Agent skill

Slides Grab HTML

by NomaDamas in NomaDamas/slides-grab

HTML-mode presentation pipeline usable in Codex and Claude Code.

MITAuto-check passedDocuments & Office

Install Slides Grab HTML

skills CLI
$ npx skills add NomaDamas/slides-grab --skill slides-grab-html -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NomaDamas/slides-grab slides-grab-html --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NomaDamas/slides-grab.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/slides-grab-html .claude/skills/slides-grab-html && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
slides-grab-html
GitHub stars
1.2k
Token cost
~1.6k tokens
SKILL.md length
744 words
Files
1
Skills in repo
7
Repo updated
First seen
Licence
MIT

At a glance

HTML-mode presentation pipeline usable in Codex and Claude Code.

  • Works in 3 steps: Plan → Design → Export
  • The deck needs editable
  • SKILL.md covers Mode signal, Bespoke imagery rule, Workflow and Rules, plus 1 more section
  • Calls codex; reaches cdn.jsdelivr.net; needs OPENAI_API_KEY and GOOGLE_API_KEY

What it does

Slides Grab HTML is an agent skill from NomaDamas/slides-grab. HTML-mode presentation pipeline usable in Codex and Claude Code. Build semantic slide-XX.html files, generate bespoke hero/accent imagery with slides-grab image, run the design gate, and export. Use when the deck needs editable, searchable, accessible text or when no existing template must be matched pixel-for-pixel.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering Slides and decks. The repository describes itself as: Best harness + editor + linter for generating slides in Claude Code / Codex - Claude Design Open Source Alternative. The licence is MIT.

When your agent uses it

  • The deck needs editable
  • Accessible text
  • No existing template must be matched pixel-for-pixel

Example prompts

  • “/slides-grab-html”

Requirements

  • A credential in OPENAI_API_KEY
  • A credential in GOOGLE_API_KEY

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Plan
  2. Design
  3. Export

What it can do on your machine

Read from SKILL.md and the folder at commit 49bdaed. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • codex

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • cdn.jsdelivr.net

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY
    • GOOGLE_API_KEY
    • GEMINI_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Slides Grab HTML loads about 1.6k tokens when it runs. Until then it costs about 84 tokens; SKILL.md has 744 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~84
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NomaDamas/slides-grab at commit 49bdaed, republished under its MIT licence (© NomaDamas). 744 words, ~1,630 tokens.

Download SKILL.mdSave it as .claude/skills/slides-grab-html/SKILL.md (or your agent's skills folder).
name
slides-grab-html
description
HTML-mode presentation pipeline usable in Codex and Claude Code. Build semantic slide-XX.html files, generate bespoke hero/accent imagery with slides-grab image, run the design gate, and export. Use when the deck needs editable, searchable, accessible text or when no existing template must be matched pixel-for-pixel.
metadata.short-description
Semantic HTML slide pipeline with bespoke imagery

slides-grab HTML Skill

Build semantic slide-XX.html files where text is real HTML (selectable, editable, accessible) and imagery is generated as supporting accent/hero assets — never as whole-slide rasters. Use this pipeline when the user wants a deck they can edit, when slides contain charts or diagrams, or when no existing template demands pixel-perfect visual matching.

Mode signal

The plan stage records mode: html in slide-outline.md. If no mode is recorded, default to this pipeline.

Bespoke imagery rule

  • Use slides-grab image to generate individual hero/accent images that sit beside or behind semantic text inside an HTML slide. The generated image is a supporting visual — text and layout stay in HTML/CSS.
  • A bespoke image prompt describes the accent visual only — the atmospheric mood, the hero illustration, the background texture — not the slide's title, body copy, or layout. Let HTML handle text and layout.
  • Good prompt: "Atmospheric dawn horizon, cyan and silver tones, dreamy Y2K mood, no text, 16:9" — describes a hero background.
  • If you instead need the generated image to BE the whole slide (title, body, layout burned into the raster), use the image-native pipeline (../slides-grab-image/SKILL.md) — semantic HTML is the wrong tool for that.

