Skip to content

gpsaggese/helpers / .claude/skills/slides.add_visuals

slides.add_visuals

Verified

Propose and add visuals for the slides

Goal

  • Given a markdown file or slides from the user <FILE>, propose visuals (e.g., diagrams, pictures, tables) that make the slides more intuitive

Workflow

Read Related Rules

  • Read the file or the provided text
  • Read .claude/skills/slides.rules.md for the slide conventions and rules
  • Read .claude/skills/figure.rules.md for the visual rules

Propose a Visual for Each Slide

  • If a slide has no visual element, consider what can illustrate its concepts
  • Options, from ## Types of Illustrations in .claude/skills/figure.rules.md:
    • Table
    • Mermaid graph
    • Graphviz diagram
    • TikZ diagram
    • Images
    • Website screenshots

Output Example

  • The proposal can look like:
    Slide 1: "A Map of Machine Learning"
    - **Current**: Has mermaid mindmap (present)
    - **Assessment**: Excellent visual already present. Keep as-is.
    
    Slide 2: "Machine Learning Paradigms"
    - **Proposed**: Comparison table showing Paradigm name, Question asked, and Key characteristic
      - Format: Use styled-table for consistency
      - Shows supervised vs unsupervised vs RL vs active learning side-by-side
      - Helps learners see the contrasts quickly
    
    Slide 3: "Machine Learning Theory"
    - **Current**: Text-only explanation of 4 theoretical foundations
    - **Proposed**: Graphviz diagram showing theoretical frameworks
      - Show how VC theory, Bias-variance decomposition, MDL, and Bayesian approach relate
      - Color by category: theoretical foundations
      - Add connections showing dependencies/relationships
    
    Slide 4: "Machine Learning Models"
    - **Current**: Text-only list of model variants
    - **Proposed**: Taxonomy diagram (Graphviz or TikZ)
      - Organize models by key distinctions: parametric vs non-parametric, linear vs non-linear
      - Show example models in each category
      - Helps learners understand the model space structure
    
    Slide 5: "Machine Learning Techniques"
    - **Current**: Text-only list of pipeline stages
    - **Proposed**: ML Pipeline flowchart (Graphviz)
      - Show the stages: Input Processing -> Model Building -> Performance Evaluation -> Diagnostic -> Regularization -> Aggregation
      - Color stages by function (data preparation, model, evaluation, improvement)
      - Include key techniques under each stage
      - This is the most impactful addition for learning
    
    Slide 6: "Some machine Learning Adages"
    - **Current**: Collection of quotes with attributions
    - **Assessment**: Text-based content is appropriate here. No visual needed.
    
    | Slide | Change                         | Type          | Impact    |
    |-------|--------------------------------|---------------|-----------|
    | 1     | Keep existing                  | -             | Good      |
    | 2     | Add paradigm comparison table  | Table         | High      |
    | 3     | Add theory framework diagram   | Graphviz      | Medium    |
    | 4     | Add model taxonomy diagram     | Graphviz/TikZ | High      |
    | 5     | Add ML pipeline flowchart      | Graphviz      | Very High |
    | 6     | Keep as-is                     | -             | Good      |
    

Save the Plan

  • Save the plan to plan-slides.add_visuals.md
  • Say in the plan file how it was generated, with this line right after the title:
    - Generated by `.claude/skills/slides.add_visuals/SKILL.md`
    

Ask User to Confirm

  • Make a numbered list of the proposed changes for the user
  • Once the user confirms, perform the changes

Constraints

  • Maintain the structure of the text and keep the content of the existing text

Verification

  • Make sure the updated slides work by running the flow, e.g., gen_slides.py
    > gen_slides.py -i book.Agentic_AI/12.1 --notes_to_pdf_args="--skip_action open_pdf"
    
  • The plan file says it was generated by .claude/skills/slides.add_visuals/SKILL.md
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: 196kUpdated 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: 196kUpdated 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: 196kUpdated 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: 196kUpdated Claude CodeCodexVerifiedInstall