aboylabs/ai-agent-skills / skills/creative/visual-assets-generation
visual-assets-generation
VerifiedGenerate visual assets (ASCII art, diagrams, banners) for repos and documentation
Visual Assets Generation
Generate visual assets for repositories and documentation — ASCII art, diagrams, banners, social cards.
When to Use
- User asks "bikin gambar", "buat visual", "generate banner"
- Repo needs visual improvements (README header, architecture diagram)
- Social media sharing (Twitter/LinkedIn cards)
- Documentation needs diagrams (workflow, architecture, comparison)
Workflow
Step 1: Create ASCII Preview First ⭐
ALWAYS create TXT preview before generating real images:
Why:
- Faster iteration (no image generation wait)
- User can review before committing
- Works everywhere (no image dependencies)
- Easy to edit and refine
Format:
VISUAL_ASSETS_PREVIEW.txt
├── ASCII Art Banner
├── Architecture Diagram
├── Workflow Diagram
├── Comparison Tables
├── Folder Structure
├── Performance Metrics
├── Quick Start Guide
└── Social Media Preview
Step 2: Generate Comprehensive Preview
Include multiple visual types in one file:
-
ASCII Art Banner/Logo
- Use box-drawing characters (╔═╗║╚╝)
- Use block characters (█▀▄▌▐)
- Include tagline and URL
-
Architecture Diagram
- System components
- Data flow (arrows: → ↓ ↑ ←)
- Integration points
-
Workflow Diagram
- Step-by-step process
- Decision points
- Outcomes
-
Comparison Tables
- Feature comparison
- Before/After
- Options comparison
-
Folder Structure
- Tree view (├── └── │)
- Annotations
- Purpose explanations
-
Performance Metrics
- Bar charts (█ blocks)
- Speed comparisons
- Size comparisons
-
Quick Start Guide
- Installation steps
- Usage examples
- Success criteria
-
Social Media Preview
- Title + tagline
- Key features (emoji bullets)
- Call to action
- URL
Step 3: Offer Options
After creating preview, present choices:
Option A: Use ASCII Directly
# Add to README.md
cat VISUAL_ASSETS_PREVIEW.txt >> README.md
- ✅ Works everywhere
- ✅ No dependencies
- ✅ Easy to maintain
- ❌ Less visually appealing
Option B: Convert to Real Images
- SVG architecture diagram (dark theme)
- PNG social card (1200x630)
- PNG banner (for README header)
- ✅ Professional appearance
- ✅ Better for social sharing
- ❌ Requires image generation
- ❌ Harder to maintain
Option C: Both ⭐ RECOMMENDED
- ASCII in README (works everywhere)
- Real images in
/assetsfolder - Best of both worlds
Templates
ASCII Art Banner
Box-drawing style:
┌─────────────────────────────────────────────────────────────┐
│ │
│ PROJECT NAME │
│ Tagline goes here │
│ │
└─────────────────────────────────────────────────────────────┘
Block character style:
███╗ ███╗██╗ ██╗ ██████╗ ██████╗ ██████╗ ██╗███████╗ ██████╗████████╗
████╗ ████║╚██╗ ██╔╝ ██╔══██╗██╔══██╗██╔═══██╗ ██║██╔════╝██╔════╝╚══██╔══╝
██╔████╔██║ ╚████╔╝ ██████╔╝██████╔╝██║ ██║ ██║█████╗ ██║ ██║
██║╚██╔╝██║ ╚██╔╝ ██╔═══╝ ██╔══██╗██║ ██║██ ██║██╔══╝ ██║ ██║
██║ ╚═╝ ██║ ██║ ██║ ██║ ██║╚██████╔╝╚█████╔╝███████╗╚██████╗ ██║
╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═╝ ╚═════╝ ╚════╝ ╚══════╝ ╚═════╝ ╚═╝
Architecture Diagram
USER
│
│ Request
▼
┌────────────────────────────────┐
│ │
│ COMPONENT A │
│ (Description) │
│ │
└────────────────────────────────┘
│
┌────────────────┴────────────────┐
│ │
▼ ▼
┌───────────────────┐ ┌───────────────────┐
│ │ │ │
│ COMPONENT B │ │ COMPONENT C │
│ (Description) │ │ (Description) │
│ │ │ │
└───────────────────┘ └───────────────────┘
│ │
└────────────────┬────────────────┘
│
▼
┌────────────────────────────────┐
│ │
│ OUTPUT │
│ (Result) │
│ │
