@heylemon/lemonade 0.1.4 → 0.1.6

package/skills/xlsx/scripts/create_xlsx.py

@@ -0,0 +1,222 @@
+#!/usr/bin/env python3
+"""
+Pro Sheets — Spreadsheet Creation Engine
+"""
+
+import json
+import sys
+
+try:
+    import openpyxl
+    from openpyxl.styles import Font, PatternFill, Alignment, Border, Side
+    from openpyxl.utils import get_column_letter
+except ImportError:
+    print("ERROR: openpyxl not installed. Run: pip install openpyxl --break-system-packages")
+    sys.exit(1)
+
+DEFAULT_BRAND = {
+    "primary": "1B3A5C",
+    "accent": "2E86AB",
+    "light_bg": "F8FAFC",
+    "text_dark": "2C3E50",
+    "text_light": "FFFFFF",
+    "border": "D5D8DC",
+    "positive": "27AE60",
+    "negative": "E74C3C",
+    "highlight": "FFF8E1",
+    "font": "Arial",
+}
+
+
+def hex_color(c):
+    return c.lstrip("#")
+
+
+def make_border(color="D5D8DC"):
+    side = Side(style="thin", color=hex_color(color))
+    return Border(left=side, right=side, top=side, bottom=side)
+
+
+def header_font(brand, size=11):
+    return Font(bold=True, size=size, color=hex_color(brand["text_light"]), name=brand["font"])
+
+
+def header_fill(brand):
+    return PatternFill("solid", fgColor=hex_color(brand["primary"]))
+
+
+def body_font(brand, size=11, bold=False, color=None):
+    return Font(size=size, name=brand["font"], bold=bold, color=hex_color(color or brand["text_dark"]))
+
+
+def alt_fill(brand, row_idx):
+    if row_idx % 2 == 0:
+        return PatternFill("solid", fgColor=hex_color(brand["light_bg"]))
+    return PatternFill(fill_type=None)
+
+
+class ProSheetBuilder:
+    def __init__(self, spec):
+        self.spec = spec
+        self.brand = {**DEFAULT_BRAND, **(spec.get("brand", {}))}
+        self.wb = openpyxl.Workbook()
+        self.border = make_border(self.brand["border"])
+
+    def build(self, output_path):
+        sheets = self.spec.get("sheets", [])
+        if not sheets:
+            print("ERROR: No sheets defined in spec")
+            sys.exit(1)
+
+        for si, sheet_spec in enumerate(sheets):
+            if si == 0:
+                ws = self.wb.active
+                ws.title = sheet_spec.get("name", "Sheet1")
+            else:
+                ws = self.wb.create_sheet(sheet_spec.get("name", f"Sheet{si+1}"))
+            self._build_sheet(ws, sheet_spec)
+
+        self.wb.save(output_path)
+        return output_path
+
+    def _build_sheet(self, ws, sheet_spec):
+        sheet_type = sheet_spec.get("type", "data")
+        if sheet_type == "dashboard":
+            self._build_dashboard(ws, sheet_spec)
+        elif sheet_type == "financial":
+            self._build_financial(ws, sheet_spec)
+        else:
+            self._build_data_sheet(ws, sheet_spec)
+
+        freeze = sheet_spec.get("freeze_panes")
+        if freeze:
+            ws.freeze_panes = freeze
+        if sheet_spec.get("auto_filter", False) and ws.max_row > 1:
+            ws.auto_filter.ref = f"A1:{get_column_letter(ws.max_column)}{ws.max_row}"
+
+    def _build_data_sheet(self, ws, sheet_spec):
+        headers = sheet_spec.get("headers", [])
+        rows = sheet_spec.get("rows", [])
+        col_widths = sheet_spec.get("col_widths", [])
+        title = sheet_spec.get("title")
+        start_row = 1
+
+        if title:
+            ws.cell(row=1, column=1, value=title).font = Font(
+                bold=True, size=16, color=hex_color(self.brand["text_dark"]), name=self.brand["font"]
+            )
+            ws.merge_cells(start_row=1, start_column=1, end_row=1, end_column=max(len(headers), 1))
+            start_row = 3
+
+        if headers:
+            for ci, h in enumerate(headers, 1):
+                cell = ws.cell(row=start_row, column=ci, value=h)
+                cell.font = header_font(self.brand)
+                cell.fill = header_fill(self.brand)
+                cell.alignment = Alignment(horizontal="center", wrap_text=True)
+                cell.border = self.border
+
+        for ri, row_data in enumerate(rows):
+            r = start_row + 1 + ri
+            for ci, val in enumerate(row_data, 1):
+                cell = ws.cell(row=r, column=ci, value=val)
+                cell.font = body_font(self.brand)
+                cell.fill = alt_fill(self.brand, ri)
+                cell.border = self.border
+                cell.alignment = Alignment(wrap_text=True, vertical="top")
+                if isinstance(val, (int, float)):
