Brand Asset logo

Brand Asset

Community
sanky369
brand-asset

Produces branded visual identity elements — logo concepts, icon sets, seamless patterns, brand illustrations, and textures — as generation-ready prompt specs, and generates them via FAL.ai fal-ai/nano-banana-pro when the automation is configured. Use when the user says 'design a logo', 'I need icons', 'brand pattern / texture', 'brand illustrations', 'visual identity elements', or 'make my brand assets'. Produces one prompt-spec block per asset (asset type, style, palette with hex, composition, negative constraints), a variant plan for user selection, file-naming conventions, and a brand-guidelines entry for each approved asset; runs docs/creative_cli.py brand when FAL_API_KEY is set.

Overview

Publishersanky369
Repositoryvibe-building-skills
Skill namebrand-asset
Stars
31
Forks
7
Bundled files
1
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.

  • 1 bundled files

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

  • Open source

    Published by sanky369 on GitHub. Read the source before you install it.

Installation

Install the Brand Asset 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/sanky369/vibe-building-skills/tree/main/skills/creative/brand-asset
  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/sanky369/vibe-building-skills.git /tmp/vibe-building-skills
mkdir -p .claude/skills
cp -r /tmp/vibe-building-skills/skills/creative/brand-asset .claude/skills/brand-asset
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Brand Asset 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 Brand Asset 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 Brand Asset 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

Generate the visual identity elements a brand reuses everywhere — logo concepts, icons, patterns, illustrations, textures — as prompt specs sharp enough that the whole family looks designed by one hand. Prime rule: cohesion over cleverness. A brand asset is judged by how well it matches its siblings and survives resizing, not by how impressive it is alone. And be honest about the medium: the model outputs raster concepts; production logos and icons still need vector tracing.

When to use / when not to

Use for logos, icon sets, patterns, brand illustrations, and textures. Hand off instead when:

  • No visual direction exists → skills/creative/creative-strategist first; its brief supplies this skill's style, palette, and mood. For a single throwaway asset, derive a minimal style inline and label it an assumption.
  • The asset is a product image → skills/creative/product-photography
  • The asset is a platform post/banner → skills/creative/social-graphics
  • It's a general non-branded image → skills/creative/image-generation
  • The user wants a full identity system rolled out across asset types → skills/creative/orchestrator sequences it (strategist → this skill → the rest)

Intake

Ask in one batch, only what's missing:

  1. Brand — name, what it does, one sentence of personality.
  2. Asset type(s) — logo, icon set, pattern, illustration, texture? (These are also the automation's exact --asset-type choices.)
  3. Style anchor — Creative Direction Brief / existing logo to match, or palette hex codes? For icons/patterns joining an existing identity, matching it is mandatory, not optional.
  4. Usage — where will it live (app icon, website, print, merch)? This drives simplicity requirements and variant needs.
  5. Automation — FAL_API_KEY set, or deliver specs only?

Infer, don't ask: aspect ratio (logos/icons/patterns → 1:1; wordmark lockups → 3:2 or 16:9); resolution 2K (patterns/textures 4K). Don't stall: with brand + asset type known, assume the rest, label it, proceed.

Workflow

  1. Lock the style line. One style from the vocabulary (minimalist, geometric, organic, illustrative, abstract) + palette in words and hex + mood — taken from the Creative Direction Brief when it exists. Every asset in the family uses the same style line verbatim.

  2. Write prompt specs from the templates in references/asset-library.md — read it now; it has the per-type templates, style vocabulary, color application patterns, and delivery specs. Decision rules:

    • Logo → always generate as concepts to choose from: 4 variants (--num-images 4) or 3–4 distinct specs (different style angles). Never one take. Flat, plain background, no photorealism, no tiny text.
    • Icon set → generate the whole set as ONE sheet in one call so stroke weight and corner radius stay consistent; never one icon per call.
    • Pattern/texture → demand seamless, tileable, edge-to-edge and test-tile the result before accepting.
    • Illustration → fix subject + line weight + palette; generate 2–3.
  3. Set negative constraints on every spec: no watermark, no gradients-and- bevels clutter (unless the style calls for it), no readable text beyond the exact brand name supplied, no stock-clipart clichés.

