Agent Skills
› fastclaw-ai/fastclaw
› image-gen
image-gen
GitHub指导在沙箱环境中使用Matplotlib和Pillow生成图表、绘图及图像，并强调通过Base64内联方式展示结果。
Trigger Scenarios
用户要求绘制图表或数据可视化
用户要求创建或编辑图像
Install
npx skills add fastclaw-ai/fastclaw --skill image-gen -g -y
SKILL.md
Frontmatter
{
"name": "image-gen",
"metadata": {
"fastclaw": {
"always": false
}
},
"description": "Generate images, charts, plots, and visualizations. Use when the user asks to draw, plot, chart, visualize data, or create images."
}
Image Generation Skill
Generate images in the headless sandbox using Python libraries.
Available Libraries
Matplotlib (charts, plots, graphs)
import matplotlib
matplotlib.use('Agg') # REQUIRED: headless backend
import matplotlib.pyplot as plt
plt.figure(figsize=(10, 6))
plt.plot([1, 2, 3], [1, 4, 9])
plt.title('My Chart')
plt.savefig('/tmp/chart.png', dpi=150, bbox_inches='tight')
PIL/Pillow (drawing, image manipulation)
from PIL import Image, ImageDraw, ImageFont
img = Image.new('RGB', (400, 300), 'white')
draw = ImageDraw.Draw(img)
draw.rectangle([50, 50, 350, 250], outline='black', width=2)
img.save('/tmp/drawing.png')
CRITICAL: Displaying Images to User
After generating an image, always output it as inline base64 markdown so it renders in chat:
import base64
with open('/tmp/output.png', 'rb') as f:
b64 = base64.b64encode(f.read()).decode()
print(f'')
Do this in the same exec call as the image generation. The markdown image tag will render directly in the chat.
Guidelines
- Always use
matplotlib.use('Agg')before importing pyplot - NEVER use turtle, tkinter, pygame, or any GUI library
- Save images to /tmp/ directory
- Always output base64 inline — don't just report the file path
- For charts: use clear labels, titles, and legends
- Install missing packages with pip if needed:
pip install matplotlib pillow
Version History
- beee30c Current 2026-07-25 08:17