+                    cell.alignment = Alignment(horizontal="right", vertical="top")
+                    if isinstance(val, float) and abs(val) < 1:
+                        cell.number_format = "0.0%"
+                    elif isinstance(val, float):
+                        cell.number_format = "#,##0.00"
+                    elif isinstance(val, int) and val > 999:
+                        cell.number_format = "#,##0"
+
+        if col_widths:
+            for ci, w in enumerate(col_widths, 1):
+                ws.column_dimensions[get_column_letter(ci)].width = w
+        else:
+            for ci, h in enumerate(headers, 1):
+                ws.column_dimensions[get_column_letter(ci)].width = max(len(str(h)) + 4, 12)
+
+        for formula_spec in sheet_spec.get("formulas", []):
+            cell = ws[formula_spec["cell"]]
+            cell.value = formula_spec["formula"]
+            if formula_spec.get("bold", False):
+                cell.font = body_font(self.brand, bold=True)
+            cell.border = self.border
+
+    def _build_dashboard(self, ws, sheet_spec):
+        title = sheet_spec.get("title", "Dashboard")
+        kpis = sheet_spec.get("kpis", [])
+        sections = sheet_spec.get("sections", [])
+
+        ws.cell(row=1, column=1, value=title).font = Font(
+            bold=True, size=18, color=hex_color(self.brand["text_dark"]), name=self.brand["font"]
+        )
+        ws.merge_cells(start_row=1, start_column=1, end_row=1, end_column=max(len(kpis) * 2, 6))
+
+        if kpis:
+            r = 3
+            for ki, kpi in enumerate(kpis):
+                col = ki * 2 + 1
+                v = ws.cell(row=r, column=col, value=kpi.get("value", ""))
+                v.font = Font(bold=True, size=22, name=self.brand["font"], color=hex_color(self.brand["accent"]))
+                v.alignment = Alignment(horizontal="center")
+                ws.merge_cells(start_row=r, start_column=col, end_row=r, end_column=col + 1)
+
+                l = ws.cell(row=r + 1, column=col, value=kpi.get("label", ""))
+                l.font = Font(size=9, color="7F8C8D", name=self.brand["font"])
+                l.alignment = Alignment(horizontal="center")
+                ws.merge_cells(start_row=r + 1, start_column=col, end_row=r + 1, end_column=col + 1)
+
+                for dr in range(3):
+                    for dc in range(2):
+                        c = ws.cell(row=r + dr, column=col + dc)
+                        c.fill = PatternFill("solid", fgColor=hex_color(self.brand["highlight"]))
+                        c.border = self.border
+
+        current_row = 8 if kpis else 3
+        for section in sections:
+            ws.cell(row=current_row, column=1, value=section.get("title", "")).font = Font(
+                bold=True, size=13, color=hex_color(self.brand["text_dark"]), name=self.brand["font"]
+            )
+            current_row += 1
+            headers = section.get("headers", [])
+            rows = section.get("rows", [])
+            for ci, h in enumerate(headers, 1):
+                c = ws.cell(row=current_row, column=ci, value=h)
+                c.font = header_font(self.brand, size=10)
+                c.fill = header_fill(self.brand)
+                c.border = self.border
+                c.alignment = Alignment(horizontal="center")
+            for ri, row_data in enumerate(rows):
+                r = current_row + 1 + ri
+                for ci, val in enumerate(row_data, 1):
+                    c = ws.cell(row=r, column=ci, value=val)
+                    c.font = body_font(self.brand, size=10)
+                    c.fill = alt_fill(self.brand, ri)
+                    c.border = self.border
+            current_row += len(rows) + 3
+
+    def _build_financial(self, ws, sheet_spec):
+        self._build_data_sheet(ws, sheet_spec)
+        for ref in sheet_spec.get("input_cells", []):
+            ws[ref].font = Font(size=11, name=self.brand["font"], color="0000FF")
+        for ref in sheet_spec.get("assumption_cells", []):
+            ws[ref].fill = PatternFill("solid", fgColor="FFFF00")
+
+
+def main():
+    if len(sys.argv) < 3:
+        print("Usage: python create_xlsx.py spec.json output.xlsx")
+        sys.exit(1)
+    with open(sys.argv[1], "r", encoding="utf-8") as f:
+        spec = json.load(f)
+    ProSheetBuilder(spec).build(sys.argv[2])
+    print(f"Spreadsheet created: {sys.argv[2]}")
+
+
+if __name__ == "__main__":
+    main()

