@farazirfan/costar-server-executor 1.7.37 → 1.7.39

package/skills/pdf/scripts/extract_form_structure.py

@@ -0,0 +1,124 @@
+#!/usr/bin/env python3
+"""
+Extract form structure from a non-fillable PDF.
+
+This script analyzes the PDF to find:
+- Text labels with their exact coordinates
+- Horizontal lines (row boundaries)
+- Checkboxes (small rectangles)
+
+Output: A JSON file with the form structure that can be used to generate
+accurate field coordinates for filling.
+
+Usage: python extract_form_structure.py <input.pdf> <output.json>
+"""
+
+import json
+import sys
+import pdfplumber
+
+
+def extract_form_structure(pdf_path):
+    """Extract structural elements from a PDF form."""
+    structure = {
+        "pages": [],
+        "labels": [],
+        "lines": [],
+        "checkboxes": [],
+        "row_boundaries": []
+    }
+
+    with pdfplumber.open(pdf_path) as pdf:
+        for page_num, page in enumerate(pdf.pages, 1):
+            # Page info
+            structure["pages"].append({
+                "page_number": page_num,
+                "width": float(page.width),
+                "height": float(page.height)
+            })
+
+            # Extract text labels with positions
+            words = page.extract_words()
+            for word in words:
+                structure["labels"].append({
+                    "page": page_num,
+                    "text": word["text"],
+                    "x0": round(float(word["x0"]), 1),
+                    "top": round(float(word["top"]), 1),
+                    "x1": round(float(word["x1"]), 1),
+                    "bottom": round(float(word["bottom"]), 1)
+                })
+
+            # Extract horizontal lines (row separators)
+            for line in page.lines:
+                # Horizontal lines span most of page width
+                if abs(float(line["x1"]) - float(line["x0"])) > page.width * 0.5:
+                    structure["lines"].append({
+                        "page": page_num,
+                        "y": round(float(line["top"]), 1),
+                        "x0": round(float(line["x0"]), 1),
+                        "x1": round(float(line["x1"]), 1)
+                    })
+
+            # Extract checkboxes (small square rectangles)
+            for rect in page.rects:
+                width = float(rect["x1"]) - float(rect["x0"])
+                height = float(rect["bottom"]) - float(rect["top"])
+                # Checkboxes are typically 5-15 points square
+                if 5 <= width <= 15 and 5 <= height <= 15 and abs(width - height) < 2:
+                    structure["checkboxes"].append({
+                        "page": page_num,
+                        "x0": round(float(rect["x0"]), 1),
+                        "top": round(float(rect["top"]), 1),
+                        "x1": round(float(rect["x1"]), 1),
+                        "bottom": round(float(rect["bottom"]), 1),
+                        "center_x": round((float(rect["x0"]) + float(rect["x1"])) / 2, 1),
+                        "center_y": round((float(rect["top"]) + float(rect["bottom"])) / 2, 1)
+                    })
+
+    # Calculate row boundaries from horizontal lines
+    lines_by_page = {}
+    for line in structure["lines"]:
+        page = line["page"]
+        if page not in lines_by_page:
+            lines_by_page[page] = []
+        lines_by_page[page].append(line["y"])
+
+    for page, y_coords in lines_by_page.items():
+        y_coords = sorted(set(y_coords))
+        for i in range(len(y_coords) - 1):
+            structure["row_boundaries"].append({
+                "page": page,
+                "row_top": y_coords[i],
+                "row_bottom": y_coords[i + 1],
+                "row_height": round(y_coords[i + 1] - y_coords[i], 1)
+            })
+
+    return structure
+
+
+def main():
+    if len(sys.argv) != 3:
+        print("Usage: extract_form_structure.py <input.pdf> <output.json>")
+        sys.exit(1)
+
+    pdf_path = sys.argv[1]
+    output_path = sys.argv[2]
+
+    print(f"Extracting structure from {pdf_path}...")
