mapify.render-markdown
mapify.render-markdownFull Description
Use this when you want to visualize structured markdown content as an interactive mind map. This tool instantly renders the provided markdown into a zoomable, hierarchical mind map. Ideal for: webpage summaries, conversation organization, text analysis, knowledge structuring, or any content that benefits from visual hierarchy.
Parameters (2 required)
languagestringLanguage for the mind map content and interface.
markdownstringStructured markdown content to render as interactive mind map. Follow these critical requirements: STRUCTURE: - Start with exactly ONE H1 heading (#) summarizing the main topic - Use H2 (##) headings for main concepts (typically 3-8 sections) - Use H3 (###) headings to break down each H2 into sub-topics (2-5 per H2) - Use bullet points (-) for detailed information under appropriate heading levels HEADING-CONTENT RULE (CRITICAL): - Every heading MUST be immediately followed by either: 1. A heading of the next lower level (e.g., ### follows ##) 2. Bullet points (-) with actual content - Absolutely NO standalone paragraphs, summary text, or introductory sentences after headings - Never use empty or duplicate bullet points like "- -" BULLET POINT REQUIREMENTS: - Decompose information logically - each distinct idea should form a separate bullet point - Each bullet point should contain 15-30 words of substantive content - For multilevel bullets, use proper indentation: - First level: "-" (dash + space) - Second level: " -" (two spaces + dash + space) - Never use "- -" or double dashes FORMATTING CONSTRAINTS: - PLAIN TEXT ONLY - no bold (**text**), italics (*text*), code blocks, or tables - No horizontal rules (---) or meta-information - If a heading contains only a single word, do not add punctuation at the end - Use consistent language throughout EXAMPLE: # Machine Learning Fundamentals ## Supervised Learning ### Classification Algorithms - Decision trees split data based on feature values to create prediction rules for categorical outcomes - Support Vector Machines find optimal hyperplanes that maximize the margin between different classes - Kernel trick allows SVM to handle non-linearly separable data ### Regression Models - Linear regression predicts continuous values by fitting a line through data points ## Unsupervised Learning - Clustering algorithms group similar data points without predefined labels