package/skills/xlsx/scripts/validate_xlsx.py

@@ -0,0 +1,73 @@
+#!/usr/bin/env python3
+"""
+Validate an .xlsx file for formula errors.
+"""
+
+import json
+import os
+import sys
+
+try:
+    from openpyxl import load_workbook
+except ImportError:
+    print("ERROR: openpyxl not installed. Run: pip install openpyxl --break-system-packages")
+    sys.exit(1)
+
+
+def validate(path):
+    if not os.path.exists(path):
+        print(json.dumps({"status": "error", "message": f"File not found: {path}"}))
+        return 1
+
+    wb = load_workbook(path, data_only=False)
+    wb_data = load_workbook(path, data_only=True)
+    result = {
+        "status": "success",
+        "total_errors": 0,
+        "total_formulas": 0,
+        "error_summary": {},
+        "warnings": [],
+        "sheets": {},
+    }
+
+    error_types = ["#REF!", "#DIV/0!", "#VALUE!", "#N/A", "#NAME?", "#NULL!", "#NUM!"]
+
+    for sheet_name in wb.sheetnames:
+        ws = wb[sheet_name]
+        ws_data = wb_data[sheet_name]
+        sheet_info = {"rows": ws.max_row, "cols": ws.max_column, "formulas": 0, "errors": []}
+
+        for row in ws.iter_rows():
+            for cell in row:
+                if cell.value and isinstance(cell.value, str) and cell.value.startswith("="):
+                    sheet_info["formulas"] += 1
+                    result["total_formulas"] += 1
+                    data_cell = ws_data[cell.coordinate]
+                    if data_cell.value and isinstance(data_cell.value, str):
+                        for err_type in error_types:
+                            if err_type in str(data_cell.value):
+                                sheet_info["errors"].append(
+                                    {"cell": cell.coordinate, "formula": cell.value, "error": err_type}
+                                )
+                                result["total_errors"] += 1
+                                if err_type not in result["error_summary"]:
+                                    result["error_summary"][err_type] = {"count": 0, "locations": []}
+                                result["error_summary"][err_type]["count"] += 1
+                                result["error_summary"][err_type]["locations"].append(
+                                    f"{sheet_name}!{cell.coordinate}"
+                                )
+
+        result["sheets"][sheet_name] = sheet_info
+
+    if result["total_errors"] > 0:
+        result["status"] = "errors_found"
+
+    print(json.dumps(result, indent=2))
+    return 0 if result["total_errors"] == 0 else 1
+
+
+if __name__ == "__main__":
+    if len(sys.argv) < 2:
+        print("Usage: python validate_xlsx.py spreadsheet.xlsx")
+        sys.exit(1)
+    sys.exit(validate(sys.argv[1]))

package/skills/pptx/editing.md

@@ -1,205 +0,0 @@
-# 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)