prezentit

1
1
Source

Generate beautiful AI-powered presentations instantly. Create professional slides with custom themes, visual designs, and speaker notes—all through natural language commands. Connect your Prezentit account to generate presentations directly from chat.

Install

mkdir -p .claude/skills/prezentit && curl -L -o skill.zip "https://mcp.directory/api/skills/download/5036" && unzip -o skill.zip -d .claude/skills/prezentit && rm skill.zip

Installs to .claude/skills/prezentit

About this skill

---
name: prezentit
description: Generate beautiful AI-powered presentations instantly. Create professional slides with custom themes, visual designs, and speaker notes—all through natural language commands.
homepage: https://prezentit.net
emoji: "👽"
metadata:
  clawdbot:
    emoji: "👽"
    skillKey: prezentit
    homepage: https://prezentit.net
    requires:
      config:
        - PREZENTIT_API_KEY
    config:
      requiredEnv:
        - name: PREZENTIT_API_KEY
          description: Your Prezentit API key (starts with pk_). Get one free at https://prezentit.net/api-keys
      example: |
        export PREZENTIT_API_KEY=pk_your_api_key_here
    permissions:
      network:
        - https://prezentit.net/api/v1/*
      fileSystem: none
      env:
        reads:
          - PREZENTIT_API_KEY
        writes: none
---

# Prezentit - AI Presentation Generator

**Base URL**: `https://prezentit.net/api/v1`
**Auth Header**: `Authorization: Bearer {PREZENTIT_API_KEY}`

> **This skill requires a `PREZENTIT_API_KEY` environment variable.** Get a free API key at https://prezentit.net/api-keys — new accounts include 100 free credits.

