image-logo-icons
Skill17 starsChanged 8 months agoMITView on GitHub
Generate structured image prompts for brand visuals: logos, UI icons, favicons/PWA icons, featured blog images, and Open Graph social cards. Use when users ask to design or iterate brand identity assets, social preview graphics, or reusable prompt templates for image models.
In this repository4 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Create production-ready prompts for brand and marketing images.
- Distinctive: line 21
Keep one coherent visual language.
- Distinctive: line 22
Keep output clean and uncluttered.
- Distinctive: line 23
Avoid trademarked logo imitation or direct brand copying.
- Distinctive: line 24
Prefer legibility at small sizes for logo/icon outputs.
- Distinctive: line 42
Use defaults when optional fields are not provided:
- Distinctive: line 56
If a user requests multiple assets in one turn:
- Very specific: line 58
Keep shared brand fields consistent (brand_name, palette, mood).
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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.
Files
Image Logo Icons
Create production-ready prompts for brand and marketing images.
Workflow
- Classify request as one of:
site_logoui_iconfeatured_blog_imagesocial_og_imagefavicon_app_icon
- Collect required fields from the input matrix below. Ask only for missing required fields.
- Load the matching template from references/templates.md.
- Apply global quality rules:
- Keep one coherent visual language.
- Keep output clean and uncluttered.
- Avoid trademarked logo imitation or direct brand copying.
- Prefer legibility at small sizes for logo/icon outputs.
- Return results in this exact order:
Final prompt:Render settings:Variation ideas:
Input Matrix
| Type | Required | Optional |
site_logo | brand_name, niche, style, primary_color, mood | icon_concept, neutral_color, font_tone |
ui_icon | icon_name, icon_purpose, icon_style, primary_color, size_context | stroke_weight, corner_style |
featured_blog_image | article_title, keywords, primary_color, image_style, tone | visual_metaphor, focal_subject |
social_og_image | brand_name, page_title, tagline, primary_color, bg_style | domain_text, logo_position |
favicon_app_icon | brand_symbol, shape, primary_color, secondary_color | border_style, padding_ratio |
Defaults
Use defaults when optional fields are not provided:
neutral_color:slate grayfont_tone:clean modern sans-serifstroke_weight:1.5pxcorner_style:slightly roundedvisual_metaphor: derive from title + keywordsfocal_subject: abstract symbol tied to keyword intentdomain_text: include only if providedlogo_position:bottom-leftborder_style:nonepadding_ratio:12%
Multi-Asset Requests
If a user requests multiple assets in one turn:
- Generate one prompt block per asset type.
- Keep shared brand fields consistent (
brand_name, palette, mood). - Vary only what each artifact needs (size, composition, style constraints).
References
- Prompt templates: references/templates.md
- Registry examples: references/registry-snippets.ts
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
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.

