pitch-deck-creator-edtech
Use when user needs to create a pitch deck for EdTech startups - transforms content into visually compelling, narrative-driven presentations through collaborative refinement, wireframing, and hybrid deck generation (PowerPoint + Google Slides)
What this skill does
# Pitch Deck Creator for EdTech Startups ## Overview Transform content-heavy pitch materials into visually compelling, narrative-driven pitch decks. This skill guides EdTech startup founders through collaborative content refinement, wireframe validation, professional design generation, and hybrid deck creation (PowerPoint + Google Slides). **Target User:** EdTech startup founders with written pitch content who need help with structure, narrative flow, and visual design. **Core Value:** Combines storytelling expertise with graphic design principles to maximize investor impact. --- ## When to Use This Skill Use this skill when: - User asks to "create a pitch deck" or "design a presentation" - User has pitch content but needs help with structure and visual design - User mentions they don't know how to make content visually appealing - User wants to refine existing pitch materials for investors - User says they have content but struggle with narrative flow **Trigger phrases:** "create pitch deck," "design presentation," "make slides," "help with my pitch" --- ## Prerequisites **Required from user:** - Content markdown file structured by slide topics (similar to Harry_Llama_Pitch_Deck_Content.md format) - Each slide should have: slide number, title, and content organized by section **Resource locations:** - Best practices: `/pitch_deck_skill/` (articles, examples, design principles) - Example decks: `examples/` (visual reference images relative to skill directory) - Output directory: `./pitch_deck_output/` (will be created in working directory) --- ## The 7-Phase Process ### Phase 1: Discovery & Setup **Goal:** Gather requirements and understand user's needs. **Actions:** 1. Ask user for content markdown file path 2. Use `AskUserQuestion` tool to gather: - **Purpose:** Investor pitch | Customer pitch | Partnership pitch | Internal pitch - **Target Audience:** VCs | Angels | Strategic investors | Corporate partners - **Tone:** Bold/aggressive | Professional/measured | Visionary/aspirational | Data-driven/analytical - **Format Preference:** PowerPoint | Google Slides | Both - **Brand Assets:** Colors (hex codes), Fonts (names), Logo location 3. Use `Read` tool to load: - User's content markdown file - Best practices resource: `resources.md` (from skill directory) - 2-3 example pitch deck images from `examples/` folder (use `Read` tool to view visual design patterns) - 1-2 HTML template examples from templates folder for reference 4. Use `TodoWrite` to create checklist: - [ ] Content analysis and collaborative editing - [ ] Text wireframes generation - [ ] ASCII wireframes confirmation - [ ] HTML slides generation - [ ] Visual preview and iteration - [ ] PowerPoint creation - [ ] Google Slides creation (if requested) **Output:** Complete understanding of requirements + loaded resources. --- ### Phase 2: Content Analysis & Collaborative Editing **Goal:** Refine content for maximum narrative impact through collaborative editing. **Analysis Criteria:** Evaluate content against EdTech pitch deck best practices: - **Narrative flow:** Story builds logically (Problem → Solution → Market → Why Us) - **Clarity:** Each point immediately understandable (no jargon, concrete examples) - **Emotional impact:** Connects with investor motivations (FOMO, vision, urgency) - **Data balance:** Right mix of numbers and story (not too dry, not too fluffy) - **Slide economy:** Can any slides be combined/removed? (10-20 slides ideal) - **Audience alignment:** Tone matches investor expectations (confident but honest) **Analysis Process:** 1. Read through ALL slide content 2. Identify issues per slide: - Redundant points - Unclear messaging - Missing emotional hooks - Too much/too little data - Poor narrative transitions - Weak value propositions 3. Prioritize by impact: HIGH (narrative/clarity) > MEDIUM (emotional/data) > LOW (polish) **Edit Presentation Format:** For each proposed change, show: ``` ═══════════════════════════════════════════════ SLIDE X: [Slide Title] SECTION: [Which part of the slide] CURRENT: [Original text] PROPOSED: [Edited text] RATIONALE: [Why this change improves the pitch - specific principle applied] IMPACT: [High/Medium/Low] - [Narrative/Clarity/Emotional/Data] ═══════════════════════════════════════════════ ``` **Presentation Strategy:** - Present 3-5 edits at a time (don't overwhelm) - Start with HIGH impact changes first - After each batch, ask: "Approve all | Approve some | Reject all | Suggest alternative" - If "Approve some": Present each edit individually for Accept/Reject decision - If "Suggest alternative": Listen to user's direction, regenerate proposals **Editing Guidelines:** - **Preserve founder's voice** - Don't make it sound generic - **Respect data integrity** - Never change numbers without explicit approval - **Flag assumptions** - If proposing content not in original, clearly mark as [SUGGESTED ADDITION] - **Prioritize high-impact** - Show most important changes first - **Show before/after** - Make it easy to compare **Collaborative Loop:** 1. Present batch of edits 2. Gather user decisions 3. Apply approved changes 4. Present next batch 5. Repeat until all slides reviewed **Output:** - Refined content markdown with all approved edits applied - Use `Write` tool to save: `./pitch_deck_output/content_refined.md` - Mark Phase 2 todo as complete --- ### Phase 3: Text Wireframes **Goal:** Define slide layouts in text form before visual design. **For each slide, describe:** - **Layout structure:** Header placement, content zones (left/right/center), footer - **Content organization:** How many sections, how points are grouped - **Visual emphasis:** Which elements are primary/secondary/tertiary - **Special elements:** Stats callout boxes, charts, images, tables **Text Wireframe Format:** ``` ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ SLIDE X: [Title] ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ LAYOUT TYPE: [Full-bleed header | Split-screen | Centered | Grid] HEADER ZONE: - Background: [Brand color] - Title: [Large, bold, brand accent color] - Position: [Top-left | Centered | Top-banner] CONTENT ZONE: - Organization: [3-column | Left-text-right-visual | Bullet list | Cards] - Primary element: [Main headline or key stat] - Secondary elements: [Supporting points] - Emphasis: [Callout box | Color highlight | Size variation] SPECIAL ELEMENTS: - [Stats callout box bottom-right] - [Chart placeholder center] - [Icon grid for features] FOOTER: - [Logo left | Page number right] WHITESPACE: [~35% of slide] ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ ``` **Validation:** After presenting all text wireframes, ask: "Do these layouts support the narrative flow? Any slides that need restructuring?" If user requests changes, update wireframes before proceeding. **Output:** - Text wireframe descriptions for all slides - Use `Write` tool to save: `./pitch_deck_output/wireframes_text.md` - Mark Phase 3 todo as complete --- ### Phase 4: ASCII Wireframes **Goal:** Show spatial relationships and visual hierarchy before committing to code. **ASCII Wireframe Format:** ``` ╔═══════════════════════════════════════════════════════════════╗ ║ SLIDE X: [TITLE] ║ ╠═══════════════════════════════════════════════════════════════╣ ║ ┌───────────────────────────────────────────────────────────┐ ║ ║ │ [HEADER BANNER] │ ║ ║ │ ████████ SLIDE TITLE ████████ │ ║ ║ └───────────────────────────────────────────────────────────┘ ║ ║ ║ ║ ┌─────────────┐ ┌─────────────┐ ┌─────────────┐ ║ ║ │ POINT 1 │ │ POINT 2 │ │ POINT 3 │ ║ ║ │ │ │ │ │ │ ║ ║ │ • Detail │ │ • Detail │ │ • Detail │ ║ ║ │
Related in Writing & Docs
jax-development
IncludedUse this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.
nature-article-writer
IncludedDrafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.
deckrd
IncludedDocument-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.
clinical-decision-support
IncludedGenerate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.
handling-sf-data
IncludedSalesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).
accelint-ac-to-playwright
IncludedConvert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.