Useslidekit logo

Useslidekit

Community
Dragoon0x
useslidekit

Comprehensive presentation design skill for Claude Code. Projection-aware design, audience-adaptive layouts, narrative architecture, perceptual data visualization, anti-AI-slop detection, rehearsal intelligence, and multi-format export. Complements Anthropic's built-in PPTX skill.

Overview

PublisherDragoon0x
Repositoryuseslidekit
Skill nameuseslidekit
Stars
3
Forks
0
Bundled files
34
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.

  • 34 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by Dragoon0x on GitHub. Read the source before you install it.

Installation

Install the Useslidekit 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/Dragoon0x/useslidekit/tree/main
  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/Dragoon0x/useslidekit.git \
  .claude/skills/useslidekit
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Useslidekit 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 Useslidekit 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 Useslidekit 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.

useSlideKit

When to Use

Activate when the user asks to create, improve, redesign, or review a presentation, deck, slides, pitch, or keynote. This skill handles content strategy, design precision, and quality assurance. It complements (never conflicts with) Anthropic's built-in PPTX skill which handles file generation.

Quick Start

  1. Identify audience → Load references/AUDIENCE.md, select profile
  2. Structure narrative → Load references/NARRATIVE.md, choose framework
  3. Design slides → Load references/DESIGN-SYSTEM.md for visual rules
  4. Add data → Load references/DATA-VIZ.md for chart precision
  5. Add motion → Load references/MOTION.md for animation rules
  6. Write speaker notes → Load references/SPEAKER.md for rehearsal prep
  7. Quality check → Load references/RUBRIC.md, score, refine if < 80
  8. Anti-slop scan → Load references/ANTI-SLOP.md, fix detections
  9. Glance test → Load references/GLANCE-TEST.md on every slide
  10. Export → Load references/EXPORT.md for format-specific rules

Core Principles

The Glance Test (applies to every slide)

A person should understand the slide's point in 3 seconds. Not read every word. Understand the point. If they can't, the slide has too much content, unclear hierarchy, or a topic-label heading instead of an assertion heading. See references/GLANCE-TEST.md.

Audience-First Design

Every design decision — density, typography, color, animation, speaker notes — changes based on who is watching. An investor deck is not a conference talk is not a team update is not a workshop handout. Load references/AUDIENCE.md FIRST. Everything else follows.

Projection-Aware Color

Screens emit light. Projectors reflect it. This means: lower contrast in bright rooms, color temperature shifts, washed-out pastels. Every color choice must account for the viewing environment. See references/DESIGN-SYSTEM.md §2.

Assertion Headlines

Every slide title is a complete sentence stating the takeaway. Not "Revenue" but "Revenue grew 34% year-over-year driven by enterprise expansion." The headline IS the message. The body is evidence. If you read only the headlines in sequence, you should understand the entire presentation. This is the Ghost Deck Test.

Intake Questions (ask before building)

#QuestionDefault if unanswered
1Who is the audience?General professional
2What is the one thing you want them to DO after?Understand and agree
3Presentation or async reading?Presented live
4Projector, screen, or both?Screen (laptop/monitor)
5Duration?15 minutes
6How many slides max?12-15
7Brand colors/fonts?Neutral dark theme
8Data available?No — use narrative evidence
9Tone?Confident, clear, direct
10Export format?PPTX

Workflow

INTAKE → AUDIENCE PROFILE → NARRATIVE FRAMEWORK → OUTLINE
→ SLIDE DESIGN → DATA VIZ → SPEAKER NOTES → MOTION
→ GLANCE TEST → ANTI-SLOP SCAN → RUBRIC SCORE → EXPORT

Stage 1: Intake & Audience Profile

Gather answers to 10 questions. Load references/AUDIENCE.md. Select the matching profile (investor, conference, internal, workshop, async). The profile sets defaults for density, typography scale, animation level, and speaker note depth.

Stage 2: Narrative Architecture

Load references/NARRATIVE.md. Choose the right framework based on purpose:

  • Persuade → Problem-Agitation-Solution (PAS)
  • Inform → Situation-Complication-Resolution (SCR)
  • Teach → What-So What-Now What
  • Sell → Before-After-Bridge Select framework, write the 1-sentence thesis, build the 3-5 point structure.

Stage 3: Outline & Slide Titles

Write assertion-headline for every slide. Run the Ghost Deck Test: read only the headlines in order. Do they tell the complete story? If not, restructure. Reference: SLIDE-PATTERNS.md for per-slide-type specs.

Stage 4: Slide Design

Load references/DESIGN-SYSTEM.md. Apply typography scale, color system, spacing grid, and layout rules from the audience profile.

Stage 5: Data Visualization

Load references/DATA-VIZ.md. For every data point: select chart type from the decision matrix, apply perceptual encoding rules, add annotations.

