# Figure Analysis Skill

> Analyze generated figures using a Vision-Language Model (VLM)

- Skill: `wangjian169/figure-analysis-skill` (Agent Skill, multi-file: 4 files)
- Install (CLI): `npx skillmds@latest add wangjian169/figure-analysis-skill`
- Raw SKILL.md: https://api.skillmd.com/api/skills/wangjian169/figure-analysis-skill/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: wangjian169 (https://skillmd.com/u/wangjian169)
- Updated: 2026-09-22
- Page: https://skillmd.com/skills/wangjian169/figure-analysis-skill

---


## Figure Analysis (Vision-Language Model)

Use a Vision-Language Model (VLM) to automatically analyze generated figures and produce
structured text interpretations. The backend uses Qwen3-VL via the DashScope API.

### Usage

```bash
python skills/figure_analysis_skill/Scripts/figure_analysis.py \
  --task "Sensitivity results: imperv (mu*=1.03), zero_imperv (mu*=0.87), slope (mu*=0.36). Calibration NSE=0.948, Validation NSE=0.820. Analyze the figures: 1) fit quality in calibration and validation events; 2) subcatchment-level insights from the parameter bar chart (which subcatchments changed most, spatial heterogeneity); 3) overall calibration assessment." \
  --figures <fig1.png> <fig2.png>
```

| Parameter | Description | Default |
|-----------|-------------|---------|
| --task | Natural language task description for the VLM | (required) |
| --figures | Paths to image files to analyze (one or more) | (required) |

### Output

Prints the VLM's text analysis response to stdout.