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 agentmods add skills/manalkaff/opendesign/make-a-decknpx skills add manalkaff/opendesign --skill make-a-deckgit clone --depth 1 https://github.com/manalkaff/opendesignWrote 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/manalkaff/opendesign/make-a-deck)<a href="https://agentmods.dev/skills/manalkaff/opendesign/make-a-deck"><img src="https://agentmods.dev/badge/skills/manalkaff/opendesign/make-a-deck.svg" alt="Measured on agentmods" 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 | $0.00047 | $0.01137 |
| Opus 5 | $0.00023 | $0.00568 |
| Sonnet 5 | $0.00009 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00114 |
Grade A, and why
make-a-deck 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 3d 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 — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Loaded when the user asks for a slide presentation.
Output location
Write all output files to ./opendesign/mockups/<task-slug>/. Derive the slug from the deck topic (e.g. q3-board-update, product-launch).
Role shift
You are a presentation designer — a consultant, analyst, or executive preparing for a boardroom. You are not a web designer. The output is HTML, but the design thinking is slide-native: fixed canvas, chapter-driven flow, read from across the room.
Intake
Ask for deck length in minutes if it is not given. Length drives slide count, pacing, and how much text per slide is defensible. Also confirm: audience, delivery mode (live vs. read-alone), brand context, required sections.
Canvas
- 1920×1080 by default. Fixed-size canvas. Letterbox on smaller viewports; scale uniformly with JS.
- One
<section>per slide. - Never reflow slides to viewport width. Slides are compositions, not responsive pages.
Type scale and spacing constants
Define these at the top of the stylesheet and reference them from every slide. Never use ad-hoc pixel values.
:root {
--title: 64px;
--subtitle: 44px;
--body: 34px;
--small: 28px;
--pad-top: 100px;
--pad-bottom: 80px;
--pad-x: 100px;
--title-gap: 52px;
--item-gap: 28px;
}
Adjust the numbers to the brand if one is given, but the structure stays the same: named constants only, referenced everywhere.
Web defaults (14–16px body, 48–72px padding) are too small for slides. Do not regress to them.
When the user specifies sizes in points, convert: px = pt × 1.333. "36pt body" → 48px body.
Title discipline
- Pick ONE grammatical style for titles across the entire deck and stick to it. Either topic noun-phrases (
Market position,Why now,The path forward) or short declarative sentences (Our margins are shrinking,We need to move first). Do not mix. - Titles should read like chapters. Someone reading only the titles should follow the story.
- The title sequence is a standalone deliverable. Write every title first. Read them back as a block. Check they tell the story of the deck without any slide content. Revise until the title list alone is coherent.
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.
- 3d ago First seen · 102 lines · 47 tokens per session scan A d52636e0c98f
make-a-deck is a skill published in the GitHub repository manalkaff/opendesign (255 stars, last pushed 2mo ago), licensed MIT. It adds 47 tokens to every session and 1,137 once invoked, about $0.0002 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
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
exploratory-data-analysis
Perform bounded, local exploratory analysis of explicitly supported scientific files. Use for redacted CSV/TSV/JSON profiles; optional NumPy, HDF5, FASTA/FASTQ, and basic image metadata inspection; missingness/leakage audits; outlier and transformation sensitivity; and rigorous EDA report scaffolds. Other domain…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
docx-comment-reply
Reply to comments (批注) in Word .docx/.doc files: extract comment context, draft replies, write threaded replies back, and validate OOXML.
file-forensics
Examine what a file claims about itself and what it actually contains — powered by Apache Tika. True content-based type detection (extensions lie), provenance claims (authors, dates, creating application), revision and tamper signals (PDF incremental updates, tracked changes, hidden slides, zip integrity), hidden and…