  4. Generate or deliver. If FAL_API_KEY (or FAL_KEY) is set:

    bash
    python docs/creative_cli.py brand \
      --asset-type logo --brand-name "TechCorp" \
      --prompt "<full prompt>" \
      --aspect-ratio 1:1 --resolution 2K --num-images 4

    Saves to assets/brand-assets/<brand-slug>/<asset-type>/ as <type>_<n>_<timestamp>.png. No key → deliver specs + exact commands; never claim generation happened. Parameter source of truth: skills/creative/image-generation/references/automation.md.

  5. User selects; you verify. Present variants, have the user pick one per slot (recommend one, one-line reason). Check winners against the quality bar; fix misses with the fix-it phrases in references/asset-library.md — one iteration round.

  6. Record in the brand guide. Add each approved asset to the guidelines entry (format below) and state the production step honestly (e.g. "trace to SVG before shipping").

Required output format

One block per asset:

## Asset Spec — [asset name, e.g. logo-concept-A]
- **Asset type:** logo / icon / pattern / illustration / texture
- **Brand:** [name] · **Usage:** [where it will live]
- **Style:** [one style line, shared across the family]
- **Palette:** [color name #hex, role] ...
- **Composition:** [e.g. centered mark, plain background / 6-icon sheet on grid / edge-to-edge tile]
- **Mood:** [2–3 adjectives]
- **Aspect ratio:** [ratio] · **Resolution:** [1K/2K/4K] · **Format:** png
- **Negative constraints:** [no watermark, no text beyond "<brand>", ...]
- **Prompt (final, paste-ready):**
  > [single flowing prompt]
- **Variants:** [n] — [what varies]
- **File naming:** assets/brand-assets/<brand-slug>/<asset-type>/<type>_<n>_<timestamp>.png
- **Generate with:** `python docs/creative_cli.py brand --asset-type ... --brand-name "..." --prompt "..." --aspect-ratio ... --num-images n`
- **Production note:** [raster concept — trace to SVG / normalize grid / verify tiling]

After selection, append per approved asset a Brand guide entry: asset name, file path, color variants needed, minimum size / clear space (logos), and usage rule — using the guidelines skeleton in references/asset-library.md.

Quality bar

  • Every asset in the family shares the same style line and palette verbatim
  • Logos: 3+ distinct concepts offered; works in one color; still reads at thumbnail size (describe the check, don't assume)
  • Icon sets: generated as one sheet; consistent stroke weight and corner radius
  • Patterns/textures: seamless, tileable in the prompt AND tiling verified (or flagged unverified)
  • All colors given in words + hex, pulled from the brief when one exists
  • Negative constraints on every spec; no text rendered beyond the supplied brand name
  • Deliverable states the raster→vector production step for logos/icons — never imply the PNG is print-ready vector
  • Only real automation parameters (fal-ai/nano-banana-pro; no size/steps/guidance knobs exist)

Hard don'ts: never mix two styles in one asset family; never present a generated logo as trademark-cleared (recommend a clearance search); never fake generation results when the API key is absent.

Integration

  • skills/creative/creative-strategist → upstream; the Creative Direction Brief supplies style line, palette, mood, and prohibitions.
  • skills/creative/image-generation → shared automation; skills/creative/image-generation/references/automation.md is the parameter source of truth.
  • skills/creative/social-graphics and skills/creative/product-photography → downstream; consume approved logos/patterns as recurring elements.
  • skills/creative/orchestrator → sequences this skill inside brand-identity and rebrand paths; the artifact passed forward is the approved asset set + brand guide entries.
  • references/asset-library.md — full templates, style vocabulary, delivery specs, guidelines skeleton, fix-it phrases. Read before writing specs.

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 Brand Asset AI skill do?

Produces branded visual identity elements — logo concepts, icon sets, seamless patterns, brand illustrations, and textures — as generation-ready prompt specs, and generates them via FAL.ai fal-ai/nano-banana-pro when the automation is configured. Use when the user says 'design a logo', 'I need icons', 'brand pattern / texture', 'brand illustrations', 'visual identity elements', or 'make my brand assets'. Produces one prompt-spec block per asset (asset type, style, palette with hex, composition, negative constraints), a variant plan for user selection, file-naming conventions, and a brand-gu...

Why use Brand Asset on TypingMind?

Because you install it once and use it with any model. Brand Asset 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 Brand Asset in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sanky369/vibe-building-skills/tree/main/skills/creative/brand-asset. 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 Brand Asset?

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 Brand Asset?

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

Is the Brand Asset AI skill free?

Yes. It is published on GitHub by sanky369 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 👇