## ⚠️ CRITICAL FOR AI AGENTS

**ALWAYS use `"stream": false`** in generation requests! Without this, you get streaming responses that cause issues.

---

## Complete Workflow (FOLLOW THIS ORDER)

### Step 1: Check Credits First

```http
GET /api/v1/me/credits
Authorization: Bearer {PREZENTIT_API_KEY}

Response:

{
  "credits": 100,
  "pricing": {
    "outlinePerSlide": 5,
    "designPerSlide": 10,
    "estimatedCostPerSlide": 15
  },
  "_ai": {
    "canGenerate": true,
    "maxSlidesAffordable": 6,
    "nextSteps": ["..."]
  }
}

→ If _ai.canGenerate is false, direct user to https://prezentit.net/buy-credits → Use _ai.maxSlidesAffordable to know the limit

Step 2: Choose a Theme

Option A — Browse all available themes and pick by ID:

GET /api/v1/themes
Authorization: Bearer {PREZENTIT_API_KEY}

Response:

{
  "themes": [
    { "id": "corporate_blue", "name": "Corporate Blue", "category": "Corporate & Professional" },
    { "id": "nature_earth", "name": "Nature Earth", "category": "Nature & Organic" }
  ],
  "categories": ["Corporate & Professional", "Creative & Visual", "Data & Analytics", ...],
  "_ai": {
    "totalThemes": 20,
    "popularThemes": ["corporate_blue", "midnight_tech", "nature_earth", "storyteller", "data_dashboard"]
  }
}

→ Use the exact id value in your generation request

Option B — Search for a theme by keyword:

GET /api/v1/themes?search=minimalist
Authorization: Bearer {PREZENTIT_API_KEY}

→ Returns best matches ranked by relevance. Use the id from bestMatch.

Option C — Describe a custom style (no theme ID needed):

Use the customDesignPrompt parameter instead. See the Custom Design Prompt section below.

Step 3: Generate Presentation

POST /api/v1/presentations/generate
Authorization: Bearer {PREZENTIT_API_KEY}
Content-Type: application/json

{
  "topic": "User's topic here",
  "slideCount": 5,
  "theme": "corporate_blue",
  "stream": false
}

⏱️ IMPORTANT: Generation takes 1-3 minutes. The API will return when complete.

Full Request Parameters:

ParameterTypeRequiredDescription
topicstringYes*Presentation topic (2-500 chars). Required if no outline. prompt is also accepted as an alias.
outlineobjectNoPre-built outline (saves ~33% credits). See Outline section below.
slideCountnumberNoNumber of slides (3-50, default: 5). Ignored if outline provided.
themestringNoTheme ID from GET /api/v1/themes. Use the exact id value.
customDesignPromptstringNoCustom visual style description (see below). Overrides theme ID.
detailsstringNoAdditional context about the presentation content.
confirmPartialbooleanNoSet true to confirm partial generation when credits are limited.
streambooleanALWAYS falseAI agents must always set stream: false.

*topic is required even when providing an outline (used for presentation metadata).

Step 4: Get the Result

Success Response:

{
  "presentationId": "uuid-here",
  "viewUrl": "https://prezentit.net/view/abc123",
  "creditsUsed": 75,
  "remainingCredits": 25
}

→ Share the viewUrl with the user. That's their presentation!

Step 5: Download (Optional)

GET /api/v1/presentations/{presentationId}/download?format=pptx
Authorization: Bearer {PREZENTIT_API_KEY}

Formats: pptx (PowerPoint), pdf, json (raw data)


Pricing

ScenarioCost per SlideExample (5 slides)
Auto-generate outline15 credits75 credits
Provide your own outline10 credits50 credits (~33% savings!)

Theme Selection

How to Pick a Theme

  1. Fetch the theme list: GET /api/v1/themes — returns all available themes with id, name, and category
  2. Pick the best match for the user's topic and style preference
  3. Pass the id in the generation request as the theme parameter

You can also search: GET /api/v1/themes?search=KEYWORD or filter by category: GET /api/v1/themes?category=CATEGORY_NAME

Custom Design Prompt (Skip the Theme List)

If no existing theme fits, use customDesignPrompt to describe a fully custom visual style. This must be a detailed, structured description — not just a color palette.

REQUIRED structure for customDesignPrompt (include ALL of these sections):

COLOR SYSTEM: Primary [hex], secondary [hex], accent [hex], background [hex/gradient], text colors for headings and body.

TYPOGRAPHY: Heading font style [e.g., bold geometric sans-serif like Montserrat], body font style [e.g., clean humanist sans-serif like Open Sans], size hierarchy [large/medium/small], weight contrast.

LAYOUT SYSTEM: Slide structure [e.g., asymmetric split with 60/40 content-to-visual ratio], alignment [left-aligned text with right visual panel], spacing philosophy [generous whitespace vs. dense information], grid approach.

VISUAL ELEMENTS: Background treatment [solid/gradient/textured/patterned], decorative motifs [geometric shapes, organic curves, line art, etc.], image style [photography with overlay, illustrations, icons, data visualizations], border/frame treatments.

MOOD & TONE: Overall aesthetic [e.g., corporate authority, playful creativity, academic rigor, tech-forward], energy level [calm/dynamic/bold], intended audience impression.

Example — Good customDesignPrompt:

{
  "topic": "AI in Healthcare",
  "customDesignPrompt": "COLOR SYSTEM: Primary deep medical blue (#1B3A5C), secondary teal (#2A9D8F), accent warm coral (#E76F51) for callouts, backgrounds alternate between clean white (#FAFAFA) and very subtle blue-gray (#F0F4F8), heading text dark navy, body text #333333. TYPOGRAPHY: Headings in bold geometric sans-serif (Montserrat style), body in clean humanist sans (Source Sans style), strong size hierarchy with 48pt titles, 24pt subtitles, 16pt body. LAYOUT SYSTEM: Asymmetric layouts with 60/40 content-to-visual split, left-aligned text blocks with right-side data visualizations or medical imagery, generous padding (60px margins), clean grid structure. VISUAL ELEMENTS: Subtle DNA helix watermark in corners at 5% opacity, thin teal accent lines as section dividers, medical iconography (stethoscope, heartbeat, molecular structures) as small decorative elements, photography with blue-tinted overlay for full-bleed backgrounds. MOOD & TONE: Professional medical authority balanced with approachable warmth, calm and trustworthy, designed for hospital executives and medical professionals.",
