Skip to content

VidyFoo/antigravity-skill-engine / .agent/skills/4-tools/pptx-creating

pptx-creating

Verified

PPTX 演示文稿创建、编辑与分析。支持:(1) 从零创建演示文稿 (2) 编辑现有内容 (3) 使用模板创建 (4) 添加评论或演讲者备注。Presentation creation, editing, and analysis using html2pptx and OOXML.

FileKindSize
LICENSE.txtmarkdown1.4 KB
SKILL.mdskill md24.9 KB
ooxml/schemas/ISO-IEC29500-4_2016/dml-chart.xsdother73.2 KB
ooxml/schemas/ISO-IEC29500-4_2016/dml-chartDrawing.xsdother6.8 KB
ooxml/schemas/ISO-IEC29500-4_2016/dml-diagram.xsdother50.1 KB
ooxml/schemas/ISO-IEC29500-4_2016/dml-lockedCanvas.xsdother624 B
ooxml/schemas/ISO-IEC29500-4_2016/dml-main.xsdother148.5 KB
ooxml/schemas/ISO-IEC29500-4_2016/dml-picture.xsdother1.2 KB
ooxml/schemas/ISO-IEC29500-4_2016/dml-spreadsheetDrawing.xsdother8.7 KB
ooxml/schemas/ISO-IEC29500-4_2016/dml-wordprocessingDrawing.xsdother14.4 KB
ooxml/schemas/ISO-IEC29500-4_2016/pml.xsdother81.7 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-additionalCharacteristics.xsdother1.2 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-bibliography.xsdother7.2 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-commonSimpleTypes.xsdother6.2 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlDataProperties.xsdother1.2 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-customXmlSchemaProperties.xsdother880 B
ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesCustom.xsdother2.5 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesExtended.xsdother3.4 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-documentPropertiesVariantTypes.xsdother7.3 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-math.xsdother22.8 KB
ooxml/schemas/ISO-IEC29500-4_2016/shared-relationshipReference.xsdother1.3 KB
ooxml/schemas/ISO-IEC29500-4_2016/sml.xsdother236.6 KB
ooxml/schemas/ISO-IEC29500-4_2016/vml-main.xsdother25.5 KB
ooxml/schemas/ISO-IEC29500-4_2016/vml-officeDrawing.xsdother24.7 KB
ooxml/schemas/ISO-IEC29500-4_2016/vml-presentationDrawing.xsdother535 B
ooxml/schemas/ISO-IEC29500-4_2016/vml-spreadsheetDrawing.xsdother5.6 KB
ooxml/schemas/ISO-IEC29500-4_2016/vml-wordprocessingDrawing.xsdother3.9 KB
ooxml/schemas/ISO-IEC29500-4_2016/wml.xsdother167.4 KB
ooxml/schemas/ISO-IEC29500-4_2016/xml.xsdother4.5 KB
ooxml/schemas/ecma/fouth-edition/opc-contentTypes.xsdother1.9 KB
ooxml/schemas/ecma/fouth-edition/opc-coreProperties.xsdother2.5 KB
ooxml/schemas/ecma/fouth-edition/opc-digSig.xsdother2.8 KB
ooxml/schemas/ecma/fouth-edition/opc-relationships.xsdother1.3 KB
ooxml/schemas/mce/mc.xsdother3.1 KB
ooxml/schemas/microsoft/wml-2010.xsdother25.9 KB
ooxml/schemas/microsoft/wml-2012.xsdother3.7 KB
ooxml/schemas/microsoft/wml-2018.xsdother901 B
ooxml/schemas/microsoft/wml-cex-2018.xsdother1.7 KB
ooxml/schemas/microsoft/wml-cid-2016.xsdother1002 B
ooxml/schemas/microsoft/wml-sdtdatahash-2020.xsdother600 B
ooxml/schemas/microsoft/wml-symex-2015.xsdother745 B
ooxml/scripts/pack.pyscript5.5 KB
ooxml/scripts/unpack.pyscript1.0 KB
ooxml/scripts/validate.pyscript1.9 KB
ooxml/scripts/validation/__init__.pyscript336 B
ooxml/scripts/validation/base.pyscript39.0 KB
ooxml/scripts/validation/docx.pyscript9.8 KB
ooxml/scripts/validation/pptx.pyscript12.0 KB
ooxml/scripts/validation/redlining.pyscript10.9 KB
resources/html2pptx.mdmarkdown19.4 KB
resources/ooxml.mdmarkdown10.1 KB
scripts/html2pptx.jsscript36.9 KB
scripts/inventory.pyscript37.2 KB
scripts/rearrange.pyscript8.3 KB
scripts/replace.pyscript13.3 KB
scripts/thumbnail.pyscript15.1 KB

ooxml/scripts/validation/redlining.py

View on GitHub
"""
Validator for tracked changes in Word documents.
"""

import subprocess
import tempfile
import zipfile
from pathlib import Path


class RedliningValidator:
    """Validator for tracked changes in Word documents."""

