agentleFS
RhythrosaLabsRhythrosaLabs/otto-mate/skills/product_design/SKILL.md

product_design

Skill1 starsChanged 10 months agoMITView on GitHub

The file

Show its rules and text

We split this skill into the rules it gives an agent

17 rules. About 0 are common, 17 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈17

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Design Generation: Create original designs using AI models

    line 7
  2. Distinctive:

    Lifestyle Scenes: Place products in lifestyle photography

    line 9
  3. Distinctive:

    Format Optimization: Ensure correct dimensions and DPI

    line 12
  4. Distinctive:

    Safe Area: Keep important elements 2 inches from edges

    line 88
  5. Distinctive:

    Wrap Style: Consider handle placement

    line 94
  6. Distinctive:

    Bleed Area: Add 0.125" bleed on all sides

    line 100
  7. Distinctive:

    Safe Zone: Keep text 0.25" from trim

    line 101
  8. Distinctive:

    Use upscale_image tool to enhance

    line 122
  9. Distinctive:

    Use consistent prompting patterns

    line 128
  10. Distinctive:

    Avoid specific brand names or characters

    line 132
  11. Distinctive:

    Use "inspired by" rather than direct copies

    line 133
  12. Distinctive:

    Add unique elements to differentiate

    line 135
  13. Distinctive:

    Always research trends before creating

    line 138
  14. Distinctive:

    Test designs on actual product mockups

    line 140
  15. Distinctive:

    Use brand guidelines if provided

    line 143
  16. Distinctive:

    Check print requirements before finalizing

    line 144
  17. Distinctive:

    Create both light and dark background versions

    line 146

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Product Design Skill

Description

AI-powered product design creation for print-on-demand, including t-shirts, mugs, posters, and lifestyle products with trend analysis and brand consistency.

Capabilities

  • Design Generation: Create original designs using AI models
  • Mockup Creation: Generate realistic product mockups
  • Lifestyle Scenes: Place products in lifestyle photography
  • Brand Consistency: Maintain visual identity across designs
  • Trend Integration: Apply current design trends
  • Format Optimization: Ensure correct dimensions and DPI

Tools Required

  • generate_image
  • generate_tshirt_design
  • generate_product_mockup
  • generate_lifestyle_scene
  • upscale_image
  • remove_background
  • replicate_smart_generate
  • replicate_run_model
  • search_web (for trend research)
  • get_trending_topics

Workflows

Complete Design Creation

name: Create Product Design from Concept
steps:
  1. Analyze design request and brand guidelines
  2. Research current trends in niche
  3. Generate 3-5 design variations
  4. Select best design based on criteria
  5. Upscale to print quality (300 DPI, 4500x5400px)
  6. Remove background if needed
  7. Create product mockups (t-shirt, mug, etc.)
  8. Generate lifestyle scene
  9. Save all assets with metadata

success_criteria:
  - Design matches brand guidelines
  - Print-ready quality (300 DPI minimum)
  - Multiple mockup angles
  - Lifestyle scene for marketing

Trend-Based Design

name: Create Trending Design
steps:
  1. Get trending topics in target niche
  2. Analyze trending visual styles
  3. Generate design incorporating trends
  4. Test on multiple product types
  5. Create variant designs

success_criteria:
  - Aligns with current trends
  - Unique enough to avoid copyright
  - Works on multiple product types

Design Optimization

name: Optimize Existing Design
steps:
  1. Analyze current design
  2. Upscale if low resolution
  3. Enhance colors and contrast
  4. Remove artifacts
  5. Create print-ready version
  6. Generate new mockups

success_criteria:
  - Minimum 300 DPI
  - Proper color profile (RGB for digital, CMYK for print)
  - Clean edges and backgrounds

Design Guidelines

T-Shirt Designs

  • Dimensions: 4500x5400 pixels (standard print area)
  • DPI: 300 minimum
  • Color Mode: RGB
  • Safe Area: Keep important elements 2 inches from edges
  • File Format: PNG with transparent background

Mug Designs

  • Dimensions: 2475x1155 pixels (11oz mug)
  • DPI: 300 minimum
  • Wrap Style: Consider handle placement
  • Color Mode: RGB

Poster Designs

  • Dimensions: Variable by size (18x24" = 5400x7200px at 300 DPI)
  • DPI: 300 minimum
  • Bleed Area: Add 0.125" bleed on all sides
  • Safe Zone: Keep text 0.25" from trim

Prompting Strategies

High-Quality Design Prompts

For photorealistic: "highly detailed, photorealistic, 8k uhd, professional photography"
For illustrations: "vector art style, clean lines, professional illustration, trending on dribbble"
For minimalist: "minimalist design, clean aesthetic, negative space, modern typography"
For vintage: "retro aesthetic, vintage texture, distressed effect, classic typography"

AI Model Selection

  • Flux Pro: Best for photorealistic and detailed designs
  • SDXL: Great for artistic styles and illustrations
  • Midjourney: Excellent aesthetic quality (via replicate)
  • Stable Diffusion: Good for specific styles and controlnet

Error Handling

Low Resolution Output

  • Use upscale_image tool to enhance
  • Regenerate with explicit resolution requirements
  • Try different AI models

Inconsistent Style

  • Provide detailed style reference
  • Use consistent prompting patterns
  • Include negative prompts to avoid unwanted elements

Copyright Concerns

  • Avoid specific brand names or characters
  • Use "inspired by" rather than direct copies
  • Generate original concepts
  • Add unique elements to differentiate

Best Practices

  • Always research trends before creating
  • Generate multiple variations
  • Test designs on actual product mockups
  • Maintain a design library for consistency
  • Document successful prompts
  • Use brand guidelines if provided
  • Check print requirements before finalizing
  • Save high-res originals
  • Create both light and dark background versions

Dependencies

  • Replicate API access
  • Image storage system
  • Brand guidelines (optional)
  • Design trend knowledge base

Metadata

  • Domain: creative, ecommerce
  • Complexity: Medium-High
  • Automation Level: Semi-Automated
  • Human Verification: Recommended (aesthetic review)

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.