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 vstorm-co/content-skills --skill content-presentationgit clone --depth 1 https://github.com/vstorm-co/content-skillsWrote 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/vstorm-co/content-skills/content-presentation)<a href="https://agentmods.dev/skills/vstorm-co/content-skills/content-presentation"><img src="https://agentmods.dev/badge/skills/vstorm-co/content-skills/content-presentation/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/vstorm-co/content-skills/content-presentation"><img src="https://agentmods.dev/badge/skills/vstorm-co/content-skills/content-presentation.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 | $0.00072 | $0.02208 |
| Opus 5 | $0.00036 | $0.01104 |
| Sonnet 5 | $0.00014 | $0.00442 |
| Haiku 4.5 | $0.00007 | $0.00221 |
Grade A, and why
content-presentation 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 — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Content Presentation Skill
Purpose
Generate complete, brand-aligned presentation decks in multiple frameworks. This skill handles everything from narrative structure to slide-by-slide code output with speaker notes.
Framework Selection Guide
Choose the framework based on the use case. If the user has no preference, default based on context:
| Framework | Best For | Default When |
|---|---|---|
| Slidev | Developer talks, markdown-first workflows, Vue-based teams, heavy code content | The audience is technical, the content has code, or no preference stated |
| Reveal.js | Classic presentations, maximum browser compatibility, HTML/CSS/JS control | The user needs broad compatibility or prefers HTML-native authoring |
| Spectacle | React teams, custom interactive components, rich animations | The team uses React or needs interactive slide components |
| Raw HTML | Single portable file, no build step, email-embeddable, offline delivery | The user needs one file they can send or open anywhere |
See frameworks/ for detailed guides on each:
frameworks/slidev.md-- Markdown syntax, layouts, components, themingframeworks/reveal-js.md-- Setup, transitions, fragments, speaker notes, PDF exportframeworks/spectacle.md-- React components, deck structure, themes, animationsframeworks/raw-html.md-- Single-file structure, inline CSS, embedded fonts, responsive slides
Generation Flow
Follow this sequence exactly. Do not skip steps.
Step 1: Read Brand Context
Read these files if they exist:
brand/BRAND.md-- identity, audience, differentiatorsbrand/VISUAL.md-- colors, fonts, logo rulesbrand/VOICE.md-- tone, vocabulary, anti-patterns
If brand/ is missing, ask the user for basic color, font, and tone preferences before proceeding. Do not generate a deck with default blue-and-white styling.
Step 2: Clarifying Questions
Ask 3-5 targeted questions. Adapt based on what you already know:
- Length: How many slides? (Offer a range based on type: pitch deck 10-15, conference talk 30-40, sales deck 12-18.)
- Audience: Who is in the room? Technical depth, seniority, familiarity with the topic.
- Purpose: What should the audience do after the last slide? (Buy, approve, learn, share, hire.)
- Data available: Do you have specific stats, case studies, screenshots, or code to include?
- Delivery context: Live talk, async read, recorded video, or print handout?
What ships with it
12 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.
- brand-integration.md 6.1 KB
- frameworks/raw-html.md 7.8 KB
- frameworks/reveal-js.md 6.2 KB
- frameworks/slidev.md 5.2 KB
- frameworks/spectacle.md 5.5 KB
- presentation-narrative.md 7.7 KB
- slide-patterns.md 6.8 KB
- templates/client-proposal.html.template 7.3 KB
- templates/conference-talk.reveal.template 5.6 KB
- templates/pitch-deck.slidev.template 5.6 KB
- templates/sales-deck.slidev.template 6.9 KB
- templates/workshop.spectacle.template 7.5 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.
- 9d ago First seen · 215 lines · 72 tokens per session scan A 54ed21a8bbe1
content-presentation is a skill published in the GitHub repository vstorm-co/content-skills (22 stars, last pushed 4mo ago), licensed MIT. It adds 72 tokens to every session and 2,208 once invoked, about $0.0004 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
frame-logo-outro
Segmented logo assembly, glow bloom, and tagline reveal for video outros or brand closing frames.
html-presentation
Converts documents, outlines, or notes into self-contained HTML slide decks with horizontal (Reveal.js) or vertical scroll navigation and multiple themes. Triggers on: "create a presentation", "slide deck", "pitch deck", "HTML presentation", "web-based slides", "reveal.js deck", "convert document into slides".
marp-slides
Author MARP markdown slide decks exportable to PDF, PPTX, and HTML via marp-cli. Covers Marpit directives, custom CSS themes, SVG chart recipes, and dashboard components. Triggers on: "marp", "marp deck", "markdown slides", "slides from markdown", "marp-cli", "pdf from markdown", "pptx from markdown".
template-pitch-deck
Pitch-deck generation exemplar — short/medium/long PDF+PPTX decks from one token-resolved, diligence-cited content source.
template-storybook
Full-page illustrated storybook exemplar — symbolic shape-family characters, page-level raster scenes, text overlays, deterministic PDF assembly.
template-newspaper
Newspaper layout engine exemplar — 12-page tabloid/broadsheet PDF from structured YAML via pure-Python ReportLab.