    def __init__(self, unpacked_dir, original_docx, verbose=False):
        self.unpacked_dir = Path(unpacked_dir)
        self.original_docx = Path(original_docx)
        self.verbose = verbose
        self.namespaces = {
            "w": "http://schemas.openxmlformats.org/wordprocessingml/2006/main"
        }

    def validate(self):
        """Main validation method that returns True if valid, False otherwise."""
        # Verify unpacked directory exists and has correct structure
        modified_file = self.unpacked_dir / "word" / "document.xml"
        if not modified_file.exists():
            print(f"FAILED - Modified document.xml not found at {modified_file}")
            return False

        # First, check if there are any tracked changes by Claude to validate
        try:
            import xml.etree.ElementTree as ET

            tree = ET.parse(modified_file)
            root = tree.getroot()

            # Check for w:del or w:ins tags authored by Claude
            del_elements = root.findall(".//w:del", self.namespaces)
            ins_elements = root.findall(".//w:ins", self.namespaces)

            # Filter to only include changes by Claude
            claude_del_elements = [
                elem
                for elem in del_elements
                if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude"
            ]
            claude_ins_elements = [
                elem
                for elem in ins_elements
                if elem.get(f"{{{self.namespaces['w']}}}author") == "Claude"
            ]

            # Redlining validation is only needed if tracked changes by Claude have been used.
            if not claude_del_elements and not claude_ins_elements:
                if self.verbose:
                    print("PASSED - No tracked changes by Claude found.")
                return True

        except Exception:
            # If we can't parse the XML, continue with full validation
            pass

        # Create temporary directory for unpacking original docx
        with tempfile.TemporaryDirectory() as temp_dir:
            temp_path = Path(temp_dir)

            # Unpack original docx
            try:
                with zipfile.ZipFile(self.original_docx, "r") as zip_ref:
                    zip_ref.extractall(temp_path)
            except Exception as e:
                print(f"FAILED - Error unpacking original docx: {e}")
                return False

            original_file = temp_path / "word" / "document.xml"
            if not original_file.exists():
                print(
                    f"FAILED - Original document.xml not found in {self.original_docx}"
                )
                return False

            # Parse both XML files using xml.etree.ElementTree for redlining validation
            try:
                import xml.etree.ElementTree as ET

                modified_tree = ET.parse(modified_file)
                modified_root = modified_tree.getroot()
                original_tree = ET.parse(original_file)
                original_root = original_tree.getroot()
            except ET.ParseError as e:
                print(f"FAILED - Error parsing XML files: {e}")
                return False

            # Remove Claude's tracked changes from both documents
            self._remove_claude_tracked_changes(original_root)
            self._remove_claude_tracked_changes(modified_root)

            # Extract and compare text content
            modified_text = self._extract_text_content(modified_root)
            original_text = self._extract_text_content(original_root)

            if modified_text != original_text:
                # Show detailed character-level differences for each paragraph
                error_message = self._generate_detailed_diff(
                    original_text, modified_text
                )
                print(error_message)
                return False

            if self.verbose:
                print("PASSED - All changes by Claude are properly tracked")
            return True

    def _generate_detailed_diff(self, original_text, modified_text):
        """Generate detailed word-level differences using git word diff."""
        error_parts = [
            "FAILED - Document text doesn't match after removing Claude's tracked changes",
            "",
            "Likely causes:",
            "  1. Modified text inside another author's <w:ins> or <w:del> tags",
            "  2. Made edits without proper tracked changes",
            "  3. Didn't nest <w:del> inside <w:ins> when deleting another's insertion",
            "",
            "For pre-redlined documents, use correct patterns:",
            "  - To reject another's INSERTION: Nest <w:del> inside their <w:ins>",
            "  - To restore another's DELETION: Add new <w:ins> AFTER their <w:del>",
            "",
        ]

        # Show git word diff
        git_diff = self._get_git_word_diff(original_text, modified_text)
        if git_diff:
            error_parts.extend(["Differences:", "============", git_diff])
        else:
            error_parts.append("Unable to generate word diff (git not available)")

        return "\n".join(error_parts)

    def _get_git_word_diff(self, original_text, modified_text):
        """Generate word diff using git with character-level precision."""
        try:
            with tempfile.TemporaryDirectory() as temp_dir:
                temp_path = Path(temp_dir)

                # Create two files
                original_file = temp_path / "original.txt"
                modified_file = temp_path / "modified.txt"

                original_file.write_text(original_text, encoding="utf-8")
                modified_file.write_text(modified_text, encoding="utf-8")

