Pitch Deck Visuals logo

Pitch Deck Visuals

Organization
inference-sh
pitch-deck-visuals

Investor pitch deck structure with slide-by-slide framework, visual design rules, and data presentation. Covers the 12-slide framework, chart types, team slides, and common investor turn-offs. Use for: fundraising decks, investor presentations, startup pitch, demo day, grant proposals. Triggers: pitch deck, investor deck, startup pitch, fundraising deck, demo day, pitch presentation, investor presentation, seed deck, series a deck, pitch slides, startup presentation, vc pitch, investor meeting

Overview

Publisherinference-sh
Repositoryskills
Skill namepitch-deck-visuals
Stars
790
Forks
106
Bundled files
Instructions only
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by inference-sh on GitHub. Read the source before you install it.

Installation

Install the Pitch Deck Visuals AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/inference-sh/skills/tree/main/guides/design/pitch-deck-visuals
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/inference-sh/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/guides/design/pitch-deck-visuals .claude/skills/pitch-deck-visuals
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Pitch Deck Visuals in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Pitch Deck Visuals on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Pitch Deck Visuals is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Install the belt CLI skill: npx skills add belt-sh/cli

Pitch Deck Visuals

Create investor-ready pitch deck visuals via inference.sh CLI.

Quick Start

Requires inference.sh CLI (belt). Install instructions

bash
belt login

# Generate a slide background
belt app run infsh/html-to-image --input '{
  "html": "<div style=\"width:1920px;height:1080px;background:linear-gradient(135deg,#0f0f23,#1a1a3e);display:flex;align-items:center;padding:100px;font-family:system-ui;color:white\"><div><p style=\"font-size:24px;color:#818cf8;text-transform:uppercase;letter-spacing:3px\">The Problem</p><h1 style=\"font-size:72px;margin:16px 0;font-weight:800;line-height:1.1\">Teams waste 12 hours/week on manual reporting</h1><p style=\"font-size:28px;opacity:0.7\">Source: Forrester Research, 2024</p></div></div>"
}'

The 12-Slide Framework

#SlideDurationContent
1Title15sCompany name, tagline, your name
2Problem45sPain point with data
3Solution45sYour product in one sentence
4Demo/Product60sScreenshot or live demo
5Market Size30sTAM → SAM → SOM
6Business Model30sHow you make money
7Traction45sGrowth metrics, customers
8Competition30sPositioning, not feature list
9Team30sWhy you specifically will win
10Financials30sRevenue projections, unit economics
11The Ask15sHow much, what for
12Contact10sEmail, next steps

Total: ~6 minutes. Never exceed 20 slides.

Slide Design Rules

Typography

ElementSize (1920x1080)Rule
Slide title48-72pxMax 6 words
Key stat/number96-144pxOne per slide, when applicable
Body text24-32pxMax 6 bullet points
Caption/source16-20pxCite data sources
FontSans-serif onlyInter, Helvetica, SF Pro, or similar

The 1-6-6 Rule

  • 1 idea per slide
  • 6 words max per bullet
  • 6 bullets max per slide

If you need more text, you need more slides.

Color

ElementGuideline
BackgroundDark (navy, charcoal) OR clean white — pick one, commit
Accent colorONE brand color for emphasis
TextWhite on dark, or dark grey (#333) on light
Charts2-3 colors max, your brand color = "you"
AvoidGradients on text, neon colors, more than 3 colors

Layout

RuleWhy
Consistent margins (80-100px)Professional, clean
Left-align text (never center body text)Easier to scan
One visual per slideFocus attention
Slide numbersHelps investors reference specific slides
Logo in cornerSubtle brand reinforcement

Slide-by-Slide Visual Guide

1. Title Slide

bash
belt app run infsh/html-to-image --input '{
  "html": "<div style=\"width:1920px;height:1080px;background:#0f0f23;display:flex;align-items:center;justify-content:center;font-family:system-ui;color:white;text-align:center\"><div><h1 style=\"font-size:80px;font-weight:900;margin:0\">DataFlow</h1><p style=\"font-size:32px;opacity:0.7;margin-top:16px\">Automated reporting for data teams</p><p style=\"font-size:22px;opacity:0.5;margin-top:40px\">Seed Round — Q1 2025</p></div></div>"
}'

2. Problem Slide

One big number + one sentence.

bash
belt app run infsh/html-to-image --input '{
  "html": "<div style=\"width:1920px;height:1080px;background:#0f0f23;display:flex;align-items:center;padding:100px;font-family:system-ui;color:white\"><div><p style=\"font-size:24px;color:#f59e0b;text-transform:uppercase;letter-spacing:3px;margin:0\">The Problem</p><h1 style=\"font-size:144px;margin:20px 0;font-weight:900;color:#f59e0b\">12 hrs/week</h1><p style=\"font-size:36px;opacity:0.8;line-height:1.4\">The average data analyst spends 12 hours per week<br>building reports manually</p><p style=\"font-size:20px;opacity:0.4;margin-top:30px\">Source: Forrester Research, 2024</p></div></div>"
}'