+    structure = extract_form_structure(pdf_path)
+
+    with open(output_path, "w") as f:
+        json.dump(structure, f, indent=2)
+
+    print(f"Found:")
+    print(f"  - {len(structure['pages'])} pages")
+    print(f"  - {len(structure['labels'])} text labels")
+    print(f"  - {len(structure['lines'])} horizontal lines")
+    print(f"  - {len(structure['checkboxes'])} checkboxes")
+    print(f"  - {len(structure['row_boundaries'])} row boundaries")
+    print(f"Saved to {output_path}")
+
+
+if __name__ == "__main__":
+    main()

package/skills/pdf/scripts/fill_fillable_fields.py

@@ -0,0 +1,116 @@
+import json
+import sys
+
+from pypdf import PdfReader, PdfWriter
+
+from extract_form_field_info import get_field_info
+
+
+# Fills fillable form fields in a PDF. See FORMS.md.
+
+
+def fill_pdf_fields(input_pdf_path: str, fields_json_path: str, output_pdf_path: str):
+    with open(fields_json_path) as f:
+        fields = json.load(f)
+    # Group by page number.
+    fields_by_page = {}
+    for field in fields:
+        if "value" in field:
+            field_id = field["field_id"]
+            page = field["page"]
+            if page not in fields_by_page:
+                fields_by_page[page] = {}
+            fields_by_page[page][field_id] = field["value"]
+    
+    reader = PdfReader(input_pdf_path)
+
+    has_error = False
+    field_info = get_field_info(reader)
+    fields_by_ids = {f["field_id"]: f for f in field_info}
+    for field in fields:
+        existing_field = fields_by_ids.get(field["field_id"])
+        if not existing_field:
+            has_error = True
+            print(f"ERROR: `{field['field_id']}` is not a valid field ID")
+        elif field["page"] != existing_field["page"]:
+            has_error = True
+            print(f"ERROR: Incorrect page number for `{field['field_id']}` (got {field['page']}, expected {existing_field['page']})")
+        else:
+            if "value" in field:
+                err = validation_error_for_field_value(existing_field, field["value"])
+                if err:
+                    print(err)
+                    has_error = True
+    if has_error:
+        sys.exit(1)
+
+    writer = PdfWriter(clone_from=reader)
+    for page, field_values in fields_by_page.items():
+        writer.update_page_form_field_values(writer.pages[page - 1], field_values, auto_regenerate=False)
+
+    # This seems to be necessary for many PDF viewers to format the form values correctly.
+    # It may cause the viewer to show a "save changes" dialog even if the user doesn't make any changes.
+    writer.set_need_appearances_writer(True)
+    
+    with open(output_pdf_path, "wb") as f:
+        writer.write(f)
+    
+    print(f"PDF form filled and saved to {output_pdf_path}")
+
+
+def validation_error_for_field_value(field_info, field_value):
+    field_type = field_info["type"]
+    field_id = field_info["field_id"]
+    if field_type == "checkbox":
+        checked_val = field_info["checked_value"]
+        unchecked_val = field_info["unchecked_value"]
+        if field_value != checked_val and field_value != unchecked_val:
+            return f'ERROR: Invalid value "{field_value}" for checkbox field "{field_id}". The checked value is "{checked_val}" and the unchecked value is "{unchecked_val}"'
+    elif field_type == "radio_group":
+        option_values = [opt["value"] for opt in field_info["radio_options"]]
+        if field_value not in option_values:
+            return f'ERROR: Invalid value "{field_value}" for radio group field "{field_id}". Valid values are: {option_values}' 
+    elif field_type == "choice":
+        choice_values = [opt["value"] for opt in field_info["choice_options"]]
+        if field_value not in choice_values:
+            return f'ERROR: Invalid value "{field_value}" for choice field "{field_id}". Valid values are: {choice_values}'
+    return None
+
+
+# pypdf (at least version 5.7.0) has a bug when setting the value for a selection list field.
+# In _writer.py around line 966:
+#
+# if field.get(FA.FT, "/Tx") == "/Ch" and field_flags & FA.FfBits.Combo == 0:
+#     txt = "\n".join(annotation.get_inherited(FA.Opt, []))
+#
+# The problem is that for selection lists, `get_inherited` returns a list of two-element lists like
+# [["value1", "Text 1"], ["value2", "Text 2"], ...]
+# This causes `join` to throw a TypeError because it expects an iterable of strings.
+# The horrible workaround is to patch `get_inherited` to return a list of the value strings.
+# We call the original method and adjust the return value only if the argument to `get_inherited`
+# is `FA.Opt` and if the return value is a list of two-element lists.
