slides-grab is a tool for creating and editing presentations as HTML and CSS files, with an editor that lets coding agents work on selected parts of a slide and export decks to PDF or experimental PPTX files. It is for people generating presentations with Claude Code, Codex, and related agents. The catalogue entries provide skills, agents, and instructions for its presentation workflow.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add NomaDamas/slides-grab --skill slides-grab-htmlgit clone --depth 1 https://github.com/NomaDamas/slides-grabWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/nomadamas/slides-grab/slides-grab-html)<a href="https://agentmods.dev/skills/nomadamas/slides-grab/slides-grab-html"><img src="https://agentmods.dev/badge/skills/nomadamas/slides-grab/slides-grab-html/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nomadamas/slides-grab/slides-grab-html"><img src="https://agentmods.dev/badge/skills/nomadamas/slides-grab/slides-grab-html.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Rogue Agent · line 33 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00069 | $0.01635 |
| Opus 5 | $0.00034 | $0.00817 |
| Sonnet 5 | $0.00014 | $0.00327 |
| Haiku 4.5 | $0.00007 | $0.00163 |
Grade A, and why
slides-grab-html scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 68 lines — stays where its author put it; the contents beside it link to each section on GitHub.
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 imageto 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.
- Take topic, audience, and tone.
- Run
slides-grab list-styles, shortlist 2–3 bundled styles, get explicit approval. Optionally offerslides-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 withslides-grab import-templateand recordstyle: template-pack— the template pack supplies design tokens, but slides stay semantic HTML. - Record
mode: htmlinslide-outline.mdmeta. - Present outline, revise until approved.
Stage 2 — Design
Use the installed slides-grab-design skill.
- Read approved
slide-outline.md, load the style spec (src/design-styles-data.jsfor bundled ids,slides-grab show-designforDESIGN.slides.md, or.slides-grab/template-pack.jsonfor imported packs). - Write a visual thesis, content plan, system declaration, and design tokens before generating slides.
- Generate
slide-XX.htmlsemantic HTML files with 2-digit numbering in--slides-dir. - 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— runcodex loginonce; 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 viaOPENAI_API_KEY),--provider nano-banana(Googlegemini-3-pro-image-previewviaGOOGLE_API_KEY/GEMINI_API_KEY, supports--image-size 2K|4K). If credentials are unavailable, fall back to web search + download into<slides-dir>/assets/. - Diagrams: for complex diagrams (architecture, workflows, relationship maps), use
tldrawviaslides-grab tldraw, store under<slides-dir>/assets/. - Charts: default to Chart.js (
<script src="https://cdn.jsdelivr.net/npm/chart.js"></script>), start fromtemplates/chart.html, keepanimation: false,responsive: true,maintainAspectRatio: false, wrap<canvas>in a stable container.slides-grab validatereportsempty-canvasfor unpainted canvases. - Video: store under
<slides-dir>/assets/, preferposter="./assets/<file>". Useslides-grab fetch-videooryt-dlpfor web sources. - Icons: prefer Lucide before emoji.
- Run
slides-grab validate --slides-dir <path>. Auto-fix failures until it passes. - 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 untilProceed. Record withslides-grab design-gate --slides-dir <path> --verdict proceed --pass-a-report <a.md> --pass-b-report <b.md>. - Launch the HTML editor:
slides-grab edit --slides-dir <path>. For chart decks, also runslides-grab build-viewerand confirm charts render inviewer.html.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 68 lines · 69 tokens per session scan A d00a01bb7dde
slides-grab-html is a skill published in the GitHub repository NomaDamas/slides-grab (1,204 stars, last pushed 2d ago), licensed MIT. It adds 69 tokens to every session and 1,635 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
powerpoint-ppt
PowerPoint (.pptx) manipulation via MCP server. Use for creating slides, formatting presentations, managing placeholders, adding images, applying templates, or extracting text from .pptx files.
presentation-forge
A workflow for creating editable PowerPoint presentations and related visual outputs from topics, documents, slides, templates, or images. It supports Chinese business reports and can use generated visual assets.
ppt-master
AI-driven presentation workflow for generating editable PPTX decks and slides, reconstructing page visuals, creating reusable Brand/Style/Layout/Deck workspaces, filling native PPTX templates, and enhancing finished PPTX files. Use when the user asks to create, generate, reconstruct, regenerate, beautify, redesign…
deck-ljg-present
A presentation template that converts an outline or Markdown document into large, poster-like slides while keeping the original wording, order, and content. It uses black, red, or yellow colour themes and assigns document elements to slide layouts.
xiaobei-skill-academic-paper-to-ppt
A workflow that turns academic papers, reports, and technical documents into presentation slides, optionally following a supplied PowerPoint template. It creates a written outline, full-slide images, and a PowerPoint file.
guizang-ppt-skill
A tool that creates slide-deck images from content by first making an outline and then rendering each slide. It supports multiple visual styles and is designed for decks people can read and share.