pip install pymupdf pillow

web/
└── <pdf_stem>_<timestamp>/
    ├── outline.json        ← structured web plan (WebPlan schema)
    ├── crops/              ← locally-saved cropped images
    │   ├── fig_arch_crop.png
    │   ├── table_results_crop.png
    │   └── ...
    └── index.html          ← the website

import os, datetime
pdf_stem = os.path.splitext(os.path.basename(pdf_path))[0]
timestamp = datetime.datetime.now().strftime("%Y%m%d_%H%M%S")
out_dir = os.path.join(workspace, "web", f"{pdf_stem}_{timestamp}")

mkdir -p "<out_dir>/crops"

pdf_stem=$(basename "$ARGUMENTS" .pdf)
curl -L -o "/tmp/${pdf_stem}.pdf" "$ARGUMENTS"

python {SKILL_DIR}/scripts/pdf_to_images.py "<pdf_path>" --dpi 120

[{"page": 1, "path": "/abs/path/page_001.png"}, ...]

{
  "project_title": "Paper Title",
  "lang": "English",
  "authors": ["Author One", "Author Two"],
  "sections_plan": [
    {
      "section_index": 1,
      "section_id": "hero",
      "title": "Hero",
      "content": "Title, authors, venue, teaser figure description",
      "required_images": [
        {
          "url": "<local_page_path_from_phase1>",
          "visual_description": "Figure 1: teaser showing input-output examples",
          "usage_reason": "Hero section visual to immediately show the paper's output"
        }
      ]
    }
  ]
}

Agent tool call:
  description: "Grounding crop page N"
  prompt: |
    You are a visual grounding and cropping assistant. Your task is to precisely
    locate specified visual elements in a page image and crop them out.

    ## Grounding method

    Use visual grounding to locate each target:
    1. Read the source image using the Read tool to view it
    2. Identify the target element described below
    3. Determine its bounding box as normalized coordinates in the 0–999 range:
       - 0 = left/top edge of the image
       - 999 = right/bottom edge of the image
       - These are thousandths, NOT pixels, NOT percentages (0–100)
       - Format: [x1, y1, x2, y2] where (x1,y1) is top-left, (x2,y2) is bottom-right
       - Example: [0, 0, 500, 500] = top-left quarter of the image
    4. Be precise: tightly bound the target element with a small margin (~10–20 units)
       around it. Do NOT crop too wide or too narrow.

    ## Source image
    <page_image_path>

    ## Crops needed

    For each crop below, first do grounding (locate the element), then crop:

    1. Name: "<descriptive_name>"
       Target: "<visual_description from outline.json>"
       Context: "<usage_reason from outline.json>"

    ## Crop command

    After determining the bounding box [X1, Y1, X2, Y2] for each target, run:
    ```bash
    python <SKILL_DIR>/scripts/crop.py \
        --path "<page_image_path>" \
        --box X1 Y1 X2 Y2 \
        --name "<crop_name>" \
        --out-dir "<out_dir>/crops"
    ```

    ## Verification

    After each crop, READ the output image to visually verify the correct region
    was captured. If the crop missed the target or is too wide/narrow, adjust the
    coordinates and re-run crop.py.

    ## Output

    Report the final results as a list:
    - crop_name: <name>, file: <output_filename>, box: [X1, Y1, X2, Y2]

python3 -c "
from PIL import Image; import os, json
d = '<out_dir>/crops'
sizes = {}
for f in sorted(os.listdir(d)):
    if f.endswith('.png'):
        w, h = Image.open(os.path.join(d, f)).size
        sizes[f] = {'width': w, 'height': h, 'aspect': round(w/h, 2)}
print(json.dumps(sizes, indent=2))
"

python {SKILL_DIR}/scripts/generate_web.py \
    --html-file /tmp/website.html \
    --title "<paper title>" \
    --out-dir "<out_dir>/"