pixel-art
Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.
Best use case
pixel-art is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.
Teams using pixel-art should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/pixel-art/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How pixel-art Compares
| Feature / Agent | pixel-art | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
ChatGPT vs Claude for Agent Skills
Compare ChatGPT and Claude for AI agent skills across coding, writing, research, and reusable workflow execution.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
# Pixel Art SVG Generator
Create a pixel art SVG illustration: $ARGUMENTS
## Design Principles
### Pixel Grid
- Each "pixel" is a `<rect>` with width/height of 7px
- Grid spacing: 7px (no gaps between pixels)
- Characters are typically 8-10 pixels wide, 8-12 pixels tall
- Use `<g transform="translate(x,y)">` to position and reuse character groups
### Color Palette
Keep it simple — 3-5 colors per character:
- **Skin**: `#FFDAB9` (light), `#E8967A` / `#D4956A` (blush/shadow)
- **Eyes**: `#333`
- **Hair**: `#8B5E3C` (brown), `#2C2C2C` (black), `#FFD700` (blonde), `#C0392B` (red)
- **Clothes**: use project's brand color (e.g. `#4A9EDA` for blue, `#74AA63` for green)
- **Shoes/pants**: `#444`
- **Accessories**: `#555` (glasses frames), `#FFD700` (crown)
### Character Template (7px grid)
```
Row 0 (hair top): 4 pixels centered
Row 1 (hair): 6 pixels wide
Row 2 (face top): 6 pixels — all skin
Row 3 (eyes): 6 pixels — skin, eye, skin, skin, eye, skin
Row 4 (mouth): 6 pixels — skin, skin, mouth, mouth, skin, skin
Row 5 (body top): 8 pixels — hand, 6 shirt, hand
Row 6 (body): 6 pixels — all shirt
Row 7 (legs): 2+2 pixels — with gap in middle
```
### Scene Composition
#### Chat Dialogue Layout (like our hero image)
- Two characters on left/right sides, vertically centered
- Chat bubbles between them, alternating left/right
- Bubble tails point toward the speaking character
- Arrows between bubbles show direction of communication
- Use `orient="auto"` markers for arrow heads
- Bottom: tagline or decoration
#### Single Character with Label
- Character centered
- Label text below
- Optional: speech bubble above
#### Group Scene
- Characters spaced evenly
- Optional: ground line, background elements
- Keep viewBox tight — no wasted space
### SVG Structure
```xml
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 W H" font-family="monospace">
<defs>
<!-- Arrow markers if needed -->
</defs>
<rect width="W" height="H" fill="#fafbfc" rx="12"/> <!-- Background -->
<!-- Characters via <g transform="translate(...)"> -->
<!-- Dialogue bubbles: <rect> + <polygon> tail + <text> -->
<!-- Arrows: <line> with marker-end -->
<!-- Labels: <text> with text-anchor="middle" -->
</svg>
```
### Chat Bubble Recipe
```xml
<!-- Blue bubble (left character speaks) -->
<rect x="110" y="29" width="280" height="26" fill="#e8f4fd" stroke="#4a9eda" stroke-width="1.5" rx="8"/>
<!-- Tail pointing left toward character -->
<polygon points="108,41 99,47 108,46" fill="#e8f4fd" stroke="#4a9eda" stroke-width="1.5"/>
<rect x="107" y="40" width="3" height="7" fill="#e8f4fd"/> <!-- covers stroke at junction -->
<text x="123" y="46" font-size="13px">📄 Message here</text>
<!-- Orange bubble (right character responds) -->
<rect x="490" y="71" width="280" height="26" fill="#fdf2e8" stroke="#da8a4a" stroke-width="1.5" rx="8"/>
<!-- Tail pointing right toward character -->
<polygon points="772,83 781,89 772,88" fill="#fdf2e8" stroke="#da8a4a" stroke-width="1.5"/>
<rect x="770" y="82" width="3" height="7" fill="#fdf2e8"/>
<text x="503" y="88" font-size="13px">🤔 Response here</text>
```
### Arrow Recipe
```xml
<defs>
<marker id="ar" markerWidth="8" markerHeight="6" refX="8" refY="3" orient="auto">
<polygon points="0 0, 8 3, 0 6" fill="#4a9eda"/>
</marker>
</defs>
<!-- Right arrow (→): x1 < x2 -->
<line x1="392" y1="42" x2="465" y2="42" stroke="#4a9eda" stroke-width="2" marker-end="url(#ar)"/>
<!-- Left arrow (←): x1 > x2 -->
<line x1="488" y1="84" x2="420" y2="84" stroke="#da8a4a" stroke-width="2" marker-end="url(#ar-o)"/>
```
## Workflow
### Step 1: Understand the Request
- What characters/objects to draw?
- What's the scene? (dialogue, portrait, group, diagram)
- What colors/brand to match?
- What size? (compact for badge, wide for README hero)
### Step 2: Generate SVG
- Write to a temp file or project directory
- Open with `open <file.svg>` for preview
- Keep viewBox tight — measure actual content bounds
### Step 3: Iterate with User
- User provides feedback on screenshot
- Common fixes: overlap, arrow direction, spacing, sizing
- Use `Edit` for small tweaks, `Write` for major redesigns
- Typical: 2-4 iterations to get it right
### Step 4: Finalize
- Ensure no personal info in the SVG
- Clean up: remove unused defs, tighten viewBox
- Suggest adding to README: ``
## Common Pitfalls
- **Arrow direction**: `orient="auto"` follows line direction. Line going right→left = arrowhead points left
- **Bubble overlap**: keep 38-44px vertical spacing between rows
- **Text overflow**: monospace 13px ≈ 7.8px/char, emoji ≈ 14px. Measure before setting bubble width
- **Character overlap with bubbles**: keep character x-zone and bubble x-zone separated by ≥10px
- **viewBox too large**: match viewBox to actual content, add ~10px padding
- **Tail stroke artifact**: always add a small `<rect>` at the bubble-tail junction to cover the stroke lineRelated Skills
vast-gpu
Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware.
system-profile
Profile a target (script, process, GPU, memory, interconnect) using external tools and code instrumentation. Produces structured performance reports with actionable recommendations. Use when user says "profile", "benchmark", "bottleneck", or wants performance analysis.
training-check
Periodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
serverless-modal
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
semantic-scholar
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.
run-experiment
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
result-to-claim
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
research-review
Get a deep critical review of research from GPT via Codex MCP. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
research-refine
Turn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-5.4 review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
research-refine-pipeline
Run an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
research-pipeline
Full research pipeline: Workflow 1 (idea discovery) → implementation → Workflow 2 (auto review loop). Goes from a broad research direction all the way to a submission-ready paper. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
research-lit
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.