Sn Da Image Caption

This is a vision model wrapper for extracting structured data from images. Drop in a chart screenshot, table, or diagram, and it captions via `scripts/caption.py`, then you parse the markdown table output into a DataFrame for analysis or export. The auto-detection is decent but you'll want custom prompts for precision work. Built-in caching means repeat runs are free, and batch mode handles folders. The repo includes parsing helpers and matplotlib setup with Chinese font config. Main gotcha is large tables can truncate, so you might need to caption in chunks. It's fast, no API key juggling, and the JSON output mode is clean for scripting. Use it when you need numbers out of a PNG, not for photo editing or generation.

install copies · 90 days. Times the install command was copied on this site in the last 90 days, bots filtered.: 9
skills.sh installs: 143
GitHub stars: 6.1K
last updated: Jun 11, 2026

View on GitHub

Install

$ npx -y skills add opensensenova/sensenova-skills --skill sn-da-image-caption --agent claude-code

Installs into .claude/skills of the current project.

Files

Image Caption Analysis — 图片描述与数据提取

Overview

Analyze, extract data from, or understand image files (.png, .jpg, .jpeg, .gif, .webp, .bmp). The core workflow:

Run scripts/caption.py to get a text description of the image
Parse the description into structured data (DataFrame, etc.)
Analyze, visualize, or export

scripts/caption.py — Image Caption

The script converts images to text descriptions via a vision model. Configure via SN_API_KEY (minimum required), or use SN_VISION_API_KEY / SN_VISION_BASE_URL / SN_VISION_MODEL for fine-grained control. See the project environment variable spec for the full fallback chain.

Usage

# Basic — get text description
python3 scripts/caption.py /mnt/data/image.png

# Custom prompt — guide what to extract
python3 scripts/caption.py /mnt/data/chart.png --prompt "提取所有数值，Markdown 表格格式"

# JSON output — includes detected type, usage stats, cache info
python3 scripts/caption.py /mnt/data/image.png --json

# Batch — process all images in a directory
python3 scripts/caption.py /mnt/data/images/ --batch --output /mnt/data/captions.json

SKILL.md on GitHub