@heylemon/lemonade 0.1.4 → 0.1.6

package/skills/docx/scripts/create_doc.py

@@ -0,0 +1,252 @@
+#!/usr/bin/env python3
+"""
+Pro Docs — Document Creation Engine
+Takes a JSON document spec and produces a professionally formatted .docx file.
+"""
+
+import json
+import sys
+from datetime import datetime
+
+try:
+    from docx import Document
+    from docx.shared import Inches, Pt, RGBColor
+    from docx.enum.text import WD_ALIGN_PARAGRAPH
+    from docx.enum.table import WD_TABLE_ALIGNMENT
+    from docx.oxml.ns import nsdecls
+    from docx.oxml import parse_xml
+except ImportError:
+    print("ERROR: python-docx not installed. Run: pip install python-docx --break-system-packages")
+    sys.exit(1)
+
+
+DEFAULT_BRAND = {
+    "primary_color": "1B3A5C",
+    "accent_color": "2E86AB",
+    "light_accent": "E8F4F8",
+    "text_color": "2C3E50",
+    "muted_color": "7F8C8D",
+    "font_heading": "Arial",
+    "font_body": "Arial",
+}
+
+SIZES = {
+    "title": Pt(26),
+    "subtitle": Pt(14),
+    "h1": Pt(18),
+    "h2": Pt(14),
+    "h3": Pt(12),
+    "body": Pt(11),
+    "small": Pt(9),
+}
+
+
+def hex_to_rgb(hex_color: str) -> RGBColor:
+    h = hex_color.lstrip("#")
+    return RGBColor(int(h[0:2], 16), int(h[2:4], 16), int(h[4:6], 16))
+
+
+def set_cell_shading(cell, color_hex: str) -> None:
+    shading = parse_xml(f'<w:shd {nsdecls("w")} w:fill="{color_hex}" w:val="clear"/>')
+    cell._tc.get_or_add_tcPr().append(shading)
+
+
+def set_cell_border(cell, color="D5D8DC") -> None:
+    tc = cell._tc
+    tc_pr = tc.get_or_add_tcPr()
+    borders = parse_xml(
+        f'<w:tcBorders {nsdecls("w")}>'
+        f'  <w:top w:val="single" w:sz="4" w:space="0" w:color="{color}"/>'
+        f'  <w:left w:val="single" w:sz="4" w:space="0" w:color="{color}"/>'
+        f'  <w:bottom w:val="single" w:sz="4" w:space="0" w:color="{color}"/>'
+        f'  <w:right w:val="single" w:sz="4" w:space="0" w:color="{color}"/>'
+        f"</w:tcBorders>"
+    )
+    tc_pr.append(borders)
+
+
+class ProDocBuilder:
+    def __init__(self, spec):
+        self.spec = spec
+        self.brand = {**DEFAULT_BRAND, **spec.get("brand", {})}
+        self.doc = Document()
+        self._setup_styles()
+        self._setup_page()
+
+    def _setup_page(self):
+        section = self.doc.sections[0]
+        section.page_width = Inches(8.5)
+        section.page_height = Inches(11)
+        section.top_margin = Inches(0.8)
+        section.bottom_margin = Inches(0.8)
+        section.left_margin = Inches(1)
+        section.right_margin = Inches(1)
+
+        if self.spec.get("include_page_numbers", True):
+            footer = section.footer
+            fp = footer.paragraphs[0]
+            fp.alignment = WD_ALIGN_PARAGRAPH.CENTER
+            run = fp.add_run()
+            run.font.size = SIZES["small"]
+            run.font.color.rgb = hex_to_rgb(self.brand["muted_color"])
+            fld_char1 = parse_xml(f'<w:fldChar {nsdecls("w")} w:fldCharType="begin"/>')
+            run._r.append(fld_char1)
+            instr = parse_xml(
+                f'<w:instrText {nsdecls("w")} xml:space="preserve"> PAGE </w:instrText>'
+            )
+            run._r.append(instr)
+            fld_char2 = parse_xml(f'<w:fldChar {nsdecls("w")} w:fldCharType="end"/>')
+            run._r.append(fld_char2)
+
+    def _setup_styles(self):
+        style = self.doc.styles["Normal"]
+        style.font.name = self.brand["font_body"]
+        style.font.size = SIZES["body"]
+        style.font.color.rgb = hex_to_rgb(self.brand["text_color"])
+
+    def _add_title_block(self):
+        title = self.spec.get("title", "Untitled Document")
+        subtitle = self.spec.get("subtitle", "")
+        author = self.spec.get("author", "")
+        date_str = self.spec.get("date", "auto")
+        if date_str == "auto":
+            date_str = datetime.now().strftime("%B %d, %Y")
+
+        p = self.doc.add_paragraph()
+        p.alignment = WD_ALIGN_PARAGRAPH.LEFT
+        run = p.add_run(title)
+        run.font.size = SIZES["title"]
+        run.font.bold = True
+        run.font.color.rgb = hex_to_rgb(self.brand["primary_color"])
+        run.font.name = self.brand["font_heading"]
+
+        if subtitle:
+            p2 = self.doc.add_paragraph()
+            r2 = p2.add_run(subtitle)
+            r2.font.size = SIZES["subtitle"]
+            r2.font.color.rgb = hex_to_rgb(self.brand["muted_color"])
+            r2.font.name = self.brand["font_heading"]
+
+        if author or date_str:
+            p3 = self.doc.add_paragraph()
+            r3 = p3.add_run(" · ".join([x for x in [author, date_str] if x]))
+            r3.font.size = SIZES["small"]
+            r3.font.color.rgb = hex_to_rgb(self.brand["muted_color"])
+
+    def _add_heading(self, text, level=1):
+        heading = self.doc.add_heading(text, level=level)
+        for run in heading.runs:
+            run.font.color.rgb = hex_to_rgb(self.brand["primary_color"])
+            run.font.name = self.brand["font_heading"]
+        return heading
+
+    def _add_paragraph(self, text):
+        p = self.doc.add_paragraph(text)
+        for run in p.runs:
+            run.font.name = self.brand["font_body"]
+            run.font.size = SIZES["body"]
+            run.font.color.rgb = hex_to_rgb(self.brand["text_color"])
+
+    def _add_bullets(self, items, numbered=False):
+        style = "List Number" if numbered else "List Bullet"
+        for item in items:
+            p = self.doc.add_paragraph(item, style=style)
+            for run in p.runs:
+                run.font.name = self.brand["font_body"]
+                run.font.size = SIZES["body"]
+
+    def _add_table(self, table_spec):
+        headers = table_spec.get("headers", [])
+        rows = table_spec.get("rows", [])
+        if not headers and not rows:
+            return
+        num_cols = len(headers) if headers else len(rows[0])
+        table = self.doc.add_table(rows=0, cols=num_cols)
+        table.alignment = WD_TABLE_ALIGNMENT.CENTER
+
+        if headers:
+            row = table.add_row()
+            for i, h in enumerate(headers):
+                cell = row.cells[i]
+                cell.text = str(h)
+                for p in cell.paragraphs:
+                    for run in p.runs:
+                        run.font.bold = True
+                        run.font.color.rgb = RGBColor(0xFF, 0xFF, 0xFF)
+                        run.font.name = self.brand["font_heading"]
+                set_cell_shading(cell, self.brand["primary_color"])
+                set_cell_border(cell, self.brand["primary_color"])
+
+        for ri, row_data in enumerate(rows):
+            row = table.add_row()
+            for ci, cell_text in enumerate(row_data):
+                cell = row.cells[ci]
+                cell.text = str(cell_text)
+                if ri % 2 == 0:
+                    set_cell_shading(cell, self.brand.get("light_accent", "F8F9FA"))
+                set_cell_border(cell, "D5D8DC")
+
+    def _add_callout(self, text):
+        p = self.doc.add_paragraph()
+        p_pr = p._p.get_or_add_pPr()
+        p_bdr = parse_xml(
+            f'<w:pBdr {nsdecls("w")}>'
+            f'  <w:left w:val="single" w:sz="24" w:space="8" w:color="{self.brand["accent_color"]}"/>'
+            f"</w:pBdr>"
+        )
+        p_pr.append(p_bdr)
+        run = p.add_run(text)
+        run.font.size = SIZES["body"]
+        run.font.name = self.brand["font_body"]
+        run.font.color.rgb = hex_to_rgb(self.brand["text_color"])
+
+    def _process_section(self, section):
+        if section.get("page_break_before", False):
+            self.doc.add_page_break()
+
+        heading = section.get("heading", "")
+        if heading:
+            self._add_heading(heading, section.get("level", 1))
+
+        content = section.get("content", "")
+        if isinstance(content, list):
+            for para in content:
+                self._add_paragraph(para)
+        elif content:
+            for para in content.split("\n\n"):
+                self._add_paragraph(para.strip())
+
+        items = section.get("items", [])
+        if items:
+            self._add_bullets(items, section.get("numbered", False))
+
+        table_spec = section.get("table")
+        if table_spec:
+            self._add_table(table_spec)
+
+        callout = section.get("callout", "")
+        if callout:
+            self._add_callout(callout)
+
+    def build(self, output_path):
+        self._add_title_block()
+        for section in self.spec.get("sections", []):
+            self._process_section(section)
+        self.doc.save(output_path)
+        return output_path
+
+
+def main():
+    if len(sys.argv) < 3:
+        print("Usage: python create_doc.py spec.json output.docx")
+        sys.exit(1)
+
+    with open(sys.argv[1], "r", encoding="utf-8") as f:
+        spec = json.load(f)
+    builder = ProDocBuilder(spec)
+    builder.build(sys.argv[2])
+    print(f"Document created: {sys.argv[2]}")
+
+
+if __name__ == "__main__":
+    main()

