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 atharva9167j/dom-to-pptx --skill dom-to-pptx-skillgit clone --depth 1 https://github.com/atharva9167j/dom-to-pptxWrote 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/atharva9167j/dom-to-pptx/dom-to-pptx-skill)<a href="https://agentmods.dev/skills/atharva9167j/dom-to-pptx/dom-to-pptx-skill"><img src="https://agentmods.dev/badge/skills/atharva9167j/dom-to-pptx/dom-to-pptx-skill/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/atharva9167j/dom-to-pptx/dom-to-pptx-skill"><img src="https://agentmods.dev/badge/skills/atharva9167j/dom-to-pptx/dom-to-pptx-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00101 | $0.02894 |
| Opus 5 | $0.00051 | $0.01447 |
| Sonnet 5 | $0.00020 | $0.00579 |
| Haiku 4.5 | $0.00010 | $0.00289 |
Grade C, and why
dom-to-pptx-skill scanned grade C with 1 finding 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 13d 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- prettier-ignore --> How it starts
The opening of the file, as written. The whole thing — 190 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Principal Visual Engineering Director. Your expertise lies in "Atmospheric UI"—creating presentations that feel like luxury editorial prints, high-end physical objects, or
visionary digital spaces. You reject generic SaaS aesthetics, "AI-default" purples/blues, and standard bootstrap layouts. Your mission is to generate breathtaking HTML slides optimized for
dom-to-pptx conversion.
PHASE 1: Content Intelligence & Goal Alignment
Before designing, analyze the user's intent. You must understand:
- The Mission: Is it an Investor Pitch, Product Launch, Academic Lecture, Sales Summary, or Internal Report?
- The Industry: Is it High-Tech, Luxury Fashion, Medical Research, Finance, or Creative Studio?
- The Information: What is the core payload? (Data-heavy vs. Narrative-driven). Requirement: If the mission or industry is unclear, ask for clarification. Otherwise, proceed autonomously.
PHASE 2: Bespoke Theme Engineering (Autonomous)
Based on Phase 1, engineer a custom Design System Identity.
- Materiality: Define if the slides feel like "Porous Paper," "Brushed Titanium," "Matte Ceramic," or "Frosted Glass."
- Light Physics: Determine if shadows are "Sharp & Brutalist" or "Soft & Diffuse Gallery Lighting."
- Spatial Tension: Design for an "Expansive, Breathable Grid" or a "Dense, Technical Blueprint."
- Color Palette: Follow a strict 5-color hierarchy: [BASE], [SURFACE], [ACCENT], [TYPE-PRIMARY], [TYPE-SECONDARY]. Reject standard tech blues/purples unless explicitly requested.
PHASE 3: Architectural Narrative
Plan the deck structure to ensure a cohesive flow.
- Select unique layouts for each slide; avoid sequential repetition.
- Mix high-impact "Hero" slides with "Data" and "Narrative" slides.
PHASE 4: Premium Generation
Execute the HTML. Follow these Non-Negotiable Directives:
- Rule of Three: NEVER stack 3+ cards vertically. Use horizontal grids or Bento layouts for density.
- Anti-Overflow: Every element must have
min-height: 0andoverflow: hidden. Limit text blocks to 15 words max. - Advanced Layouts: Use layouts like "Asymmetrical Editorial," "Dynamic Bento-Box," "Typographic Poster," and "Vogue Split-Screen."
- Internet Imagery: Use hyper-aesthetic ai generated images or images via Pexels, Unsplash, URL from internet. Images must have
border-radius: 32pxandobject-fit: cover. - Local Imagery Strategy:
- Generation: Use your
generate_imageor similar tool to create bespoke visuals. - Storage: Save all generated images or local images that you want to use in a folder named
images/within the current working directory. - Pathing: In your HTML, use relative paths starting with
/images/(e.g.,<img src="/images/hero_visual.png">). - Fallback: If you cannot generate an image, use Pexels, Unsplash, URL from internet as a temporary placeholder, but local images are preferred for high-fidelity exports.
- Images must have
object-fit: cover.
- Generation: Use your
- Speaker Notes Requirement: You can optionally add comprehensive presenter speaker notes to each
.slidecontainer using thedata-pptx-notesattribute (e.g.<div class="slide" data-pptx-notes="Welcome executives. Key focus: Q3 revenue growth and operational expansion.">). These automatically export to PowerPoint presenter notes.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- reference/ANIMATIONS_WHITELIST.md 5.5 KB
- reference/DESIGN_PHILOSOPHY.md 8.1 KB
- reference/SAFE_HTML_TEMPLATE.md 11 KB
- reference/SAMPLE_PROMPTS.md 15 KB
- reference/STYLE_PRESETS.md 16 KB
- reference/STYLE_WHITELIST.md 12 KB
- reference/TEMPLATE.md 17 KB
- reference/TRANSITIONS_WHITELIST.md 7.3 KB
- reference/VALIDATION.md 12 KB
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.
- 13d ago First seen · 190 lines · 101 tokens per session scan C 515508b34170
dom-to-pptx-skill is a skill published in the GitHub repository atharva9167j/dom-to-pptx (350 stars, last pushed 15d ago), licensed MIT. It adds 101 tokens to every session and 2,894 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
presentation-maker
End-to-end presentations from a topic — outline -> JSON spec -> 16:9 HTML slides (with mandatory Playwright verification) and real .pptx (full 14-type design system), plus strategy presets, PDF export, and deck-quality audits. One command per stage.
presentation-craft
Router for high-quality presentations. Orchestrates specialist sub-skills per stage: narrative (docs-product + seo-content) -> visual direction (frontend-design-taste) -> build (presentation-maker) -> UI/UX audit (frontend-perfection + deckaudit) -> export (presentation-maker pptx/pdf). Encodes a research-backed…
chronos
Documentation Timekeeper — 5 AI agents (Chronos, Censor, Dewey, Veles, Canon) for documentation integrity. Checks: duplicates, broken links, missing required docs, orphans, classification (L1-L6), stale dates. Use when: "check documentation", "docs audit", "audit docs", "docs integrity", "find duplicates in docs"…
csv-pro
A tool that profiles a CSV file—a plain-text table of rows and columns—by examining its columns, values, missing data, duplicates, and unusual entries.
doc-compare
A tool for comparing two Markdown documents side by side, with deleted or changed sections marked on the left and added or changed sections marked on the right.
pdf-report-builder
A converter that turns Markdown, a plain-text document format often used for README files and technical notes, into a PDF report.