Now liveThe Skillselion MCP - thousands of ranked skills, loaded into your agent mid-task. No install.Get it →
vkehfdl1 avatar

Slides Grab Design

  • 13 installs
  • 1.2k repo stars
  • Updated July 17, 2026
  • vkehfdl1/slides-grab

Helps with design & ui/ux tasks.

About

slides-grab-design is a Claude Code skill for design & ui/ux. It helps solo builders move faster with AI-assisted development.

  • slides-grab-design
  • Design & UI/UX
  • AI-coding skill

Slides Grab Design by the numbers

  • 13 all-time installs (skills.sh)
  • Ranked #1,418 of 1,880 Design & UI/UX skills by installs in the Skillselion catalog
  • Data as of Aug 5, 2026 (Skillselion catalog sync)
npx skills add https://github.com/vkehfdl1/slides-grab --skill slides-grab-design

Add your badge

Show developers this skill is listed on Skillselion. Paste this into your README.

Listed on Skillselion
Installs13
repo stars1.2k
Last updatedJuly 17, 2026
Repositoryvkehfdl1/slides-grab

What it does

Helps with design & ui/ux tasks.

Files

SKILL.mdMarkdownGitHub ↗

slides-grab Design Skill (Codex)

Use this after slide-outline.md is approved.

Goal

Generate high-quality slide-XX.html files in the selected slides workspace (slides/ by default) and support revision loops.

Inputs

  • Approved slide-outline.md (must contain style: <id> in meta section — style was approved in Stage 1)
  • Requested edits per slide

Outputs

  • <slides-dir>/slide-01.html ... slide-XX.html
  • Updated <slides-dir>/viewer.html via build script

Workflow

1. Read approved slide-outline.md and extract the style field from its meta section. 2. Load the chosen style's full spec:

  • If style is a bundled id (e.g. glassmorphism), load from src/design-styles-data.js — colors, fonts, layout, signature elements, and things to avoid.
  • If style ends in .md (e.g. ./DESIGN.slides.md or ./DESIGN.md), or if a design markdown file exists at the project root, parse it with slides-grab show-design <path> and treat the parsed output as the authoritative design system (colors, typography, layout, components, signature, avoid).
  • Precedence when both files exist: DESIGN.slides.md takes priority over DESIGN.md. The .slides.md version is the slide-flavored conversion produced by the plan stage and is the only file safe to apply to slide HTML. If only DESIGN.md exists, treat it as web-flavored and follow the slide layout/avoid rules in references/design-rules.md strictly to avoid leaking web-only components (top-nav, CTA buttons, footer-band columns, pricing grids) into slides — or, preferably, switch back to the plan stage and produce a DESIGN.slides.md first.
  • If the meta specifies a written custom direction, use that as the design basis.

3. Before generating slides, write a quick visual thesis (mood/material/energy), a content plan (opener → support/proof → detail/story → close/CTA), a system declaration (reused layout patterns, max two background colors, max two typefaces, image-led vs text-led slides, where section dividers reset tempo), and the core design tokens (background, surface, text, muted, accent + display/headline/body/caption roles). Ground these tokens in the chosen style's spec. Follow references/beautiful-slide-defaults.md for the full working model, content discipline, color discipline, and AI slop tropes to avoid. 4. If you need to confirm or revisit the approved bundled style before designing, re-run slides-grab list-styles and open the gallery from slides-grab preview-styles so the Stage 2 deck stays aligned with the Stage 1 direction. 5. Generate slide HTML files with 2-digit numbering in selected --slides-dir. 6. When a slide needs iconography, prefer Lucide as the default icon library. Use clean Lucide icons before falling back to emoji, and only use emoji when the brief explicitly calls for them. 7. When a slide explicitly needs bespoke imagery, when the user asks for an image, or when stronger imagery would materially improve the slide, prefer slides-grab image --prompt "<prompt>" --slides-dir <path> to generate a local asset with the default god-tibo-imagen provider (which reuses the local Codex ChatGPT login — no API key required) and save it under <slides-dir>/assets/. 8. If the deck needs a complex diagram (architecture, workflows, relationship maps, multi-node concepts), create the diagram in tldraw, export it with slides-grab tldraw, and treat the result as a local slide asset under <slides-dir>/assets/. 9. If the slide needs a local video, store the video under <slides-dir>/assets/, reference it as ./assets/<file>, and prefer a poster="./assets/<file>" thumbnail so PDF export uses a stable still image. 10. If the source video starts on YouTube or another supported page, use slides-grab fetch-video --url <youtube-url> --slides-dir <path> (or yt-dlp directly if needed) to download it into <slides-dir>/assets/ before saving the slide HTML. 11. Run slides-grab validate --slides-dir <path> after generation or edits. 12. If validation fails, automatically fix the source slide HTML/CSS and re-run validation until it passes. 13. Run the slide litmus check from references/beautiful-slide-defaults.md before presenting the deck for review. 14. Launch the interactive editor for visual review: slides-grab edit --slides-dir <path> 15. Iterate on user feedback by editing only requested slide files, then re-run validation after each edit round. 16. When the user confirms editing is complete, suggest: build the viewer (slides-grab build-viewer --slides-dir <path>) for a final read-only preview, or proceed to export (PDF/PPTX). 17. Keep revising until user approves conversion stage.

