Logo Generator

Logo Generator

Overview

Generate professional logo concepts using AI image generation. Create variations, download in multiple formats, and save to Google Drive.

You generate the logos yourself using an AI image provider, then save to Drive.

Dependencies

This skill requires the following:

Dependency	Required?	Why
google-workspace skill	Yes — for saving logos to Google Drive and creating brand kit docs via gws CLI
gemini-api skill	If user chooses Gemini — for image generation via gemini-3-pro-image-preview
$OPENAI_KEY (stand-in, use with vault-curl)	If user chooses OpenAI — for image generation via DALL-E 3
$GEMINI_KEY (stand-in, use with vault-curl)	If user chooses Gemini — for image generation via Gemini Imagen

Before starting, check:

1. Is google-workspace skill installed and $GWS_GOOGLE_ACCOUNT set? If not, logos can still be generated but won't auto-save to Drive — inform the user.
2. Which image keys do you have? [ -n "$OPENAI_KEY" ] && echo openai; [ -n "$GEMINI_KEY" ] && echo gemini. These are stand-ins (mcb_sec_…) for the user's keys, not the keys: they only work through vault-curl. A key added after you started is not in your env yet: run vault-curl --secrets and use an entry's surrogate string in place of $OPENAI_KEY / $GEMINI_KEY. Agents not yet moved to the vault may instead have real keys in the OPENAI_API_KEY / GEMINI_API_KEY variables: use those with plain curl, in the same header. Never print a key or stand-in, and never use OpenClaw's built-in secrets tool (these keys are not there). Missing keys: ask the user to add them in MyClawBots → Settings → Integrations; never ask them to paste a key into chat.

Provider Selection — ASK THE USER

Before generating any images, you must ask the user which AI provider to use:

"I can generate logo concepts using:

1. OpenAI DALL-E 3 — high quality, ~$0.04/image, great for photorealistic styles
2. Google Gemini Imagen — cheaper (~$0.025/image), supports image editing and background removal
3. SVG code — free, I'll write vector code directly (best for geometric/minimal logos)

Which would you prefer? Or I can mix — Gemini/DALL-E for concepts and SVG for the final refined version."

If only one key is available, inform the user and use that one. If neither key is set, default to SVG generation (free) and tell the user how to add an API key.

Capabilities

• Generate multiple logo concepts from text prompts
• Create variations with different colors, styles, and layouts
• Output in PNG, SVG (hand-written code), and PDF
• Save to Google Drive automatically (requires google-workspace skill)
• Suggest color palettes and font pairings
• Design logos for any industry or style

Step-by-Step Workflow

1. Gather Requirements

• Brand name and description
• Industry/category
• Style preference (minimalist, bold, geometric, organic, etc.)
• Color preferences (primary + secondary)
• Icon type preference (abstract, symbol, lettermark, wordmark)

2. Generate Logo Concepts

Option A: OpenAI DALL-E 3 (if user chose OpenAI)

vault-curl -sS https://api.openai.com/v1/images/generations \
  -H "Authorization: Bearer $OPENAI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dall-e-3",
    "prompt": "Professional logo for TechVision, a software company. Modern, minimalist tech logo with abstract geometric shapes. Primary color: deep blue (#0066CC), secondary: orange (#FF6B35). Clean lines, transparent background, vector style, suitable for app icon and business card.",
    "size": "1024x1024",
    "quality": "hd",
    "n": 1
  }' | jq -r '.data[0].url'

Save the returned URL locally:

curl -s [IMAGE_URL] -o logo_concept_1.png

Option B: Google Gemini Imagen (if user chose Gemini)

Easiest, and always works: the gemini-image skill (claw install gemini-image once). It finds the key itself and calls Gemini through the vault:

python3 /root/.openclaw/skills/gemini-image/scripts/gemini_image.py \
  --prompt "Professional logo for TechVision, a software company. Minimalist, geometric, deep blue and orange, transparent background." \
  --out /root/.openclaw/workspace/media/logo_concept_1.png

To edit an existing image, add --input-image PATH. The Python SDK below sends the stand-in directly, so it works only when AGENTS.md says plain curl and SDKs work (the MyClawBots vault proxy is on).