package/skills/docx/scripts/validate_doc.py

@@ -0,0 +1,75 @@
+#!/usr/bin/env python3
+"""
+Validate a .docx file for common formatting issues.
+"""
+
+import os
+import sys
+
+try:
+    from docx import Document
+    from docx.shared import Inches
+except ImportError:
+    print("ERROR: python-docx not installed. Run: pip install python-docx --break-system-packages")
+    sys.exit(1)
+
+
+def validate(path):
+    issues = []
+    warnings = []
+
+    if not os.path.exists(path):
+        print(f"ERROR: File not found: {path}")
+        return 1
+
+    doc = Document(path)
+
+    section = doc.sections[0]
+    if section.left_margin and section.left_margin < Inches(0.5):
+        warnings.append("Left margin is very small (< 0.5 inches)")
+    if section.right_margin and section.right_margin < Inches(0.5):
+        warnings.append("Right margin is very small (< 0.5 inches)")
+
+    heading_count = 0
+    fonts_used = set()
+
+    for p in doc.paragraphs:
+        if p.style.name.startswith("Heading"):
+            heading_count += 1
+            if p.text.strip().endswith("."):
+                warnings.append(f'Heading ends with period: "{p.text.strip()[:50]}"')
+
+        if p.text.strip().startswith(("•", "◦", "▪", "●", "○", "■", "–", "—")):
+            if not p.style.name.startswith("List"):
+                issues.append(f'Manual bullet character detected: "{p.text.strip()[:50]}"')
+
+        for run in p.runs:
+            if run.font.name:
+                fonts_used.add(run.font.name)
+
+    if len(fonts_used) > 3:
+        warnings.append(f"Too many fonts used ({len(fonts_used)}): {', '.join(sorted(fonts_used))}")
+    if heading_count == 0 and len(doc.paragraphs) > 10:
+        warnings.append("No headings found in a long document")
+
+    if issues:
+        print("Validation failed:")
+        for issue in issues:
+            print(f"- {issue}")
+        return 1
+
+    if warnings:
+        print("Validation warnings:")
+        for warning in warnings:
+            print(f"- {warning}")
+        return 0
+
+    print("Validation passed: no issues found")
+    return 0
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python validate_doc.py document.docx")
+        sys.exit(1)
+    sys.exit(validate(sys.argv[1]))

package/skills/pptx/SKILL.md

@@ -1,232 +1,24 @@
 ---
 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."
+description: "Create professional, polished slide decks using a deterministic PptxGenJS script. Trigger for presentation, slides, deck, and .pptx requests."
 license: Proprietary. LICENSE.txt has complete terms
 ---
 
-# PPTX Skill
+# Pro Slides for PPTX
 
-## 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
+Use the scripted path:
 
 ```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/
+npm install -g pptxgenjs 2>/dev/null
+node scripts/create_pptx.js spec.json output.pptx
 ```
 
----
-
-## 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
-
----
+Use `references/spec-format.md` for slide schema and themes.
 
-## 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
+Recommended 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/skills/pptx/references/spec-format.md

@@ -0,0 +1,54 @@
+# Slide Spec Format
+
+## Top Level
+
+```json
+{
+  "title": "Presentation Title",
+  "author": "Author Name",
+  "theme": {},
+  "slides": []
+}
+```
+
+## Theme
+
+```json
+"theme": {
+  "primary": "1E2761",
+  "secondary": "CADCFC",
+  "accent": "F5A623",
+  "text_dark": "1E293B",
+  "text_light": "FFFFFF",
+  "text_muted": "64748B",
+  "bg_light": "F8FAFC",
+  "bg_dark": "1E2761",
+  "font_heading": "Arial Black",
+  "font_body": "Arial",
+  "chart_colors": ["2E86AB", "F5A623", "E74C3C", "2ECC71", "9B59B6"]
+}
+```
+
+## Slide Types
+
+- `title`
+- `section`
+- `content`
+- `two_column`
+- `stats`
+- `comparison`
+- `closing`
+
+## Example
+
+```json
+{
+  "title": "Q1 Board Update",
+  "author": "Lemon",
+  "slides": [
+    {"type": "title", "title": "Q1 Board Update", "subtitle": "Performance & Plan"},
+    {"type": "stats", "title": "Key Metrics", "stats": [{"value": "$156K", "label": "Monthly Revenue"}]},
+    {"type": "content", "title": "Revenue Beat Target by 15%", "items": ["Growth driven by enterprise wins", "Pipeline conversion improved"]}
+  ]
+}
+```