Rules

  • Keep slide size 720pt x 405pt.
  • Keep semantic text tags (p, h1-h6, ul, ol, li).
  • Put local images and videos under <slides-dir>/assets/ and reference them as ./assets/<file>.
  • Allow data: URLs when the slide must be fully self-contained.
  • Do not leave remote http(s):// image URLs in saved slide HTML; download source images into <slides-dir>/assets/ and reference them as ./assets/<file>.
  • Prefer Lucide for default slide iconography. Avoid emoji as the default icon treatment unless the brief explicitly asks for emoji.
  • Prefer slides-grab image with the default god-tibo-imagen provider for bespoke slide imagery before reaching for remote URLs.
  • The default provider, god-tibo-imagen, reuses the local Codex ChatGPT login (~/.codex/auth.json) — run codex login once to enable it; no API key required. ⚠️ god-tibo-imagen calls an unsupported private Codex backend that may break without notice. Optional alternatives: --provider codex (Codex/OpenAI gpt-image-2 via OPENAI_API_KEY; maps --aspect-ratio to the nearest supported OpenAI image size), or --provider nano-banana (Google Nano Banana / gemini-3-pro-image-preview via GOOGLE_API_KEY or GEMINI_API_KEY; supports --image-size 2K|4K). If image generation credentials are unavailable, fall back to web search + download into <slides-dir>/assets/.
  • Prefer local videos with a poster="./assets/<file>" thumbnail so PDF export uses the still image.
  • Use slides-grab fetch-video or yt-dlp to pull supported web videos into <slides-dir>/assets/ before saving slide HTML.
  • Prefer <img> for slide imagery and data-image-placeholder when no final asset exists.
  • Default to one job per slide, one dominant visual anchor, and copy that scans in seconds.
  • Treat opening slides and section dividers like posters, not dashboards.
  • Default to cardless layouts; only add a card when it improves structure or comprehension.
  • Use whitespace, alignment, scale, cropping, and contrast before adding decorative chrome.
  • Do not pad slides with filler copy, dummy stats, or decorative iconography — when a slide feels empty, solve it with layout and scale, not invented content.
  • Pull every color from the approved style spec or the user's brand tokens; extend only with harmonic oklch() neighbors. Do not invent fresh standalone hex colors mid-slide.
  • Keep body copy at 14pt minimum on a 720pt × 405pt slide and never render any text below the 10pt absolute floor.
  • Avoid AI slop tropes — aggressive gradient backgrounds, left-border accent cards, SVG-drawn imagery, generic font stacks (Inter/Roboto/Arial), and generic 3×2 icon-plus-blurb grids. See references/beautiful-slide-defaults.md for the full list.
  • Prefer tldraw for complex diagrams instead of recreating dense node/edge diagrams directly in HTML/CSS.
  • Use slides-grab tldraw plus templates/diagram-tldraw.html when that gives a cleaner, more export-friendly result.
  • Do not present slides for review until slides-grab validate --slides-dir <path> passes.
  • Do not start conversion before approval.
  • Use the packaged CLI and bundled references only; do not depend on unpublished agent-specific files.

Reference

For full constraints and style system, follow:

  • references/design-rules.md
  • references/detailed-design-rules.md
  • references/beautiful-slide-defaults.md — slide-specific art direction defaults adapted from OpenAI's frontend design guidance and Anthropic's Claude design system guidance (content/color discipline, system declaration, AI slop tropes)
  • references/design-system-full.md — archived full design system, templates, and advanced pattern guidance

Related skills

This week in AI coding

Five minutes, every Monday - the tools, releases and tactics for developers.

unsubscribe anytime.