└────────────────────────────────┘
Comparison Table
┌──────────────────┬─────────────┬─────────────┬─────────────┐
│ │ OPTION A │ OPTION B │ OPTION C │
├──────────────────┼─────────────┼─────────────┼─────────────┤
│ Feature 1 │ ✅ Yes │ ❌ No │ ✅ Yes │
│ Feature 2 │ ❌ No │ ✅ Yes │ ✅ Yes │
│ Speed │ Fast │ Slow │ Medium │
│ Cost │ Free │ $10/mo │ Free │
└──────────────────┴─────────────┴─────────────┴─────────────┘
Folder Structure
project-root/
├── src/ # Source code
│ ├── components/ # React components
│ └── utils/ # Utility functions
├── tests/ # Test suite
│ ├── unit/ # Unit tests
│ └── integration/ # Integration tests
├── docs/ # Documentation
│ ├── README.md # Main docs
│ └── API.md # API reference
├── .github/ # GitHub config
│ ├── workflows/ # CI/CD
│ └── ISSUE_TEMPLATE/ # Issue templates
└── package.json # Dependencies
Performance Metrics
┌─────────────────────────────────────────────────────────────┐
│ │
│ SPEED COMPARISON │
│ │
│ Option A: ████ 2ms │
│ Option B: ████████████████████████████ 1000ms │
│ │
│ Speed Improvement: 500x faster │
│ │
└─────────────────────────────────────────────────────────────┘
Pitfalls
❌ DON'T: Generate Images Without Preview
Problem: User can't review before committing, wastes time if design needs changes.
Solution:
- Create TXT preview first
- Get user approval
- Then generate real images
❌ DON'T: Use Complex Unicode That Breaks
Problem: Some terminals don't support all Unicode characters.
Solution:
- Test in common terminals (bash, zsh, Windows Terminal)
- Use widely-supported box-drawing characters
- Provide fallback ASCII version
❌ DON'T: Make Diagrams Too Wide
Problem: Diagrams break on narrow terminals or mobile GitHub.
Solution:
- Keep width ≤ 80 characters (safe)
- Max 120 characters (acceptable)
- Test on mobile GitHub view
❌ DON'T: Forget to Include File Header
Problem: User doesn't know what the file contains or how to use it.
Solution:
# PROJECT NAME
# Visual Assets Preview
This file contains ASCII art previews for:
1. Banner/Logo
2. Architecture Diagram
3. Workflow Diagram
[...]
Generated: 2026-05-12
Repo: https://github.com/user/repo
Examples
Example 1: Simple Banner
Input: "bikin banner untuk repo mnemosyne-obsidian"
Output:
███╗ ███╗███╗ ██╗███████╗███╗ ███╗ ██████╗ ███████╗██╗ ██╗███╗ ██╗███████╗
████╗ ████║████╗ ██║██╔════╝████╗ ████║██╔═══██╗██╔════╝╚██╗ ██╔╝████╗ ██║██╔════╝
██╔████╔██║██╔██╗ ██║█████╗ ██╔████╔██║██║ ██║███████╗ ╚████╔╝ ██╔██╗ ██║█████╗
██║╚██╔╝██║██║╚██╗██║██╔══╝ ██║╚██╔╝██║██║ ██║╚════██║ ╚██╔╝ ██║╚██╗██║██╔══╝
██║ ╚═╝ ██║██║ ╚████║███████╗██║ ╚═╝ ██║╚██████╔╝███████║ ██║ ██║ ╚████║███████╗
╚═╝ ╚═╝╚═╝ ╚═══╝╚══════╝╚═╝ ╚═╝ ╚═════╝ ╚══════╝ ╚═╝ ╚═╝ ╚═══╝╚══════╝
+ OBSIDIAN + GITHUB BACKUP
500x Faster Recall • Rich Markdown Notes
https://github.com/user/mnemosyne-obsidian
Example 2: Architecture Diagram
Input: "bikin diagram arsitektur untuk integration tool"
Output:
USER
│
│ "Show VPS cleanup"
▼
┌────────────────────────────────┐
│ │
│ HERMES AGENT │
│ (AI Assistant) │
│ │
└────────────────────────────────┘
│
┌────────────────┴────────────────┐
│ │
▼ ▼
┌───────────────────────┐ ┌───────────────────────┐
│ │ │ │
│ MNEMOSYNE │ │ OBSIDIAN │
│ (Fast Recall) │ │ (Rich Content) │
│ │ │ │
│ • SQLite DB (3.7MB) │ │ • Markdown files │
│ • 500x faster │ │ • Wikilinks │
│ • Temporal scoring │ │ • Database views │
│ │ │ │
└───────────────────────┘ └───────────────────────┘
│ │
└────────────────┬────────────────┘
│
▼
┌────────────────────────────────┐
│ │
│ GITHUB BACKUP │
│ (Version Control) │
│ │
└────────────────────────────────┘
Example 3: Comprehensive Preview File
