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 Agent-Engineer-Master/skill-engineer --skill marp-slidesgit clone --depth 1 https://github.com/Agent-Engineer-Master/skill-engineerWrote 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/agent-engineer-master/skill-engineer/marp-slides)<a href="https://agentmods.dev/skills/agent-engineer-master/skill-engineer/marp-slides"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/marp-slides/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/agent-engineer-master/skill-engineer/marp-slides"><img src="https://agentmods.dev/badge/skills/agent-engineer-master/skill-engineer/marp-slides.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 | $0.00113 | $0.01340 |
| Opus 5.5 | $0.00045 | $0.00536 |
| Sonnet 5.5 | $0.00023 | $0.00268 |
| Haiku 4.5 | $0.00011 | $0.00134 |
Grade C, and why
marp-slides 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 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.
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.
<!-- Built with Agent Engineer Master — get your own production-ready skill: www.agentengineermaster.com/skill-engineer --> How it starts
The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MARP Slides
Startup
- Read
references/learnings.md— summarize the 3 most relevant bullets for this task - Detect mode from the request (see Mode Selector)
Mode Selector
| Request signals | Mode |
|---|---|
| "create", "build", "make slides", "new deck", "presentation" | A: Create |
| "edit", "update", "change slide N", "revise", "fix" | B: Edit |
| "theme only", "CSS only", "just the styles", "color palette" | C: Theme |
| "convert from", "turn this into slides", "import", "use this outline" | D: Convert |
| "summarize this deck", "what does this cover", "read this marp" | E: Read |
Mode A: Create
A1. Intake (ask all at once in a single message)
Present these 4 questions before generating anything:
- Topic + purpose — what is the deck about, and who is the audience?
- Slide count — how many slides? (if unsure, apply word-count heuristic from
references/quality-rules.md) - Theme — dark (default) or light? Describe a vibe or brand if relevant.
- Brand context — use existing brand colors/logo? (if yes, read your brand guidelines file)
Wait for reply before continuing.
Why: Generating before intent is locked is the #1 source of wasted cycles in deck authoring. The 4-question intake costs one round-trip and saves 3–5 regeneration loops.
A2. Theme + outline
- Select theme using signal-to-theme mapping table in
references/themes.md - Draft a slide-by-slide outline: slide title, one key idea, layout type, visual element planned
- Present 3 layout direction options (e.g. minimal / data-heavy / editorial) — not full decks, just 3-slide skeleton previews as markdown
- Wait for user to approve direction or request changes before generating the full deck
A3. Generate
- Read
references/components.mdfor SVG chart and component patterns - Read
references/layout-patterns.mdfor rotation rules and composition guidelines - Read 2–3 examples from
examples/that most closely match the approved style - Generate the full
.mdMARP file
What ships with it
16 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.
- evals/evals.json 4.1 KB
- evals/judge.md 3.0 KB
- evals/rubric.md 4.1 KB
- examples/marp_coffee.md 24 KB
- examples/marp_comparison.md 9.5 KB
- examples/marp_facebook-ads.md 40 KB
- examples/marp_fitness.md 11 KB
- examples/marp_hero.md 3.2 KB
- examples/marp_sample.md 37 KB
- references/cli-guide.md 3.6 KB
- references/components.md 11 KB
- references/edge-cases.md 1.1 KB
- references/layout-patterns.md 4.6 KB
- references/learnings.md 3.7 KB
- references/quality-rules.md 3.0 KB
- references/themes.md 5.7 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 · 121 lines · 113 tokens per session scan C bf50bd1fa433
marp-slides is a skill published in the GitHub repository Agent-Engineer-Master/skill-engineer (8 stars, last pushed 3mo ago), licensed MIT. It adds 113 tokens to every session and 1,340 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-08-31.
Other skills, from other repositories
openspec-verify-change
Verify implementation matches OpenSpec change artifacts. Use when the user wants to validate that implementation is complete, correct, and coherent before archiving. Also use when the user says "openspec verify" or "opsx verify".
openspec-new-change
Start a new OpenSpec change using the experimental artifact workflow. Use when the user wants to create a new feature, fix, or modification with a structured step-by-step approach. Also use when the user says "openspec new change" or "opsx new".
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
memory-system
A guide to giving an AI agent persistent, user-specific memory across conversations. It covers what to remember, how to store it, how to update or compress it, and when to use memory instead of a shared knowledge base.
extract
Run the full Semantica semantic extraction pipeline on a file or selected text — NER, relations, events, coreference resolution, triplets, and validation. Clears result cache before each run. Returns Markdown tables with entity/relation/event/triplet results and inline validator warnings.
writing
A writing guide for turning verified facts and calculations into finished text for a specific audience. It follows the requested language, structure, and length.