+def monkeypatch_pydpf_method():
+    from pypdf.generic import DictionaryObject
+    from pypdf.constants import FieldDictionaryAttributes
+
+    original_get_inherited = DictionaryObject.get_inherited
+
+    def patched_get_inherited(self, key: str, default = None):
+        result = original_get_inherited(self, key, default)
+        if key == FieldDictionaryAttributes.Opt:
+            if isinstance(result, list) and all(isinstance(v, list) and len(v) == 2 for v in result):
+                result = [r[0] for r in result]
+        return result
+
+    DictionaryObject.get_inherited = patched_get_inherited
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 4:
+        print("Usage: fill_fillable_fields.py [input pdf] [field_values.json] [output pdf]")
+        sys.exit(1)
+    monkeypatch_pydpf_method()
+    input_pdf = sys.argv[1]
+    fields_json = sys.argv[2]
+    output_pdf = sys.argv[3]
+    fill_pdf_fields(input_pdf, fields_json, output_pdf)

package/skills/pdf/scripts/fill_pdf_form_with_annotations.py

@@ -0,0 +1,136 @@
+import json
+import sys
+
+from pypdf import PdfReader, PdfWriter
+from pypdf.annotations import FreeText
+
+
+# Fills a PDF by adding text annotations defined in `fields.json`. See FORMS.md.
+
+
+def transform_from_image_coords(bbox, image_width, image_height, pdf_width, pdf_height):
+    """Transform bounding box from image coordinates to PDF coordinates"""
+    # Image coordinates: origin at top-left, y increases downward
+    # PDF coordinates: origin at bottom-left, y increases upward
+    x_scale = pdf_width / image_width
+    y_scale = pdf_height / image_height
+
+    left = bbox[0] * x_scale
+    right = bbox[2] * x_scale
+
+    # Flip Y coordinates for PDF
+    top = pdf_height - (bbox[1] * y_scale)
+    bottom = pdf_height - (bbox[3] * y_scale)
+
+    return left, bottom, right, top
+
+
+def transform_from_pdf_coords(bbox, pdf_height):
+    """Transform bounding box from pdfplumber coordinates to pypdf coordinates.
+
+    pdfplumber uses y=0 at top, y increases downward (like images).
+    pypdf FreeText expects y=0 at bottom, y increases upward.
+    Both use the same scale (PDF points), so only Y needs flipping.
+    """
+    left = bbox[0]
+    right = bbox[2]
+
+    # bbox is [left, top, right, bottom] where top < bottom (y=0 at top)
+    # pypdf wants [left, bottom, right, top] where bottom < top (y=0 at bottom)
+    pypdf_top = pdf_height - bbox[1]      # flip the "top" value
+    pypdf_bottom = pdf_height - bbox[3]   # flip the "bottom" value
+
+    return left, pypdf_bottom, right, pypdf_top
+
+
+def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path):
+    """Fill the PDF form with data from fields.json"""
+    
+    # `fields.json` format described in FORMS.md.
+    with open(fields_json_path, "r") as f:
+        fields_data = json.load(f)
+    
+    # Open the PDF
+    reader = PdfReader(input_pdf_path)
+    writer = PdfWriter()
+    
+    # Copy all pages to writer
+    writer.append(reader)
+    
+    # Get PDF dimensions for each page
+    pdf_dimensions = {}
+    for i, page in enumerate(reader.pages):
+        mediabox = page.mediabox
+        pdf_dimensions[i + 1] = [mediabox.width, mediabox.height]
+    
+    # Process each form field
+    annotations = []
+    for field in fields_data["form_fields"]:
+        page_num = field["page_number"]
+
+        # Get page dimensions and transform coordinates.
