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 CHENyiru3/AI-Skills-Collections --skill duke-nus-marpgit clone --depth 1 https://github.com/CHENyiru3/AI-Skills-CollectionsWrote 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/chenyiru3/ai-skills-collections/duke-nus-marp)<a href="https://agentmods.dev/skills/chenyiru3/ai-skills-collections/duke-nus-marp"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/duke-nus-marp/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/chenyiru3/ai-skills-collections/duke-nus-marp"><img src="https://agentmods.dev/badge/skills/chenyiru3/ai-skills-collections/duke-nus-marp.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 | $0.00066 | $0.01500 |
| Opus 5.5 | $0.00026 | $0.00600 |
| Sonnet 5.5 | $0.00013 | $0.00300 |
| Haiku 4.5 | $0.00007 | $0.00150 |
Grade A, and why
duke-nus-marp 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 — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Duke-NUS Marp slides
Produce editable Markdown with the bundled Duke-NUS CSS, source-grounded Harvard citations, and checked renders. User-specified content, slide count, location, and citation variants take precedence over defaults.
Assets and scope
assets/duke-nus.css: 1280 × 720 theme, Arial, blue #00539B, orange #F5821F, gray #4D4F53, online logo at https://i.imgur.com/hh3DOb2.png. Preserve this URL unless the user requests a change.assets/starter.md: minimal deck including Harvard references.assets/example.md: layout examples with explicitly fictional citation placeholders.references/marp-guide.md: read before authoring for syntax, class behavior, Harvard conventions, and export options.
The theme is a personal adaptation of the user's Duke-NUS PowerPoint, not an official template release. Use the bundled assets; no original machine-specific folder is required.
Work in the requested output directory. Read applicable local instructions, especially inside the Obsidian vault. Copy assets to the project before editing; do not modify the installed skill as part of making a deck. When an existing project has a customized theme or configuration, inspect and preserve it unless the user asks for replacement. Do not update vault indexes merely because slide sources live inside the vault.
Authoring decisions
- Inspect the supplied content and identify audience, purpose, and supported conclusions. Use reasonable assumptions for routine layout choices. Ask only for missing information that materially changes the talk.
- Select the needed layouts from the example, then replace the examples with the actual content. Do not force every deck to include every layout. Honor the requested slide count, including references and cover unless the user specifies otherwise.
- Keep one main point per slide. Preserve units, uncertainty, qualifiers, and attribution. Leave clear placeholders for missing data rather than inventing findings or sources.
- Use
#for the masthead title and an immediately following##for its optional subtitle. Both should fit one line on ordinary content slides. Use###for body headings. - Use local directives
<!-- _class: ... -->to avoid leaking layout changes to later slides. Supported classes aretitle,section,closing,figure,compact,references, andcenter. Use_paginate: skipon covers/closing slides when excluding them from the count. - Use plain Markdown for routine content. The optional
columns/wide-leftdivs need blank lines around their Markdown contents and HTML rendering enabled. In thefigurelayout, the last paragraph is the caption. Contain scientific figures without cropping evidence.
What ships with it
5 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.
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 · 72 lines · 66 tokens per session scan A 0475b5df3678
duke-nus-marp is a skill published in the GitHub repository CHENyiru3/AI-Skills-Collections (2 stars, last pushed 3d ago), licensed MIT. It adds 66 tokens to every session and 1,500 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 2026-11-11.
duke-nus-marp compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| duke-nus-marpCHENyiru3/AI-Skills-Collections | Skill | 2 | 3d ago | MIT | A | 66 | Claude Code, Codex |
| instrument-data-to-allotropeanthropics/knowledge-work-plugins | Skill | 36k | yesterday | Apache-2.0 | A | 123 | Claude Code |
| matlabK-Dense-AI/scientific-agent-skills | Skill | 57k | 5d ago | MIT | A | 44 | Claude Code |
| exploratory-data-analysisK-Dense-AI/scientific-agent-skills | Skill | 57k | 5d ago | MIT | A | 83 | Claude Code |
| phylogeneticsK-Dense-AI/scientific-agent-skills | Skill | 57k | 5d ago | MIT | A | 71 | Claude Code, Codex |
| research-engineerdavila7/claude-code-templates | Skill | 34k | today | MIT | A | 43 | Claude Code, Codex |
| mapping-to-snomedmaziyarpanahi/openmed | Skill | 5.8k | yesterday | Apache-2.0 | A | 205 | Claude Code |