Workflow

Stage 1 — Plan

Use the installed slides-grab-plan skill.

  1. Take topic, audience, and tone.
  2. Run slides-grab list-styles, shortlist 2–3 bundled styles, get explicit approval. Optionally offer slides-grab preview-styles. If none fit, propose a custom direction. If the user provides a reference template/PDF/PPTX for color tokens only (not pixel-perfect matching), import it with slides-grab import-template and record style: template-pack — the template pack supplies design tokens, but slides stay semantic HTML.
  3. Record mode: html in slide-outline.md meta.
  4. Present outline, revise until approved.
Stage 2 — Design

Use the installed slides-grab-design skill.

  1. Read approved slide-outline.md, load the style spec (src/design-styles-data.js for bundled ids, slides-grab show-design for DESIGN.slides.md, or .slides-grab/template-pack.json for imported packs).
  2. Write a visual thesis, content plan, system declaration, and design tokens before generating slides.
  3. Generate slide-XX.html semantic HTML files with 2-digit numbering in --slides-dir.
  4. Bespoke imagery: when a slide needs a hero/accent image, run slides-grab image --prompt "<accent-visual prompt>" --slides-dir <path>. The default codex provider reuses the local Codex ChatGPT login (~/.codex/auth.json — run codex login once; no API key required). Save under <slides-dir>/assets/. To guide the style, pass reference images with --reference <path> (repeatable). Optional providers: --provider openai (OpenAI gpt-image-2 via OPENAI_API_KEY), --provider nano-banana (Google gemini-3-pro-image-preview via GOOGLE_API_KEY/GEMINI_API_KEY, supports --image-size 2K|4K). If credentials are unavailable, fall back to web search + download into <slides-dir>/assets/.
  5. Diagrams: for complex diagrams (architecture, workflows, relationship maps), use tldraw via slides-grab tldraw, store under <slides-dir>/assets/.
  6. Charts: default to Chart.js (<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>), start from templates/chart.html, keep animation: false, responsive: true, maintainAspectRatio: false, wrap <canvas> in a stable container. slides-grab validate reports empty-canvas for unpainted canvases.
  7. Video: store under <slides-dir>/assets/, prefer poster="./assets/<file>". Use slides-grab fetch-video or yt-dlp for web sources.
  8. Icons: prefer Lucide before emoji.
  9. Run slides-grab validate --slides-dir <path>. Auto-fix failures until it passes.
  10. Run the design gate (../slides-grab-design/references/design-gate.md): capture PNG evidence, run Pass A (System Contract) + Pass B (Audience Impact), synthesize verdict. Resolve all Critical findings, re-render, re-review until Proceed. Record with slides-grab design-gate --slides-dir <path> --verdict proceed --pass-a-report <a.md> --pass-b-report <b.md>.
  11. Launch the HTML editor: slides-grab edit --slides-dir <path>. For chart decks, also run slides-grab build-viewer and confirm charts render in viewer.html.
Show full SKILL.md (193 more words)Show less
Stage 3 — Export

Use the installed slides-grab-export skill. Requires a fresh Proceed gate receipt.

  1. Widescreen → slides-grab pdf --slides-dir <path> --output <name>.pdf.
  2. Per-slide PNG → slides-grab png --slides-dir <path> --output-dir <path>/out-png --resolution 2160p.
  3. Card-news → slides-grab png --slide-mode card-news (see ../slides-grab-card-news).
  4. PPTX/Figma (experimental / unstable) → slides-grab convert / slides-grab figma.