+        page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num)
+        pdf_width, pdf_height = pdf_dimensions[page_num]
+
+        # Detect coordinate system: pdf_width/pdf_height = PDF coords, image_width/image_height = image coords
+        if "pdf_width" in page_info:
+            # PDF coordinates from structure extraction (pdfplumber style)
+            # Only need Y-flip, no scaling
+            transformed_entry_box = transform_from_pdf_coords(
+                field["entry_bounding_box"],
+                float(pdf_height)
+            )
+        else:
+            # Image coordinates - need scaling and Y-flip
+            image_width = page_info["image_width"]
+            image_height = page_info["image_height"]
+            transformed_entry_box = transform_from_image_coords(
+                field["entry_bounding_box"],
+                image_width, image_height,
+                float(pdf_width), float(pdf_height)
+            )
+        
+        # Skip empty fields
+        if "entry_text" not in field or "text" not in field["entry_text"]:
+            continue
+        entry_text = field["entry_text"]
+        text = entry_text["text"]
+        if not text:
+            continue
+        
+        font_name = entry_text.get("font", "Arial")
+        font_size = str(entry_text.get("font_size", 14)) + "pt"
+        font_color = entry_text.get("font_color", "000000")
+
+        # Font size/color seems to not work reliably across viewers:
+        # https://github.com/py-pdf/pypdf/issues/2084
+        annotation = FreeText(
+            text=text,
+            rect=transformed_entry_box,
+            font=font_name,
+            font_size=font_size,
+            font_color=font_color,
+            border_color=None,
+            background_color=None,
+        )
+        annotations.append(annotation)
+        # page_number is 0-based for pypdf
+        writer.add_annotation(page_number=page_num - 1, annotation=annotation)
+        
+    # Save the filled PDF
+    with open(output_pdf_path, "wb") as output:
+        writer.write(output)
+    
+    print(f"Successfully filled PDF form and saved to {output_pdf_path}")
+    print(f"Added {len(annotations)} text annotations")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) != 4:
+        print("Usage: fill_pdf_form_with_annotations.py [input pdf] [fields.json] [output pdf]")
+        sys.exit(1)
+    input_pdf = sys.argv[1]
+    fields_json = sys.argv[2]
+    output_pdf = sys.argv[3]
+    
+    fill_pdf_form(input_pdf, fields_json, output_pdf)

package/skills/pptx/SKILL.md

@@ -0,0 +1,171 @@
+---
+name: pptx
+description: "Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks"
+license: Proprietary. LICENSE.txt has complete terms
+---
+
+# PPTX Skill
+
+## Quick Reference
+
+| Task | Guide |
+|------|-------|
+| Read/analyze content | `python -m markitdown presentation.pptx` |
+| Edit or create from template | Read [editing.md](editing.md) (Python) |
+| Create from scratch | Read [pptxgenjs.md](pptxgenjs.md) (Node.js) |
+
+---
+
+## Reading Content
+
+```bash
+# Text extraction
+python -m markitdown presentation.pptx
+
+# Visual overview
+python scripts/thumbnail.py presentation.pptx
+
+# Raw XML
+python scripts/unpack.py presentation.pptx unpacked/
+```
+
+---
+
+## Editing Workflow
+
+**Read [editing.md](editing.md) for full details.**
+
+1. Analyze template with `thumbnail.py`
+2. Unpack → manipulate slides → edit content → clean → pack
+
+---
+
+## Creating from Scratch
+
+**Read [pptxgenjs.md](pptxgenjs.md) for full details.**
+
+Use when no template or reference presentation is available.
+
+**Important:** PptxGenJS is a **Node.js/JavaScript** library. Create a `.js` file and run it with `node script.js`.
+
+---
+
+## Design Ideas
+
+**Don't create boring slides.** Plain bullets on a white background won't impress anyone. Consider ideas from this list for each slide.
+
+### Before Starting
+
+- **Pick a bold, content-informed color palette**: The palette should feel designed for THIS topic. If swapping your colors into a completely different presentation would still "work," you haven't made specific enough choices.
+- **Dominance over equality**: One color should dominate (60-70% visual weight), with 1-2 supporting tones and one sharp accent. Never give all colors equal weight.
+- **Dark/light contrast**: Dark backgrounds for title + conclusion slides, light for content ("sandwich" structure). Or commit to dark throughout for a premium feel.
+- **Commit to a visual motif**: Pick ONE distinctive element and repeat it — rounded image frames, icons in colored circles, thick single-side borders. Carry it across every slide.