5. Market Size (TAM/SAM/SOM)

Use concentric circles, not pie charts:

bash
belt app run infsh/python-executor --input '{
  "code": "import matplotlib.pyplot as plt\nimport matplotlib\nmatplotlib.use(\"Agg\")\n\nfig, ax = plt.subplots(figsize=(19.2, 10.8))\nfig.patch.set_facecolor(\"#0f0f23\")\nax.set_facecolor(\"#0f0f23\")\n\ncircles = [\n    (0, 0, 4.0, \"#1e1e4a\", \"TAM\\n$50B\", 40),\n    (0, 0, 2.8, \"#2a2a5a\", \"SAM\\n$8B\", 32),\n    (0, 0, 1.4, \"#818cf8\", \"SOM\\n$800M\", 28)\n]\n\nfor x, y, r, color, label, fontsize in circles:\n    circle = plt.Circle((x, y), r, color=color, ec=\"#333366\", linewidth=2)\n    ax.add_patch(circle)\n    ax.text(x, y, label, ha=\"center\", va=\"center\", fontsize=fontsize, color=\"white\", fontweight=\"bold\")\n\nax.set_xlim(-5, 5)\nax.set_ylim(-5, 5)\nax.set_aspect(\"equal\")\nax.axis(\"off\")\nax.text(0, 4.8, \"Market Opportunity\", ha=\"center\", fontsize=36, color=\"white\", fontweight=\"bold\")\nplt.tight_layout()\nplt.savefig(\"market-size.png\", dpi=100, facecolor=\"#0f0f23\")\nprint(\"Saved\")"
}'

7. Traction Slide

Show growth, not just numbers. Up-and-to-the-right chart.

bash
belt app run infsh/python-executor --input '{
  "code": "import matplotlib.pyplot as plt\nimport matplotlib\nmatplotlib.use(\"Agg\")\n\nfig, ax = plt.subplots(figsize=(19.2, 10.8))\nfig.patch.set_facecolor(\"#0f0f23\")\nax.set_facecolor(\"#0f0f23\")\n\nmonths = [\"Jan\", \"Feb\", \"Mar\", \"Apr\", \"May\", \"Jun\", \"Jul\", \"Aug\"]\nrevenue = [8, 12, 18, 28, 42, 58, 82, 120]\n\nax.fill_between(range(len(months)), revenue, alpha=0.3, color=\"#818cf8\")\nax.plot(range(len(months)), revenue, color=\"#818cf8\", linewidth=4, marker=\"o\", markersize=10)\nax.set_xticks(range(len(months)))\nax.set_xticklabels(months, color=\"white\", fontsize=18)\nax.tick_params(colors=\"white\", labelsize=16)\nax.set_ylabel(\"MRR ($K)\", color=\"white\", fontsize=20)\nax.spines[\"top\"].set_visible(False)\nax.spines[\"right\"].set_visible(False)\nax.spines[\"bottom\"].set_color(\"#333\")\nax.spines[\"left\"].set_color(\"#333\")\nax.set_title(\"Monthly Recurring Revenue\", color=\"white\", fontsize=32, fontweight=\"bold\", pad=20)\nax.text(7, 120, \"$120K MRR\", color=\"#22c55e\", fontsize=28, fontweight=\"bold\", ha=\"center\", va=\"bottom\")\nax.text(7, 112, \"15x growth in 8 months\", color=\"#22c55e\", fontsize=18, ha=\"center\")\nplt.tight_layout()\nplt.savefig(\"traction.png\", dpi=100, facecolor=\"#0f0f23\")\nprint(\"Saved\")"
}'

8. Competition Slide

Never use a feature matrix against competitors. Use a 2x2 positioning map.