Stage 6: Speaker Notes

Load references/SPEAKER.md. Generate per-slide notes with timing, transition cues, and key phrases. Add Q&A prep for predictable questions.

Stage 7: Motion Design

Load references/MOTION.md. Add entrance animations for content reveals, transitions between slides, and chart build sequences. Respect reduced-motion.

Stage 8: Quality Assurance

  1. Run the Glance Test on every slide (references/GLANCE-TEST.md)
  2. Run the Anti-Slop scan (references/ANTI-SLOP.md)
  3. Score with the 100-point rubric (references/RUBRIC.md)
  4. If score < 80, identify 3 weakest areas, fix, re-score (max 2 iterations)

Stage 9: Export

Load references/EXPORT.md. Generate in requested format. Use Anthropic's built-in PPTX skill for .pptx file creation.

Reference Files (loaded on demand)

FileWhat It ContainsLoad When
references/AUDIENCE.md7 audience profiles with complete design presetsAlways — load first
references/NARRATIVE.md4 storytelling frameworks with selection criteriaStage 2
references/DESIGN-SYSTEM.mdTypography, color, spacing, layout — projection-awareStage 4
references/COLOR-PALETTES.md12 complete themed palettes with screen + stage variantsStage 4
references/TYPOGRAPHY-DEEP.mdFont pairing matrix, weight mapping, hierarchy system, number typographyStage 4
references/SLIDE-PATTERNS.md9 per-slide-type specs with exact measurementsStage 3-4
references/DATA-VIZ.mdChart selection matrix, annotation rules, perceptual encodingStage 5
references/TABLES.mdTable design, number formatting, comparison table patternsStage 5
references/ICONOGRAPHY.mdIcon sizing, style rules, circle treatment, source librariesStage 4-5
references/SPEAKER.mdRehearsal intelligence, timing, transitions, Q&A prepStage 6
references/MOTION.mdAnimation timing, easing, transition rulesStage 7
references/TRANSITIONS.mdPacing curve, slide pairs, transition phrases, flow anti-patternsStage 7
references/GLANCE-TEST.md3-second comprehension test methodologyStage 8
references/ANTI-SLOP.md30 AI presentation slop patterns with detection/fixesStage 8
references/RUBRIC.md100-point quality scoring with testable criteriaStage 8
references/CHECKLIST.md40-item pre-flight checklist (content, visual, structural, export)Stage 8
references/ACCESSIBILITY.mdWCAG contrast, color blindness, cognitive load, alt textAll stages
references/VIRTUAL.mdZoom/Teams/Meet-specific design rules and sizingStage 4 (if virtual)
references/INDUSTRY.mdIndustry-specific patterns for 7 sectorsStage 2-4
references/HANDOUT.mdAdapting a presentation into a self-contained leave-behindStage 9
references/CONTENT-DENSITY.mdExact word/bullet/element counts per audience × slide typeStage 3-4
references/WHITESPACE.md30% rule, spacing hierarchy, breathing slides, margin specsStage 4
references/IMAGE-TREATMENT.mdCrop rules, overlay opacities, resolution requirements, screenshot treatmentStage 4-5
references/CODE-SLIDES.mdCode formatting, syntax highlighting palettes, terminal stylingStage 4 (if code)
references/BRAND-ADAPTATION.mdBrand audit checklist, color/font/logo adaptation rulesStage 1-4
references/RESPONSIVE.mdAspect ratio handling, safe zones for multi-ratioStage 4
references/OPENING-SLIDES.mdFirst 3 slides methodology, hook types, problem framingStage 3
references/CLOSING-SLIDES.mdLast 3 slides, CTA patterns, Q&A handlingStage 3
references/PACING-CALCULATOR.mdDuration planning, per-slide timing, pacing patternsStage 6
references/NUMBER-FORMATTING.mdDisplay rules, alignment, change indicators, precision, contextStage 4-5
references/DIAGRAM-PATTERNS.mdProcess, hierarchy, funnel, matrix, cycle, architecture diagram specsStage 4-5
references/LANGUAGE-PRECISION.mdHeadline formulas, bullet compression, words to deleteStage 3-4
references/EXPORT.mdMulti-format output rules (PPTX, HTML, PDF)Stage 9

useSlideKit by Dragoon0x. Educational and experimental. DYOR.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Useslidekit AI skill do?

Comprehensive presentation design skill for Claude Code. Projection-aware design, audience-adaptive layouts, narrative architecture, perceptual data visualization, anti-AI-slop detection, rehearsal intelligence, and multi-format export. Complements Anthropic's built-in PPTX skill.

Why use Useslidekit on TypingMind?

Because you install it once and use it with any model. Useslidekit 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 Useslidekit in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Dragoon0x/useslidekit/tree/main. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Useslidekit?

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 Useslidekit?

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

Is the Useslidekit AI skill free?

It is published on GitHub by Dragoon0x. 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 👇