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/softaworks/agent-toolkit/marp-slidenpx skills add softaworks/agent-toolkit --skill marp-slidegit clone --depth 1 https://github.com/softaworks/agent-toolkitWrote 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/softaworks/agent-toolkit/marp-slide)<a href="https://agentmods.dev/skills/softaworks/agent-toolkit/marp-slide"><img src="https://agentmods.dev/badge/skills/softaworks/agent-toolkit/marp-slide.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 | $0.00064 | $0.02134 |
| Opus 5 | $0.00032 | $0.01067 |
| Sonnet 5 | $0.00013 | $0.00427 |
| Haiku 4.5 | $0.00006 | $0.00213 |
Grade A, and why
marp-slide 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 4d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- marp-slide — 100% identical, 0 lines differ
- marp-slide — 94% identical, 23 lines differ
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Marp Slide Creator
Create professional, visually appealing Marp presentation slides with 7 pre-designed themes and built-in best practices.
When to Use This Skill
Use this skill when the user:
- Requests to create presentation slides or Marp documents
- Asks to "make slides look good" or "improve slide design"
- Provides vague instructions like "良い感じにして" (make it nice) or "かっこよく" (make it cool)
- Wants to create lecture or seminar materials
- Needs bullet-point focused slides with occasional images
Quick Start
Step 1: Select Theme
First, determine the appropriate theme based on the user's request and content.
Quick theme selection:
- Technical/Developer content → tech theme
- Business/Corporate → business theme
- Creative/Event → colorful or gradient theme
- Academic/Simple → minimal theme
- General/Unsure → default theme
- Dark background preferred → dark or tech theme
For detailed theme selection guidance, read references/theme-selection.md.
Step 2: Create Slides
-
Read relevant references first:
- Always start by reading
references/marp-syntax.mdfor basic syntax - For images:
references/image-patterns.md(official Marpit image syntax) - For advanced features (math, emoji):
references/advanced-features.md - For custom themes:
references/theme-css-guide.md
- Always start by reading
-
Copy content from the appropriate template file:
assets/template-basic.md- Default theme (most common)assets/template-minimal.md- Minimal themeassets/template-colorful.md- Colorful themeassets/template-dark.md- Dark mode themeassets/template-gradient.md- Gradient themeassets/template-tech.md- Tech/code themeassets/template-business.md- Business theme
-
Read
references/best-practices.mdfor quality guidelines -
Structure content following best practices:
- Title slide with
<!-- _class: lead --> - Concise h2 titles (5-7 characters in Japanese)
- 3-5 bullet points per slide
- Adequate whitespace
- Title slide with
What ships with it
22 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.
- assets/template-basic.md 2.1 KB
- assets/template-business.md 2.8 KB
- assets/template-colorful.md 2.7 KB
- assets/template-dark.md 2.3 KB
- assets/template-gradient.md 2.7 KB
- assets/template-minimal.md 1.9 KB
- assets/template-tech.md 2.8 KB
- assets/theme-business.css 3.6 KB
- assets/theme-colorful.css 2.9 KB
- assets/theme-dark.css 2.4 KB
- assets/theme-default.css 2.5 KB
- assets/theme-gradient.css 2.9 KB
- assets/theme-minimal.css 1.7 KB
- assets/theme-tech.css 3.5 KB
- README.md 7.5 KB
- references/advanced-features.md 6.6 KB
- references/best-practices.md 3.3 KB
- references/image-patterns.md 4.8 KB
- references/marp-syntax.md 3.5 KB
- references/official-themes.md 5.5 KB
- references/theme-css-guide.md 5.3 KB
- references/theme-selection.md 3.9 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.
- 4d ago First seen · 238 lines · 64 tokens per session scan A 4244be1fd746
marp-slide is a skill published in the GitHub repository softaworks/agent-toolkit (2,422 stars, last pushed 6mo ago), licensed MIT. It adds 64 tokens to every session and 2,134 once invoked, about $0.0003 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
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
writing
将共享历史中的已验证事实和计算结果整理成符合受众、格式与长度约束的成稿。.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
ccc
This skill should be used when code search is needed (whether explicitly requested or as part of completing a task), when indexing the codebase after changes, or when the user asks about ccc, cocoindex-code, or the codebase index. Trigger phrases include 'search the codebase', 'find code related to', 'update the…