bash
# See the competitor-teardown skill for positioning map generation
belt app run infsh/python-executor --input '{
  "code": "import matplotlib.pyplot as plt\nimport matplotlib\nmatplotlib.use(\"Agg\")\n\nfig, ax = plt.subplots(figsize=(19.2, 10.8))\nfig.patch.set_facecolor(\"#0f0f23\")\nax.set_facecolor(\"#0f0f23\")\n\ncompetitors = {\n    \"Us\": (0.6, 0.7, \"#22c55e\", 300),\n    \"Legacy Tool\": (-0.5, 0.5, \"#6366f1\", 200),\n    \"Startup X\": (0.3, -0.4, \"#6366f1\", 200),\n    \"Manual Process\": (-0.6, -0.6, \"#475569\", 150)\n}\n\nfor name, (x, y, color, size) in competitors.items():\n    ax.scatter(x, y, s=size*5, c=color, zorder=5, alpha=0.8)\n    weight = \"bold\" if name == \"Us\" else \"normal\"\n    ax.annotate(name, (x, y), textcoords=\"offset points\", xytext=(15, 15), fontsize=22, color=\"white\", fontweight=weight)\n\nax.axhline(y=0, color=\"#333\", linewidth=1)\nax.axvline(x=0, color=\"#333\", linewidth=1)\nax.set_xlim(-1, 1)\nax.set_ylim(-1, 1)\nax.set_xlabel(\"Manual ← → Automated\", fontsize=22, color=\"white\", labelpad=15)\nax.set_ylabel(\"Basic ← → Advanced\", fontsize=22, color=\"white\", labelpad=15)\nax.set_title(\"Competitive Landscape\", fontsize=32, color=\"white\", fontweight=\"bold\", pad=20)\nax.tick_params(colors=\"#0f0f23\")\nfor spine in ax.spines.values():\n    spine.set_visible(False)\nplt.tight_layout()\nplt.savefig(\"competition.png\", dpi=100, facecolor=\"#0f0f23\")\nprint(\"Saved\")"
}'

9. Team Slide

bash
# Generate professional team headshots/avatars
belt app run falai/flux-dev-lora --input '{
  "prompt": "professional headshot portrait, person in business casual attire, clean neutral background, warm studio lighting, confident friendly expression, corporate photography style",
  "width": 512,
  "height": 512
}'

Layout: Photos in a row with name, title, and one credential each.

PersonFormat
CEOName, title, "Ex-[Company], [credential]"
CTOName, title, "Built [thing] at [Company]"
OthersName, title, one relevant credential

Max 4 people on the team slide. More = unfocused.

Chart Guidelines

Chart TypeUse ForNever Use For
Line chartGrowth over time (traction)Comparisons between categories
Bar chartComparing amountsTime series (use line)
Concentric circlesTAM/SAM/SOMAnything else
2x2 matrixCompetitive positioningFeature comparison
Single big numberKey metric highlightMultiple metrics
Pie chartNEVERAnything (hard to read, unprofessional)

Chart Design Rules

RuleWhy
Max 2 colors per chartClarity
Your company = green or brand colorPositive association
Label directly on chartNo separate legend needed
Remove gridlines or make very subtleReduce clutter
Start Y-axis at 0Don't mislead
Cite data sourcesCredibility

What Investors Look For

SlideInvestor's Real Question
Problem"Is this a real problem people pay to solve?"
Solution"Is this 10x better than the status quo?"
Market"Is this big enough to matter?"
Traction"Is this actually working?"
Team"Can these people execute?"
Ask"Is this a reasonable deal?"

Common Mistakes

MistakeProblemFix
Too many slides (20+)Loses attention, unfocusedMax 12-15 slides
Wall of textNobody reads it1-6-6 rule: 1 idea, 6 words, 6 bullets
Feature comparison table vs competitorsLooks defensiveUse 2x2 positioning map
Pie chartsHard to read, unprofessionalUse bar charts or big numbers
No data sources citedLooks made upAlways cite sources
Team slide with 8+ peopleUnfocusedMax 4, focus on relevant experience
Inconsistent designLooks amateurSame colors, fonts, margins on every slide
No "The Ask" slideInvestor doesn't know what you wantState amount, use of funds, timeline
Vanity metrics"1M visits" means nothing without conversionShow revenue, active users, retention
Too much product demoThis is a business pitch, not a demoMax 2 slides on product, focus on business

Related Skills

bash
npx skills add inference-sh/skills@competitor-teardown
npx skills add inference-sh/skills@data-visualization
npx skills add inference-sh/skills@ai-image-generation

Browse all apps: belt app list

Frequently asked questions

What does the Pitch Deck Visuals AI skill do?

Investor pitch deck structure with slide-by-slide framework, visual design rules, and data presentation. Covers the 12-slide framework, chart types, team slides, and common investor turn-offs. Use for: fundraising decks, investor presentations, startup pitch, demo day, grant proposals. Triggers: pitch deck, investor deck, startup pitch, fundraising deck, demo day, pitch presentation, investor presentation, seed deck, series a deck, pitch slides, startup presentation, vc pitch, investor meeting

Why use Pitch Deck Visuals on TypingMind?

Because you install it once and use it with any model. Pitch Deck Visuals is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Pitch Deck Visuals in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/inference-sh/skills/tree/main/guides/design/pitch-deck-visuals. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Pitch Deck Visuals?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Pitch Deck Visuals?

As many as you like. As long as a model supports skills, you can use Pitch Deck Visuals with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Pitch Deck Visuals AI skill free?

It is published on GitHub by inference-sh. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