Generate detailed word-level differences using git word diff.

Generate detailed word-level differences using git word diff.

Generate random 8-character hex RSID.

Get default font size from theme text styles or use conservative default.

Recursively extract all text content from an element. Skips text nodes that contain only whitespace (spaces, tabs, newlines),

Get the expected relationship type for an element. First checks the explicit mapping, then tries pattern detection.

Get the expected relationship type for an element. First checks the explicit mapping, then tries pattern detection.

Generate word diff using git with character-level precision.

Generate word diff using git with character-level precision.

Get the next available change ID by checking all tracked change elements.

Get the next available comment ID.

Get XSD validation errors from a single file in the original document. Args: xml_file: Path to the XML file in unpacked_dir to ch

Get XSD validation errors from a single file in the original document. Args: xml_file: Path to the XML file in unpacked_dir to ch

Determine the appropriate schema path for an XML file.

Determine the appropriate schema path for an XML file.

Get usable width and height in pixels after accounting for margins.

Check if an author already exists in people.xml.

Load existing comments from files to enable replies.

Check if a value has the general structure of a UUID.

Check if a value has the general structure of a UUID.

Preprocess XML to handle mc:Ignorable attribute properly.

Preprocess XML to handle mc:Ignorable attribute properly.

Recursively remove all elements not in allowed namespaces.

Recursively remove all elements not in allowed namespaces.

Remove template tags from XML text nodes and collect warnings. Template tags follow the pattern {{ ... }} and are used as placeholders

Remove template tags from XML text nodes and collect warnings. Template tags follow the pattern {{ ... }} and are used as placeholders

Set up comment infrastructure in unpacked directory. Args: track_revisions: If True, enables track revisions in settings.xml

Create people.xml if it doesn't exist.

Add RSID and optionally enable track revisions in settings.xml. Args: path: Path to settings.xml track_revisions: If

Wrap a single line of text to fit within max_width_px.

Add a frame to the GIF. Args: frame: Frame as numpy array or PIL Image (will be converted to RGB)

Run the agent loop with MCP tools.

Apply font properties to a text run.

Apply kaleidoscope effect by mirroring/rotating frame sections. Args: frame: Input frame segments: Number of mirror segments

Apply formatting properties to a paragraph.

Apply text replacements from JSON to PowerPoint presentation.

Blend two colors together. Args: color1: First RGB color color2: Second RGB color ratio: Blend ratio (0.0 = all colo

Calculate position along a parabolic arc (natural motion path). Args: start: (x, y) starting position end: (x, y) ending pos

Calculate if and how much two rectangles overlap. Args: rect1: (left, top, width, height) of first rectangle in inches rect2: (le

Call a tool on the MCP server with provided arguments.

Check if yt-dlp is installed, install if not.

Clear bullet formatting from a paragraph.

Recursively collect all shapes with valid text, calculating absolute positions. For shapes within groups, their positions are relative to the gro

Compare paragraph counts between original and new document.

Compare paragraph counts between original and new document.

Strip unnecessary whitespace and remove comments.

Strip unnecessary whitespace and remove comments.

Convert PowerPoint to images via PDF, handling hidden slides.

Count the number of paragraphs in the original docx file.

Count the number of paragraphs in the original docx file.

Count the number of paragraphs in the unpacked document.

Count the number of paragraphs in the unpacked document.

Create attention-grabbing pulse (good for emoji GIFs). Args: emoji: Emoji to pulse num_frames: Number of frames fram

Create frames for a bouncing animation. Args: object_type: 'circle', 'emoji', or 'custom' object_data: Data for the object (

Factory function to create the appropriate MCP connection. Args: transport: Connection type ("stdio", "sse", or "http") command:

Crossfade between two objects. Args: object1_data: First object configuration object2_data: Second object configuration

Create excited wiggle for emoji GIFs. Args: emoji: Emoji to wiggle num_frames: Number of frames frame_size: Frame si

Create dramatic explosion zoom effect. Args: emoji: Emoji to explode num_frames: Number of frames frame_width: Frame

Create thumbnail grid from slide images with optional placeholder outlining.

Create multiple thumbnail grids from slide images, max cols×(cols+1) images per grid.

Create placeholder image for hidden slides.

Create animated kaleidoscope effect. Args: base_frame: Frame to apply effect to (or None for demo pattern) num_frames: Numbe

Create a loading spinner animation. Args: num_frames: Number of frames spinner_type: Type of spinner size: Spinner s

Create "mind blown" dramatic zoom with shake. Args: emoji: Emoji to use num_frames: Number of frames frame_width: Fr

Create animation with multiple objects sliding in sequence. Args: objects: List of object configs with 'type', 'data', 'direction',

Create simple particle burst effect. Args: num_frames: Number of frames particle_count: Number of particles center_p

Create quick flip for emoji GIFs. Args: emoji_front: Front emoji emoji_back: Back emoji num_frames: Number of frames

Calculate screen shake offset for a frame. Args: intensity: Shake intensity in pixels frame_index: Current frame number

Create frames for a shaking animation. Args: object_type: 'circle', 'emoji', 'text', or 'custom' object_data: Data for the o

Morph through a sequence of shapes. Args: shapes: List of shape dicts with 'radius' and 'color' num_frames: Total number of

Create zoom animation. Args: object_type: 'emoji', 'text', 'image' object_data: Object configuration num_frames: Num

Remove duplicate or near-duplicate consecutive frames. Args: threshold: Similarity threshold (0.0-1.0). Higher = more st

Delete a slide from the presentation.

Detect overlapping shapes and update their overlapping_shapes dictionaries. This function requires each ShapeData to have its shape_id already se

Download a YouTube video. Args: url: YouTube video URL output_path: Directory to save the video quality: Quality

Draw text on a frame. Args: frame: PIL Image to draw on text: Text to draw position: (x, y) position (top-left unles

Duplicate a slide in the presentation.

Bounce ease-in (bouncy start).

Quadratic ease-out (fast start, decelerating).

Emit a burst of particles. Args: x, y: Emission position count: Number of particles to emit spre

Evaluate a single QA pair with the given tools.

Fill the PDF form with data from fields.json

Get particle opacity based on lifetime.

Extract default font size from slide layout for a placeholder shape. Args: shape: Placeholder shape slide_layout: Sli

Get easing function by name.

Get the font file path for a given font name. Args: font_name: Name of the font (e.g., 'Arial', 'Calibri') Returns:

Get suggestions for optimizing a GIF based on validation results. Args: results: Results dict from validate_gif() Returns:

Extract ALL text regions from the presentation. Returns a tuple of (placeholder_regions, slide_dimensions). text_regions is a dict mapping sl

Get slide dimensions from slide object. Args: slide: Slide object Returns: Tuple of (width_emu, height_emu)

Get the dimensions of text without drawing it. Args: text: Text to measure font_size: Font size in pixels bold: Use