale, contrast, safe zones, and mobile-first legibility; a non-designer production workflow (swap text/image → resize → export → into the WoopSocial flow) using the right tool for the team (Canva default / Adobe Express+Firefly for premium, indemnified imagery / Figma for the master system), with generated imagery briefed to the image tools via image-prompt; the honest ceiling stated (tools hit ~70–80% on-brand, a human finishes the hero work, raw AI generations may not be copyrightable); the finished assets published via WoopSocial; nothing fabricated; correctly distinguished from brand-profile, thumbnail-design/pinterest-pin-design, carousel-writer, and image-prompt.

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 Design And Templates AI skill do?

The reusable on-brand template-SYSTEM skill -- build a brand kit + a small set of reusable templates so a non-designer can produce consistent on-brand graphics fast across formats. Use when someone wants templates, a brand kit, a consistent visual system, or help choosing/using a design tool (Canva/Adobe Express/Figma). For social, consistency + speed beat bespoke. Uses the BRAND framework. Reads brand-profile first. The agent designs the SYSTEM (brand-kit tokens, template set, hierarchy rules, workflow); a design tool or the image tools produce the actual graphics; the finished asset enter...

Why use Design And Templates on TypingMind?

Because you install it once and use it with any model. Design And Templates 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 Design And Templates in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/social-media-skills/skills/tree/main/skills/design-and-templates. 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 Design And Templates?

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 Design And Templates?

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

Is the Design And Templates AI skill free?

Yes. It is published on GitHub by social-media-skills 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 👇