  "stream": false
}

Example — Bad customDesignPrompt (TOO VAGUE, will produce generic results):

"blue and white medical theme"

Creating Outlines (Save ~33% Credits)

Providing your own outline saves credits and gives you full control over content.

Outline Structure

The outline is an object with a slides array. Each slide has these fields:

{
  "topic": "Your Presentation Topic",
  "outline": {
    "slides": [
      {
        "title": "Slide Title Here",
        "mainIdea": "A clear sentence explaining the core message of this slide and what the audience should take away from it.",
        "talkingPoints": [
          "First key point with enough detail to be meaningful (at least 10 characters)",
          "Second key point expanding on the main idea",
          "Third key point providing supporting evidence or examples"
        ],
        "visualGuide": "Detailed description of the visual layout: background style, image placement, icon suggestions, chart types, color emphasis areas, and decorative elements for this specific slide."
      }
    ]
  },
  "stream": false
}

Slide Field Reference

FieldRequiredConstraintsDescription
titleYes3-100 chars, 1-15 wordsSlide heading
mainIdeaYes10-500 chars, 3-75 wordsCore message of the slide
talkingPointsYes2-7 items, each 10-300 chars (3-50 words)Key points to cover
visualGuideYes20-500 chars, 5-75 wordsVisual design instructions for this slide

Validation Rules

Overall:

  • Minimum 3 slides, maximum 50 slides
  • topic is still required (used for presentation metadata)
  • All four fields (title, `mainIde

Content truncated.

a-stock-analysis

openclaw

A股实时行情与分时量能分析。获取沪深股票实时价格、涨跌、成交量,分析分时量能分布(早盘/尾盘放量)、主力动向(抢筹/出货信号)、涨停封单。支持持仓管理和盈亏分析。Use when: (1) 查询A股实时行情, (2) 分析主力资金动向, (3) 查看分时成交量分布, (4) 管理股票持仓, (5) 分析持仓盈亏。

754288

fivem

openclaw

Fix, create, or validate FiveM server resources for QBCore/ESX (config.lua, fxmanifest.lua, items, housing/furniture, scripts, MLOs). Use when asked to debug resource errors, convert ESX↔QB, update fxmanifest versions, add items, or source scripts from GitHub. Also use for SSH key generation for SFTP access.

409258

research-paper-writer

openclaw

Creates formal academic research papers following IEEE/ACM formatting standards with proper structure, citations, and scholarly writing style. Use when the user asks to write a research paper, academic paper, or conference paper on any topic.

81168

keyword-research

openclaw

Discovers high-value keywords with search intent analysis, difficulty assessment, and content opportunity mapping. Essential for starting any SEO or GEO content strategy.

439107

html-to-ppt

openclaw

Convert HTML/Markdown to PowerPoint presentations using Marp

33389

weread

openclaw

WeChat Reading (微信读书) CLI tool for fetching notes and highlights. Use when: (1) user asks about weread/微信读书 notes or highlights, (2) fetching today's or recent reading notes, (3) exporting book highlights, (4) managing reading bookshelf, (5) any task involving reading notes from WeChat Reading.

11285

You might also like

ui-ux-pro-max

nextlevelbuilder

"UI/UX design intelligence. 50 styles, 21 palettes, 50 font pairings, 20 charts, 8 stacks (React, Next.js, Vue, Svelte, SwiftUI, React Native, Flutter, Tailwind). Actions: plan, build, create, design, implement, review, fix, improve, optimize, enhance, refactor, check UI/UX code. Projects: website, landing page, dashboard, admin panel, e-commerce, SaaS, portfolio, blog, mobile app, .html, .tsx, .vue, .svelte. Elements: button, modal, navbar, sidebar, card, table, form, chart. Styles: glassmorphism, claymorphism, minimalism, brutalism, neumorphism, bento grid, dark mode, responsive, skeuomorphism, flat design. Topics: color palette, accessibility, animation, layout, typography, font pairing, spacing, hover, shadow, gradient."

2,8652,517

pdf-to-markdown

aliceisjustplaying

Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions "load the whole PDF", "bring the PDF into context", "read the entire PDF", or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.

3,7881,649

flutter-development

aj-geddes

Build beautiful cross-platform mobile apps with Flutter and Dart. Covers widgets, state management with Provider/BLoC, navigation, API integration, and material design.

2,1481,640

drawio-diagrams-enhanced

jgtolentino

Create professional draw.io (diagrams.net) diagrams in XML format (.drawio files) with integrated PMP/PMBOK methodologies, extensive visual asset libraries, and industry-standard professional templates. Use this skill when users ask to create flowcharts, swimlane diagrams, cross-functional flowcharts, org charts, network diagrams, UML diagrams, BPMN, project management diagrams (WBS, Gantt, PERT, RACI), risk matrices, stakeholder maps, or any other visual diagram in draw.io format. This skill includes access to custom shape libraries for icons, clipart, and professional symbols.

2,2621,465

godot

bfollington

This skill should be used when working on Godot Engine projects. It provides specialized knowledge of Godot's file formats (.gd, .tscn, .tres), architecture patterns (component-based, signal-driven, resource-based), common pitfalls, validation tools, code templates, and CLI workflows. The `godot` command is available for running the game, validating scripts, importing resources, and exporting builds. Use this skill for tasks involving Godot game development, debugging scene/resource files, implementing game systems, or creating new Godot components.

2,4591,222

nano-banana-pro

garg-aayush

Generate and edit images using Google's Nano Banana Pro (Gemini 3 Pro Image) API. Use when the user asks to generate, create, edit, modify, change, alter, or update images. Also use when user references an existing image file and asks to modify it in any way (e.g., "modify this image", "change the background", "replace X with Y"). Supports both text-to-image generation and image-to-image editing with configurable resolution (1K default, 2K, or 4K for high resolution). DO NOT read the image file first - use this skill directly with the --input-image parameter.

1,953967