Input: "bikin semua visual untuk repo"
Output: VISUAL_ASSETS_PREVIEW.txt with:
- ASCII art banner
- Architecture diagram
- Workflow diagram (5 steps)
- Features comparison table
- Installation comparison
- Folder structure
- Performance metrics
- Quick start guide
- Bundled skills list
- Badges & status
- Social media preview
Size: ~30 KB
Time: 5 minutes
User can review: All visuals in one file
User Preference Pattern (from session 2026-05-12)
User workflow:
- Asks for visual: "bikin gambar/banner/diagram"
- Wants preview first: "buatkan contohnya dulu dalam file txt"
- Reviews preview
- Decides: use ASCII, generate images, or both
Key insight:
- User prefers TXT preview before committing to images
- Allows review and iteration without image generation overhead
- Can decide format after seeing content
Related Skills
architecture-diagram— Dark-themed SVG diagramsascii-art— ASCII art generation (pyfiglet, cowsay)excalidraw— Hand-drawn style diagramssketch— HTML mockups for social cards
References
- Box-drawing characters: https://en.wikipedia.org/wiki/Box-drawing_character
- Block elements: https://en.wikipedia.org/wiki/Block_Elements
- ASCII art generators: https://patorjk.com/software/taag/
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-changelog-updatemorluto/reaPrepare or rewrite REA release changelogs and GitHub release notes from pinned Git history, with verified contributor thanks and Release Please synchronization. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| academy-guideanthropics/skillsStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching courses, tutorials, and use cases from Claude Academy (academy.claude.com), Anthropic's learning hub. Trigger on: "how do I", "how can I", "getting started with", "what can Claude do", "teach me", "learn to use"; questions about artifacts, projects, skills, plugins, connectors, MCP; requests about rolling Claude out to a team, class, or organization; and any ask for training materials, onboarding content, or learning resources. Use it when the user is learning how to use a feature or product — not when they are mid-task and just want the task done. This skill composes with other skills: after consulting product documentation to answer how a Claude feature works, also check here for a matching course or tutorial — a docs-grounded answer and an Academy recommendation belong together. Only recommend on a strong match; never invent Academy content. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| claude-apianthropics/skillsReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because it "looks like a one-liner" — whenever: the prompt names Claude/Anthropic in any form (Claude, Anthropic, Fable, Opus, Sonnet, Haiku, `anthropic`, `@anthropic-ai`, `claude-*`, `us.anthropic.*`, `[1m]`); the user asks about an LLM (pricing/model choice/limits/caching) — never answer from memory; OR the task is LLM-shaped with provider unstated (agent/MCP/tool-definition/multi-agent/RAG/LLM-judge/computer-use; generate/summarize/extract/classify/rewrite/converse over NL; debugging refusals/cutoffs/streaming/tool-calls/tokens). SKIP only when another provider is being worked on (overrides all triggers): OpenAI/GPT/Gemini/Llama/Mistral/Cohere/Ollama named in the query; OR `grep -rE 'openai|langchain_openai|google.generativeai|genai|mistralai|cohere|ollama'` over the project hits (run this grep FIRST if no provider named — don't Read the file). | Stars: 198k | Updated | Claude CodeCodex | Unverified | Install |
| doc-coauthoringanthropics/skillsGuide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |