plcode-darwin-x64-baseline 2.1.0

package/.plcode/skill/experimental/document-pdf/scripts/fill_pdf_form_with_annotations.py

@@ -0,0 +1,107 @@
+import json
+import sys
+
+from pypdf import PdfReader, PdfWriter
+from pypdf.annotations import FreeText
+
+
+
+
+def transform_from_image_coords(bbox, image_width, image_height, pdf_width, pdf_height):
+    x_scale = pdf_width / image_width
+    y_scale = pdf_height / image_height
+
+    left = bbox[0] * x_scale
+    right = bbox[2] * x_scale
+
+    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):
+    left = bbox[0]
+    right = bbox[2]
+
+    pypdf_top = pdf_height - bbox[1]      
+    pypdf_bottom = pdf_height - bbox[3]   
+
+    return left, pypdf_bottom, right, pypdf_top
+
+
+def fill_pdf_form(input_pdf_path, fields_json_path, output_pdf_path):
+    
+    with open(fields_json_path, "r") as f:
+        fields_data = json.load(f)
+    
+    reader = PdfReader(input_pdf_path)
+    writer = PdfWriter()
+    
+    writer.append(reader)
+    
+    pdf_dimensions = {}
+    for i, page in enumerate(reader.pages):
+        mediabox = page.mediabox
+        pdf_dimensions[i + 1] = [mediabox.width, mediabox.height]
+    
+    annotations = []
+    for field in fields_data["form_fields"]:
+        page_num = field["page_number"]
+
+        page_info = next(p for p in fields_data["pages"] if p["page_number"] == page_num)
+        pdf_width, pdf_height = pdf_dimensions[page_num]
+
+        if "pdf_width" in page_info:
+            transformed_entry_box = transform_from_pdf_coords(
+                field["entry_bounding_box"],
+                float(pdf_height)
+            )
+        else:
+            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)
+            )
+        
+        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")
+
+        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)
+        writer.add_annotation(page_number=page_num - 1, annotation=annotation)
+        
+    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/.plcode/skill/experimental/document-pptx/LICENSE.txt

@@ -0,0 +1,30 @@
+© 2025 Anthropic, PBC. All rights reserved.
+
+LICENSE: Use of these materials (including all code, prompts, assets, files,
+and other components of this Skill) is governed by your agreement with
+Anthropic regarding use of Anthropic's services. If no separate agreement
+exists, use is governed by Anthropic's Consumer Terms of Service or
+Commercial Terms of Service, as applicable:
+https://www.anthropic.com/legal/consumer-terms
+https://www.anthropic.com/legal/commercial-terms
+Your applicable agreement is referred to as the "Agreement." "Services" are
+as defined in the Agreement.
+
+ADDITIONAL RESTRICTIONS: Notwithstanding anything in the Agreement to the
+contrary, users may not:
+
+- Extract these materials from the Services or retain copies of these
+  materials outside the Services
+- Reproduce or copy these materials, except for temporary copies created
+  automatically during authorized use of the Services
+- Create derivative works based on these materials
+- Distribute, sublicense, or transfer these materials to any third party
+- Make, offer to sell, sell, or import any inventions embodied in these
+  materials
+- Reverse engineer, decompile, or disassemble these materials
+
+The receipt, viewing, or possession of these materials does not convey or
+imply any license or right beyond those expressly granted above.
+
+Anthropic retains all right, title, and interest in these materials,
+including all copyrights, patents, and other intellectual property rights.

package/.plcode/skill/experimental/document-pptx/SKILL.md

@@ -0,0 +1,236 @@
+---
+name: pptx
+description: 'Use this skill any time a .pptx file is involved in any way — as input, output, or both. This includes: creating slide decks, pitch decks, or presentations; reading, parsing, or extracting text from any .pptx file (even if the extracted content will be used elsewhere, like in an email or summary); editing, modifying, or updating existing presentations; combining or splitting slide files; working with templates, layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx filename, regardless of what they plan to do with the content afterward. If a .pptx file needs to be opened, created, or touched, use this skill.'
+category: documents
+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)            |
+| Create from scratch          | Read [pptxgenjs.md](pptxgenjs.md)        |
+
+---
+
+## Reading Content
+
+```bash
+# Text extraction
+python -m markitdown presentation.pptx
+
+# Visual overview
+python scripts/thumbnail.py presentation.pptx
+
+# Raw XML
+python scripts/office/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.
+
+---
+
+## 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 accent lines under titles** — these are a hallmark of AI-generated slides; 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.
+
+### Visual QA
+
+**⚠️ USE SUBAGENTS** — even for 2-3 slides. You've been staring at the code and will see what you expect, not what's there. Subagents have fresh eyes.
+
+Convert slides to images (see [Converting to Images](#converting-to-images)), then use this prompt:
+
+```
+Visually inspect these slides. Assume there are issues — find them.
+
+Look for:
+- Overlapping elements (text through shapes, lines through words, stacked elements)
+- Text overflow or cut off at edges/box boundaries
+- Decorative lines positioned for single-line text but title wrapped to two lines
+- Source citations or footers colliding with content above
+- Elements too close (< 0.3" gaps) or cards/sections nearly touching
+- Uneven gaps (large empty area in one place, cramped in another)
+- Insufficient margin from slide edges (< 0.5")
+- Columns or similar elements not aligned consistently
+- Low-contrast text (e.g., light gray text on cream-colored background)
+- Low-contrast icons (e.g., dark icons on dark backgrounds without a contrasting circle)
+- Text boxes too narrow causing excessive wrapping
+- Leftover placeholder content
+
+For each slide, list issues or areas of concern, even if minor.
+
+Read and analyze these images:
+1. /path/to/slide-01.jpg (Expected: [brief description])
+2. /path/to/slide-02.jpg (Expected: [brief description])
+
+Report ALL issues found, including minor ones.
+```
+
+### Verification Loop
+
+1. Generate slides → Convert to images → Inspect
+2. **List issues found** (if none found, look again more critically)
+3. Fix issues
+4. **Re-verify affected slides** — one fix often creates another problem
+5. Repeat until a full pass reveals no new issues
+
+**Do not declare success until you've completed at least one fix-and-verify cycle.**
+
+---
+
+## Converting to Images
+
+Convert presentations to individual slide images for visual inspection:
+
+```bash
+python scripts/office/soffice.py --headless --convert-to pdf output.pptx
+pdftoppm -jpeg -r 150 output.pdf slide
+```
+
+This creates `slide-01.jpg`, `slide-02.jpg`, etc.
+
+To re-render specific slides after fixes:
+
+```bash
+pdftoppm -jpeg -r 150 -f N -l N output.pdf slide-fixed
+```
+
+---
+
+## Dependencies
+
+- `pip install "markitdown[pptx]"` - text extraction
+- `pip install Pillow` - thumbnail grids
+- `npm install -g pptxgenjs` - creating from scratch
+- LibreOffice (`soffice`) - PDF conversion (auto-configured for sandboxed environments via `scripts/office/soffice.py`)
+- Poppler (`pdftoppm`) - PDF to images

package/.plcode/skill/experimental/document-pptx/editing.md

@@ -0,0 +1,213 @@
+# Editing Presentations
+
+## Template-Based Workflow
+
+When using an existing presentation as a template:
+
+1. **Analyze existing slides**:
+
+   ```bash
+   python scripts/thumbnail.py template.pptx
+   python -m markitdown template.pptx
+   ```
+
+   Review `thumbnails.jpg` to see layouts, and markitdown output to see placeholder text.
+
+2. **Plan slide mapping**: For each content section, choose a template slide.
+
+   ⚠️ **USE VARIED LAYOUTS** — monotonous presentations are a common failure mode. Don't default to basic title + bullet slides. Actively seek out:
+   - Multi-column layouts (2-column, 3-column)
+   - Image + text combinations
+   - Full-bleed images with text overlay
+   - Quote or callout slides
+   - Section dividers
+   - Stat/number callouts
+   - Icon grids or icon + text rows
+
+   **Avoid:** Repeating the same text-heavy layout for every slide.
+
+   Match content type to layout style (e.g., key points → bullet slide, team info → multi-column, testimonials → quote slide).
+
+3. **Unpack**: `python scripts/office/unpack.py template.pptx unpacked/`
+
+4. **Build presentation** (do this yourself, not with subagents):
+   - Delete unwanted slides (remove from `<p:sldIdLst>`)
+   - Duplicate slides you want to reuse (`add_slide.py`)
+   - Reorder slides in `<p:sldIdLst>`
+   - **Complete all structural changes before step 5**
+
+5. **Edit content**: Update text in each `slide{N}.xml`.
+   **Use subagents here if available** — slides are separate XML files, so subagents can edit in parallel.
+
+6. **Clean**: `python scripts/clean.py unpacked/`
+
+7. **Pack**: `python scripts/office/pack.py unpacked/ output.pptx --original template.pptx`
+
+---
+
+## Scripts
+
+| Script         | Purpose                               |
+| -------------- | ------------------------------------- |
+| `unpack.py`    | Extract and pretty-print PPTX         |
+| `add_slide.py` | Duplicate slide or create from layout |
+| `clean.py`     | Remove orphaned files                 |
+| `pack.py`      | Repack with validation                |
+| `thumbnail.py` | Create visual grid of slides          |
+
+### unpack.py
+
+```bash
+python scripts/office/unpack.py input.pptx unpacked/
+```
+
+Extracts PPTX, pretty-prints XML, escapes smart quotes.
+
+### add_slide.py
+
+```bash
+python scripts/add_slide.py unpacked/ slide2.xml      # Duplicate slide
+python scripts/add_slide.py unpacked/ slideLayout2.xml # From layout
+```
+
+Prints `<p:sldId>` to add to `<p:sldIdLst>` at desired position.
+
+### clean.py
+
+```bash
+python scripts/clean.py unpacked/
+```
+
+Removes slides not in `<p:sldIdLst>`, unreferenced media, orphaned rels.
+
+### pack.py
+
+```bash
+python scripts/office/pack.py unpacked/ output.pptx --original input.pptx
+```
+
+Validates, repairs, condenses XML, re-encodes smart quotes.
+
+### thumbnail.py
+
+```bash
+python scripts/thumbnail.py input.pptx [output_prefix] [--cols N]
+```
+
+Creates `thumbnails.jpg` with slide filenames as labels. Default 3 columns, max 12 per grid.
+
+**Use for template analysis only** (choosing layouts). For visual QA, use `soffice` + `pdftoppm` to create full-resolution individual slide images—see SKILL.md.
+
+---
+
+## Slide Operations
+
+Slide order is in `ppt/presentation.xml` → `<p:sldIdLst>`.
+
+**Reorder**: Rearrange `<p:sldId>` elements.
+
+**Delete**: Remove `<p:sldId>`, then run `clean.py`.
+
+**Add**: Use `add_slide.py`. Never manually copy slide files—the script handles notes references, Content_Types.xml, and relationship IDs that manual copying misses.
+
+---
+
+## Editing Content
+
+**Subagents:** If available, use them here (after completing step 4). Each slide is a separate XML file, so subagents can edit in parallel. In your prompt to subagents, include:
+
+- The slide file path(s) to edit
+- **"Use the Edit tool for all changes"**
+- The formatting rules and common pitfalls below
+
+For each slide:
+
+1. Read the slide's XML
+2. Identify ALL placeholder content—text, images, charts, icons, captions
+3. Replace each placeholder with final content
+
+**Use the Edit tool, not sed or Python scripts.** The Edit tool forces specificity about what to replace and where, yielding better reliability.
+
+### Formatting Rules
+
+- **Bold all headers, subheadings, and inline labels**: Use `b="1"` on `<a:rPr>`. This includes:
+  - Slide titles
+  - Section headers within a slide
+  - Inline labels like (e.g.: "Status:", "Description:") at the start of a line
+- **Never use unicode bullets (•)**: Use proper list formatting with `<a:buChar>` or `<a:buAutoNum>`
+- **Bullet consistency**: Let bullets inherit from the layout. Only specify `<a:buChar>` or `<a:buNone>`.
+
+---
+
+## Common Pitfalls
+
+### Template Adaptation
+
+When source content has fewer items than the template:
+
+- **Remove excess elements entirely** (images, shapes, text boxes), don't just clear text
+- Check for orphaned visuals after clearing text content
+- Run visual QA to catch mismatched counts
+
+When replacing text with different length content:
+
+- **Shorter replacements**: Usually safe
+- **Longer replacements**: May overflow or wrap unexpectedly
+- Test with visual QA after text changes
+- Consider truncating or splitting content to fit the template's design constraints
+
+**Template slots ≠ Source items**: If template has 4 team members but source has 3 users, delete the 4th member's entire group (image + text boxes), not just the text.
+
+### Multi-Item Content
+
+If source has multiple items (numbered lists, multiple sections), create separate `<a:p>` elements for each — **never concatenate into one string**.
+
+**❌ WRONG** — all items in one paragraph:
+
+```xml
+<a:p>
+  <a:r><a:rPr .../><a:t>Step 1: Do the first thing. Step 2: Do the second thing.</a:t></a:r>
+</a:p>
+```
+
+**✅ CORRECT** — separate paragraphs with bold headers:
+
+```xml
+<a:p>
+  <a:pPr algn="l"><a:lnSpc><a:spcPts val="3919"/></a:lnSpc></a:pPr>
+  <a:r><a:rPr lang="en-US" sz="2799" b="1" .../><a:t>Step 1</a:t></a:r>
+</a:p>
+<a:p>
+  <a:pPr algn="l"><a:lnSpc><a:spcPts val="3919"/></a:lnSpc></a:pPr>
+  <a:r><a:rPr lang="en-US" sz="2799" .../><a:t>Do the first thing.</a:t></a:r>
+</a:p>
+<a:p>
+  <a:pPr algn="l"><a:lnSpc><a:spcPts val="3919"/></a:lnSpc></a:pPr>
+  <a:r><a:rPr lang="en-US" sz="2799" b="1" .../><a:t>Step 2</a:t></a:r>
+</a:p>
+<!-- continue pattern -->
+```
+
+Copy `<a:pPr>` from the original paragraph to preserve line spacing. Use `b="1"` on headers.
+
+### Smart Quotes
+
+Handled automatically by unpack/pack. But the Edit tool converts smart quotes to ASCII.
+
+**When adding new text with quotes, use XML entities:**
+
+```xml
+<a:t>the &#x201C;Agreement&#x201D;</a:t>
+```
+
+| Character | Name               | Unicode | XML Entity |
+| --------- | ------------------ | ------- | ---------- |
+| `“`       | Left double quote  | U+201C  | `&#x201C;` |
+| `”`       | Right double quote | U+201D  | `&#x201D;` |
+| `‘`       | Left single quote  | U+2018  | `&#x2018;` |
+| `’`       | Right single quote | U+2019  | `&#x2019;` |
+
+### Other
+
+- **Whitespace**: Use `xml:space="preserve"` on `<a:t>` with leading/trailing spaces
+- **XML parsing**: Use `defusedxml.minidom`, not `xml.etree.ElementTree` (corrupts namespaces)