With the vault proxy on, Python:

from google import genai
from google.genai import types
import os, base64

client = genai.Client(api_key=os.environ["GEMINI_KEY"])  # needs the vault proxy

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents="Professional logo for TechVision, a software company. Modern, minimalist tech logo with abstract geometric shapes. Primary color: deep blue (#0066CC), secondary: orange (#FF6B35). Clean lines, transparent background, vector style.",
    config=types.GenerateContentConfig(
        response_modalities=["image", "text"],
    )
)

for part in response.candidates[0].content.parts:
    if part.inline_data:
        with open("logo_concept_1.png", "wb") as f:
            f.write(base64.b64decode(part.inline_data.data))
        print("Saved logo_concept_1.png")

Gemini bonus: You can also edit an existing logo (remove background, change colors):

response = client.models.generate_content(
    model="gemini-3-pro-image-preview",
    contents=[
        types.Content(parts=[
            types.Part.from_bytes(data=open("logo_v1.png","rb").read(), mime_type="image/png"),
            types.Part.from_text("Remove the background, make it fully transparent. Keep the logo intact."),
        ])
    ],
    config=types.GenerateContentConfig(response_modalities=["image", "text"])
)

Option C: SVG Code (always available, free)

You can write SVG code directly — best for geometric and minimalist logos:

<svg viewBox="0 0 200 200" xmlns="http://www.w3.org/2000/svg">
  <defs>
    <linearGradient id="grad" x1="0%" y1="0%" x2="100%" y2="100%">
      <stop offset="0%" style="stop-color:#0066CC;stop-opacity:1" />
      <stop offset="100%" style="stop-color:#FF6B35;stop-opacity:1" />
    </linearGradient>
  </defs>
  <circle cx="100" cy="100" r="95" fill="none" stroke="url(#grad)" stroke-width="3"/>
  <path d="M 100 50 L 130 100 L 100 150 L 70 100 Z" fill="url(#grad)"/>
</svg>

3. Create Multiple Variations

Generate 3-5 concepts by varying the prompt:

• Change style: minimalist → bold → geometric → organic
• Change icon type: abstract → symbol → lettermark
• Vary layout: vertical → horizontal → square

Show the user each concept: save the files under /root/.openclaw/workspace/media/ (for example /root/.openclaw/workspace/media/logo_concept_1.png) and put one line MEDIA:<absolute path> per file in your reply, on its own line and not in a code block. The view_image (View Image) tool shows a file only to you, never to the user.

4. Resize for Multiple Uses

Common logo sizes:

• Favicon: 32x32 (PNG)
• Social profile: 400x400 (PNG)
• Website header: 200x80 (PNG or SVG)
• App icon: 512x512 (PNG)
• Print: 300 DPI (PDF)

Use Python Pillow to resize:

pip install Pillow -q
python3 -c "
from PIL import Image
img = Image.open('logo_concept_1.png')
img.resize((32, 32)).save('favicon.png')
img.resize((512, 512)).save('app-icon.png')
img.resize((400, 400)).save('social-profile.png')
"

5. Save to Google Drive

Depends on: google-workspace skill

Upload all logo versions to Drive:

gws drive +upload --file logo_concept_1.png --folder "[folder_id]"
gws drive +upload --file logo_concept_1.svg --folder "[folder_id]"

6. Create Brand Kit Document

Depends on: google-workspace skill

Write a brand guidelines document and save as Google Doc:

gws docs +create --title "Brand Guidelines" --content "[markdown content]"

Include: logo files, color palette (hex + RGB), clear space rules, usage guidelines.

Cost

Provider	Cost per image	Notes
OpenAI DALL-E 3	~$0.04 (1024x1024 HD)	High quality, photorealistic capable
Gemini Imagen	~$0.025-0.04	Cheaper, supports editing existing images
SVG code	Free	You write it, best for geometric/minimal
Google Drive upload	Free	Via google-workspace skill

Typical project: $0.15-0.40 for 3-5 AI-generated concepts + SVG refinements.

Example Prompt Template

Professional logo for [BRAND_NAME], a [INDUSTRY] company. [STYLE] style logo.
Primary colors: [COLOR1], [COLOR2].
Icon type: [ABSTRACT/SYMBOL/WORDMARK].
Clean, modern design suitable for web and print.
Transparent background, vector-ready appearance.
No text, icon-only.

Pro Tips

• Start with 3-5 diverse concepts (different styles) rather than subtle variations
• Always include "transparent background" in prompts for web use
• SVG logos are infinitely scalable — provide both PNG (quick use) and SVG (print/design)
• Test logos at small sizes (favicon, social icon) to ensure clarity
• Create both full-color and single-color (monochrome) versions
• If using Gemini, leverage its image editing to refine logos (remove bg, adjust colors)
• Get user feedback before spending time on detailed refinements
• Trademark check: suggest user verify brand name isn't trademarked before finalization