                # Try character-level diff first for precise differences
                result = subprocess.run(
                    [
                        "git",
                        "diff",
                        "--word-diff=plain",
                        "--word-diff-regex=.",  # Character-by-character diff
                        "-U0",  # Zero lines of context - show only changed lines
                        "--no-index",
                        str(original_file),
                        str(modified_file),
                    ],
                    capture_output=True,
                    text=True,
                )

                if result.stdout.strip():
                    # Clean up the output - remove git diff header lines
                    lines = result.stdout.split("\n")
                    # Skip the header lines (diff --git, index, +++, ---, @@)
                    content_lines = []
                    in_content = False
                    for line in lines:
                        if line.startswith("@@"):
                            in_content = True
                            continue
                        if in_content and line.strip():
                            content_lines.append(line)

                    if content_lines:
                        return "\n".join(content_lines)

                # Fallback to word-level diff if character-level is too verbose
                result = subprocess.run(
                    [
                        "git",
                        "diff",
                        "--word-diff=plain",
                        "-U0",  # Zero lines of context
                        "--no-index",
                        str(original_file),
                        str(modified_file),
                    ],
                    capture_output=True,
                    text=True,
                )

                if result.stdout.strip():
                    lines = result.stdout.split("\n")
                    content_lines = []
                    in_content = False
                    for line in lines:
                        if line.startswith("@@"):
                            in_content = True
                            continue
                        if in_content and line.strip():
                            content_lines.append(line)
                    return "\n".join(content_lines)

        except (subprocess.CalledProcessError, FileNotFoundError, Exception):
            # Git not available or other error, return None to use fallback
            pass

        return None

    def _remove_claude_tracked_changes(self, root):
        """Remove tracked changes authored by Claude from the XML root."""
        ins_tag = f"{{{self.namespaces['w']}}}ins"
        del_tag = f"{{{self.namespaces['w']}}}del"
        author_attr = f"{{{self.namespaces['w']}}}author"

        # Remove w:ins elements
        for parent in root.iter():
            to_remove = []
            for child in parent:
                if child.tag == ins_tag and child.get(author_attr) == "Claude":
                    to_remove.append(child)
            for elem in to_remove:
                parent.remove(elem)

        # Unwrap content in w:del elements where author is "Claude"
        deltext_tag = f"{{{self.namespaces['w']}}}delText"
        t_tag = f"{{{self.namespaces['w']}}}t"

        for parent in root.iter():
            to_process = []
            for child in parent:
                if child.tag == del_tag and child.get(author_attr) == "Claude":
                    to_process.append((child, list(parent).index(child)))

            # Process in reverse order to maintain indices
            for del_elem, del_index in reversed(to_process):
                # Convert w:delText to w:t before moving
                for elem in del_elem.iter():
                    if elem.tag == deltext_tag:
                        elem.tag = t_tag

                # Move all children of w:del to its parent before removing w:del
                for child in reversed(list(del_elem)):
                    parent.insert(del_index, child)
                parent.remove(del_elem)

    def _extract_text_content(self, root):
        """Extract text content from Word XML, preserving paragraph structure.

        Empty paragraphs are skipped to avoid false positives when tracked
        insertions add only structural elements without text content.
        """
        p_tag = f"{{{self.namespaces['w']}}}p"
        t_tag = f"{{{self.namespaces['w']}}}t"

        paragraphs = []
        for p_elem in root.findall(f".//{p_tag}"):
            # Get all text elements within this paragraph
            text_parts = []
            for t_elem in p_elem.findall(f".//{t_tag}"):
                if t_elem.text:
                    text_parts.append(t_elem.text)
            paragraph_text = "".join(text_parts)
            # Skip empty paragraphs - they don't affect content validation
            if paragraph_text:
                paragraphs.append(paragraph_text)

        return "\n".join(paragraphs)


if __name__ == "__main__":
    raise RuntimeError("This module should not be run directly.")
canvas-designanthropics/skillsCreate beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
docxanthropics/skillsUse this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files) or Word templates (.dotx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', '.dotx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx or .dotx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
pdfanthropics/skillsUse this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and OCR on scanned PDFs to make them searchable. If the user mentions a .pdf file or asks to produce one, use this skill.Stars: 197kUpdated Claude CodeCodexVerifiedInstall
pptxanthropics/skillsUse this skill any time a .pptx or .potx 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 or .potx 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 (.potx), layouts, speaker notes, or comments. Trigger whenever the user mentions "deck," "slides," "presentation," or references a .pptx or .potx filename, regardless of what they plan to do with the content afterward. If a .pptx or .potx file needs to be opened, created, or touched, use this skill.Stars: 197kUpdated Claude CodeCodexVerifiedInstall