Skills for Real Engineers. Straight from my .agents directory.
39 skills
sn-da-image-caption
Agent skill from
图片理解与数据提取 skill。当图片文件（.png/.jpg/.jpeg/.gif/.webp/.bmp）是主要输入且用户需要理解、提取数据或分析图片内容时使用。提供预配置的 caption 脚本（scripts/caption.py），通过 vision 模型将图片转为文本描述，无需额外配置 API Key。覆盖：(1) 通过 scripts/caption.py 对图表/表格/截图/流程图进行 caption，(2) 将 caption 文本解析为结构化 DataFrame，(3) 基于提取数据重新生成可视化图表，(4) 导出为 Excel/CSV。**遇到以下任一情况就主动使用本 skill，不要自行猜测图片内容**：①用户出现触发词：图片分析 / 图表提取 / 表格识别 / OCR / 图片描述 / 截图分析 / 图表数据 / 提取图片中的数据 / 图片转表格 / 识别图片 / image caption / extract data from image / chart analysis / table OCR；②用户上传或指定了图片文件（.png / .jpg / .jpeg / .gif / .webp / .bmp）并要求理解、提取数据或分析内容；③任务需要从图表截图、表格截图、UI 截图、流程图中提取结构化信息；④用户要求将图片中的数据转为 Excel/CSV 或重新生成可视化图表。仅不用于：图片编辑（裁剪、滤镜、缩放）、图片生成、不含数据的风景/人物照片描述。
How to install sn-da-image-caption
install sn-da-image-caption
# install the SenseNova-Skills pack with the skills CLI
npx skills add OpenSenseNova/SenseNova-Skills# or add only this skill to Claude Code: copy the folder
skills/sn-da-image-caption/
# into
~/.claude/skills/sn-da-image-caption/ (all projects)
.claude/skills/sn-da-image-caption/ (one project)
1# Image Caption Analysis — 图片描述与数据提取23## Overview45Analyze, extract data from, or understand image files (.png, .jpg, .jpeg, .gif, .webp, .bmp). The core workflow:671. Run `scripts/caption.py` to get a text description of the image82. Parse the description into structured data (DataFrame, etc.)93. Analyze, visualize, or export1011## scripts/caption.py — Image Caption1213The 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.1415### Usage1617```bash18# Basic — get text description19python3 scripts/caption.py /mnt/data/image.png2021# Custom prompt — guide what to extract22python3 scripts/caption.py /mnt/data/chart.png --prompt "提取所有数值，Markdown 表格格式"2324# JSON output — includes detected type, usage stats, cache info25python3 scripts/caption.py /mnt/data/image.png --json2627# Batch — process all images in a directory28python3 scripts/caption.py /mnt/data/images/ --batch --output /mnt/data/captions.json2930# Override model (optional)31python3 scripts/caption.py /mnt/data/image.png --model gemini-3.1-flash-lite-preview32```3334### Options3536| Option | Description |37|--------|------------|38| `--prompt, -p` | Custom prompt (overrides auto-detection) |39| `--model, -m` | Vision model (default: sensenova-6.8-flash-lite) |40| `--json` | Output structured JSON instead of plain text |41…
Excerpt shown under the repository's MIT license.
More skills in SenseNova-Skills
Keep exploring
Similar skill repositories
An agentic skills framework & software development methodology that works.
15 skills
Public repository for Agent Skills
20 skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
CCCXCUGH6 skills
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
CCCXGHGM+135 skills
Production-grade engineering skills for AI coding agents.
CCCXCU25 skills