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 appautomaton/presentation --skill deck-design-pdfgit clone --depth 1 https://github.com/appautomaton/presentationWrote 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/appautomaton/presentation/deck-design-pdf)<a href="https://agentmods.dev/skills/appautomaton/presentation/deck-design-pdf"><img src="https://agentmods.dev/badge/skills/appautomaton/presentation/deck-design-pdf/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/appautomaton/presentation/deck-design-pdf"><img src="https://agentmods.dev/badge/skills/appautomaton/presentation/deck-design-pdf.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 | $0.00065 | $0.06687 |
| Opus 5.5 | $0.00026 | $0.02675 |
| Sonnet 5.5 | $0.00013 | $0.01337 |
| Haiku 4.5 | $0.00006 | $0.00669 |
Grade A, and why
deck-design-pdf 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 1mo 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
60 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.
- build-reference.md 27 KB
- chart-taxonomy.md 20 KB
- density-adaptation.md 5.6 KB
- engagement-archetypes.md 4.9 KB
- engine/canvas.css 1.0 KB
- engine/index.js 5.3 KB runs code
- engine/render.js 1.9 KB runs code
- evidence-recipes.md 5.4 KB
- examples/bar-horizontal.js 6.7 KB runs code
- examples/before-after.js 4.8 KB runs code
- examples/bubble-scatter.js 9.7 KB runs code
- examples/burndown.js 8.7 KB runs code
- examples/capability-matrix.js 7.1 KB runs code
- examples/clustered-bars.js 6.3 KB runs code
- examples/cohort-retention.js 6.7 KB runs code
- examples/communication-cascade.js 8.6 KB runs code
- examples/coverage-matrix.js 7.6 KB runs code
- examples/data-table.js 5.1 KB runs code
- examples/decision-flow.js 8.7 KB runs code
- examples/donut.js 9.6 KB runs code
- examples/driver-tree.js 7.6 KB runs code
- examples/dumbbell-benchmark.js 7.1 KB runs code
- examples/economic-value-stack.js 5.7 KB runs code
- examples/eval-grid.js 6.9 KB runs code
- examples/facts-perspectives.js 8.0 KB runs code
- examples/fan-chart.js 8.4 KB runs code
- examples/funnel.js 8.7 KB runs code
- examples/gantt.js 5.4 KB runs code
- examples/heatmap.js 6.3 KB runs code
- examples/indexed-lines.js 8.2 KB runs code
- examples/kpi-cards.js 3.7 KB runs code
- examples/kpi-cascade.js 8.8 KB runs code
- examples/line-chart.js 7.9 KB runs code
- examples/marimekko.js 9.0 KB runs code
- examples/matrix-2x2.js 8.1 KB runs code
- examples/network-map.js 8.2 KB runs code
- examples/org-model.js 8.8 KB runs code
- examples/pareto.js 6.6 KB runs code
- examples/process-flow.js 7.7 KB runs code
- examples/radar.js 5.6 KB runs code
- examples/rag-status.js 6.1 KB runs code
- examples/rapid-map.js 10 KB runs code
- examples/sankey.js 7.0 KB runs code
- examples/scenario-lines.js 7.7 KB runs code
- examples/screening-funnel.js 8.8 KB runs code
- examples/stacked-bar-100.js 5.4 KB runs code
- examples/stacked-bar.js 7.3 KB runs code
- examples/stakeholder-map.js 9.9 KB runs code
- examples/swimlane.js 9.4 KB runs code
- examples/three-horizons.js 9.1 KB runs code
- examples/timeline.js 4.1 KB runs code
- examples/tornado.js 5.7 KB runs code
- examples/treemap.js 8.4 KB runs code
- examples/waterfall.js 7.5 KB runs code
- firm-dna.md 3.0 KB
- ghost-deck.md 7.0 KB
- package-lock.json 1.6 KB
- package.json 104 B
- palettes/anthropic-consulting.css 1.2 KB
- palettes/consulting-bain.css 1.1 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.
- 1mo ago First seen · 383 lines · 65 tokens per session scan A 7fef8da58691
deck-design-pdf is a skill published in the GitHub repository appautomaton/presentation (64 stars, last pushed 1mo ago), with no licence file. It adds 65 tokens to every session and 6,687 once invoked, about $0.0003 per session on Opus 5.5. 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
document-design
Creates print-ready HTML that exports to PDF. Use to make a proposal, report, one-pager, newsletter, slides, or flyer.
design-export-repair
Fixes broken decks/PDFs exported from Claude's "Design" feature (or similar AI deck generators) — cut-off or clipped text, wrong/substituted fonts, and corrupted .pptx package structure that shows up only once you export to PDF, not while looking at it in the app. Use this skill whenever the user uploads a zip, .pptx…
sales-deck-production
Produção do artefato final de propostas e apresentações — HTML com print CSS (uma seção por página, quebras controladas, fontes embutidas) exportado para PDF em navegador headless, componentes de página, variante deck e checagem obrigatória do PDF (páginas, overflow, fontes, peso). Use ao montar, exportar, corrigir ou…
huashu-md-to-pdf
Convert Markdown documents into professional Apple-style PDF white papers. Supports full Markdown syntax (code blocks, tables, blockquotes, lists, etc.). Auto-generates cover page, table of contents, and headers/footers. Use cases: technical documentation, white papers, tutorials, reports — any Markdown document…
travel-guidebook
A workflow for creating designed travel guidebook PDFs from trip itineraries. It researches destinations, structures the route, writes the content, builds an HTML guide, checks it, and exports the result as a PDF.
pdf-html
Exports design- HTML artifacts to single-page PDFs using headless Chromium. Targets the same .canvas / [class="canvas-"] conventions as screenshot-html, but outputs vector PDFs sized to each canvas's exact pixel dimensions rather than PNG rasters. Use when the desired output is a shareable PDF — audit reports, client…