Rules

  • Keep slide size 720pt × 405pt.
  • Keep semantic text tags (p, h1-h6, ul, ol, li). Never put text directly in <div>/<span>.
  • Backgrounds only on <div>; text only in semantic tags.
  • No CSS gradients — use flat fills; rasterize gradients to PNG with Sharp if needed.
  • Put local images/videos under <slides-dir>/assets/, reference as ./assets/<file>.
  • Allow data: URLs when a slide must be self-contained; never leave remote http(s):// image URLs in saved HTML.
  • Prefer Lucide for iconography; avoid emoji unless the brief explicitly asks.
  • Keep body copy ≥14pt on a 720pt × 405pt slide; 10pt absolute floor.
  • Avoid AI slop tropes (aggressive gradient backgrounds, left-border accent cards, SVG-drawn imagery, generic font stacks, generic 3×2 icon-plus-blurb grids).
  • Do not present slides for review until slides-grab validate passes.
  • Do not advance to export while any Critical design-gate finding is unresolved.

Reference

  • ../slides-grab-plan/SKILL.md and ../slides-grab-plan/references/
  • ../slides-grab-design/SKILL.md and ../slides-grab-design/references/
  • ../slides-grab-export/SKILL.md and ../slides-grab-export/references/

© NomaDamas, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/slides-grab-html of NomaDamas/slides-grab.

Open the folder on GitHubat commit 49bdaed

Compare with similar skills

Slides Grab HTML next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Slides Grab HTML compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Slides Grab HTML this skillNomaDamas/slides-grab1.2k—~1.6kAutomated safety check: PassMIT
Image To Editable Pptningzimu/image-to-editable-ppt-skill2.8k—~4.3kAutomated safety check: PassMIT
Codex Slidesnexu-io/codex-slides9241 repos~3kAutomated safety check: PassMIT
Slidesfcakyon/claude-codex-settings1.2k1 repos~1.1kAutomated safety check: PassMIT
Ppt Image FirstNyxTides/ppt-image-first1.2k—~1.6kAutomated safety check: PassApache-2.0
Vibe to Agentic Engineering Frameworkshanraisshan/claude-code-best-practice67k—~3.3kAutomated safety check: PassMIT

Similar skills

  • Image To Editable Ppt

    ningzimu/image-to-editable-ppt-skill

    Rebuild slide images, scanned or image-based PPT/PPTX files, and PDF decks into object-level editable PowerPoint (.pptx), preserving speaker notes when supplied.

    2.8k GitHub stars~4.3k tokensUpdated 22 days ago
    Documents & OfficeAuto-check passed
  • Codex Slides

    nexu-io/codex-slides

    Create, research, revise, restyle, present, inspect, and export Codex Slides slide decks from Codex, including scenario workflows, project Design Files, and always-on brand design systems.

    924 GitHub starsUsed in 1 repo~3k tokens
    Documents & OfficeAuto-check passed
  • Slides

    fcakyon/claude-codex-settings

    Create and edit presentation slide decks (.pptx) with PptxGenJS, bundled layout helpers, and render/validation utilities.

    1.2k GitHub starsUsed in 1 repo~1.1k tokens
    Documents & OfficeAuto-check passed
  • Ppt Image First

    NyxTides/ppt-image-first

    Build presentation plans for PPT / slides / decks through a conversation-first workflow, then propose multiple visual directions with preview images before writing deck specs.

    1.2k GitHub stars~1.6k tokensUpdated 5 mo ago
    Documents & OfficeAuto-check passed
  • Vibe to Agentic Engineering Framework

    shanraisshan/claude-code-best-practice

    Explains the conceptual model behind a presentation on moving from unstructured vibe coding to fully configured agentic engineering, including its 4-level scoring system and slide conventions.

    67k GitHub stars~3.3k tokensUpdated today
    Documents & OfficeAuto-check passed
  • Gpt Image2 Ppt

    JuneYaooo/gpt-image2-ppt-skills

    Generate visually striking PPT slides via OpenAI's gpt-image-2 -- use any style in styles/<collection/STYLEID.md or mimic a user-supplied .pptx template; outputs high-res slide PNGs and a 16:9 .pptx.

    1.3k GitHub stars~8.9k tokensUpdated 1 mo ago
    Documents & OfficeAuto-check: notes

More from NomaDamas/slides-grab

  • Slides Grab Image

    NomaDamas/slides-grab

    Image-native presentation pipeline usable in Codex and Claude Code.