+
+### Color Palettes
+
+Choose colors that match your topic — don't default to generic blue. Use these palettes as inspiration:
+
+| Theme | Primary | Secondary | Accent |
+|-------|---------|-----------|--------|
+| **Midnight Executive** | `1E2761` (navy) | `CADCFC` (ice blue) | `FFFFFF` (white) |
+| **Forest & Moss** | `2C5F2D` (forest) | `97BC62` (moss) | `F5F5F5` (cream) |
+| **Coral Energy** | `F96167` (coral) | `F9E795` (gold) | `2F3C7E` (navy) |
+| **Warm Terracotta** | `B85042` (terracotta) | `E7E8D1` (sand) | `A7BEAE` (sage) |
+| **Ocean Gradient** | `065A82` (deep blue) | `1C7293` (teal) | `21295C` (midnight) |
+| **Charcoal Minimal** | `36454F` (charcoal) | `F2F2F2` (off-white) | `212121` (black) |
+| **Teal Trust** | `028090` (teal) | `00A896` (seafoam) | `02C39A` (mint) |
+| **Berry & Cream** | `6D2E46` (berry) | `A26769` (dusty rose) | `ECE2D0` (cream) |
+| **Sage Calm** | `84B59F` (sage) | `69A297` (eucalyptus) | `50808E` (slate) |
+| **Cherry Bold** | `990011` (cherry) | `FCF6F5` (off-white) | `2F3C7E` (navy) |
+
+### For Each Slide
+
+**Every slide needs a visual element** — image, chart, icon, or shape. Text-only slides are forgettable.
+
+**Layout options:**
+- Two-column (text left, illustration on right)
+- Icon + text rows (icon in colored circle, bold header, description below)
+- 2x2 or 2x3 grid (image on one side, grid of content blocks on other)
+- Half-bleed image (full left or right side) with content overlay
+
+**Data display:**
+- Large stat callouts (big numbers 60-72pt with small labels below)
+- Comparison columns (before/after, pros/cons, side-by-side options)
+- Timeline or process flow (numbered steps, arrows)
+
+**Visual polish:**
+- Icons in small colored circles next to section headers
+- Italic accent text for key stats or taglines
+
+### Typography
+
+**Choose an interesting font pairing** — don't default to Arial. Pick a header font with personality and pair it with a clean body font.
+
+| Header Font | Body Font |
+|-------------|-----------|
+| Georgia | Calibri |
+| Arial Black | Arial |
+| Calibri | Calibri Light |
+| Cambria | Calibri |
+| Trebuchet MS | Calibri |
+| Impact | Arial |
+| Palatino | Garamond |
+| Consolas | Calibri |
+
+| Element | Size |
+|---------|------|
+| Slide title | 36-44pt bold |
+| Section header | 20-24pt bold |
+| Body text | 14-16pt |
+| Captions | 10-12pt muted |
+
+### Spacing
+
+- 0.5" minimum margins
+- 0.3-0.5" between content blocks
+- Leave breathing room—don't fill every inch
+
+### Avoid (Common Mistakes)
+
+- **Don't repeat the same layout** — vary columns, cards, and callouts across slides
+- **Don't center body text** — left-align paragraphs and lists; center only titles
+- **Don't skimp on size contrast** — titles need 36pt+ to stand out from 14-16pt body
+- **Don't default to blue** — pick colors that reflect the specific topic
+- **Don't mix spacing randomly** — choose 0.3" or 0.5" gaps and use consistently
+- **Don't style one slide and leave the rest plain** — commit fully or keep it simple throughout
+- **Don't create text-only slides** — add images, icons, charts, or visual elements; avoid plain title + bullets
+- **Don't forget text box padding** — when aligning lines or shapes with text edges, set `margin: 0` on the text box or offset the shape to account for padding
+- **Don't use low-contrast elements** — icons AND text need strong contrast against the background; avoid light text on light backgrounds or dark text on dark backgrounds
+- **NEVER use horizontal lines to seperate title and body** — use whitespace or background color instead
+
+---
+
+## QA (Required)
+
+**Assume there are problems. Your job is to find them.**
+
+Your first render is almost never correct. Approach QA as a bug hunt, not a confirmation step. If you found zero issues on first inspection, you weren't looking hard enough.
+
+### Content QA
+
+```bash
+python -m markitdown output.pptx
+```
+
+Check for missing content, typos, wrong order.
+
+**When using templates, check for leftover placeholder text:**
+
+```bash
+python -m markitdown output.pptx | grep -iE "xxxx|lorem|ipsum|this.*(page|slide).*layout"
+```
+
+If grep returns results, fix them before declaring success.
+
+---
+
+## Dependencies
+
+- `pip install "markitdown[pptx]"` - text extraction
+- `pip install Pillow` - thumbnail grids
+- `npm install -g pptxgenjs` - creating from scratch