    1.2k GitHub stars~2.1k tokensUpdated 7 days ago
    Auto-check passed
  • Slides Grab

    NomaDamas/slides-grab

    End-to-end presentation workflow usable in Codex and Claude Code.

    1.2k GitHub stars~1.3k tokensUpdated 7 days ago
    Auto-check passed
  • Slides Grab Design

    NomaDamas/slides-grab

    Stage 2 design skill usable in Codex and Claude Code. An agent skill from NomaDamas/slides-grab.

    1.2k GitHub stars~3.7k tokensUpdated 7 days ago
    Auto-check passed
  • Slides Grab Export

    NomaDamas/slides-grab

    Stage 3 conversion skill usable in Codex and Claude Code. An agent skill from NomaDamas/slides-grab.

    1.2k GitHub stars~1k tokensUpdated 7 days ago
    Auto-check passed
  • Slides Grab Plan

    NomaDamas/slides-grab

    Stage 1 planning skill usable in Codex and Claude Code. An agent skill from NomaDamas/slides-grab.

    1.2k GitHub stars~1.8k tokensUpdated 7 days ago
    Auto-check passed
  • Slides Grab Card News

    NomaDamas/slides-grab

    Generate square Instagram-style card news by reusing the slides-grab workflow with card-news mode enabled.

    1.2k GitHub stars~532 tokensUpdated 7 days ago
    Auto-check passed

Questions about Slides Grab HTML

What does Slides Grab HTML do?

HTML-mode presentation pipeline usable in Codex and Claude Code. Slides Grab HTML is an agent skill from NomaDamas/slides-grab. HTML-mode presentation pipeline usable in Codex and Claude Code.

When should I use Slides Grab HTML?

Slides Grab HTML fits situations like: the deck needs editable; accessible text; no existing template must be matched pixel-for-pixel.

How do I install Slides Grab HTML in Claude Code?

Run `npx skills add NomaDamas/slides-grab --skill slides-grab-html -a claude-code`. Or copy the skill folder (skills/slides-grab-html in NomaDamas/slides-grab) into .claude/skills/slides-grab-html in your project. Claude Code loads it when a task matches its description.

How do I install Slides Grab HTML in Codex?

Run `npx skills add NomaDamas/slides-grab --skill slides-grab-html -a codex`. Or copy the skill folder (skills/slides-grab-html in NomaDamas/slides-grab) into .agents/skills/slides-grab-html in your project. Codex loads it when a task matches its description.

Can I use Slides Grab HTML in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NomaDamas/slides-grab --skill slides-grab-html -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/slides-grab-html, .gemini/skills/slides-grab-html, .github/skills/slides-grab-html and .opencode/skills/slides-grab-html in your project.

What does Slides Grab HTML need to run?

Going by SKILL.md and its folder, Slides Grab HTML needs the command-line tools its instructions call (codex) and credentials named OPENAI_API_KEY, GOOGLE_API_KEY and GEMINI_API_KEY. Our summary lists: A credential in OPENAI_API_KEY; A credential in GOOGLE_API_KEY.

Does Slides Grab HTML access the network?

SKILL.md names 1 domain. In commands or code: cdn.jsdelivr.net; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Slides Grab HTML safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Slides Grab HTML use?

Slides Grab HTML is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Slides Grab HTML use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Slides Grab HTML?

Skills that share tags, products or a category with Slides Grab HTML: Image To Editable Ppt (ningzimu/image-to-editable-ppt-skill, 2.8k stars), Codex Slides (nexu-io/codex-slides, 924 stars), Slides (fcakyon/claude-codex-settings, 1.2k stars) and Ppt Image First (NyxTides/ppt-image-first, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Slides Grab HTML?

NomaDamas (a GitHub organization) maintains it in NomaDamas/slides-grab, which has 1,212 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on October 1, 2026.

Source: NomaDamas/slides-grab on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.