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 cyyeh/skills-playground --skill system-to-coursegit clone --depth 1 https://github.com/cyyeh/skills-playgroundWrote 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/cyyeh/skills-playground/system-to-course)<a href="https://agentmods.dev/skills/cyyeh/skills-playground/system-to-course"><img src="https://agentmods.dev/badge/skills/cyyeh/skills-playground/system-to-course/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/cyyeh/skills-playground/system-to-course"><img src="https://agentmods.dev/badge/skills/cyyeh/skills-playground/system-to-course.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 | $0.00115 | $0.03122 |
| Opus 5 | $0.00057 | $0.01561 |
| Sonnet 5 | $0.00023 | $0.00624 |
| Haiku 4.5 | $0.00012 | $0.00312 |
Grade C, and why
system-to-course 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 12d 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.
<!-- page-context: system: "[System Name]" description: "[One-line description from Overview]" page: "[Page Title]" level: "[Level Label]" --> How it starts
The opening of the file, as written. The whole thing — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
System-to-Course
Transform a structured analysis.md into a multi-page static HTML course. Each page is self-contained (inline CSS/JS), linked via shared navigation, and organized by depth levels (Beginner/Intermediate/Advanced) with inline level badges for visual clarity.
First-Run Welcome
When triggered, explain what you do:
I generate interactive HTML courses from system analysis files.
Point me at an analysis:
- From a prior analyzer run — I'll look for
[output-dir]analysis.mdautomatically- A specific file — e.g., "generate course from ./my-analysis.md"
The output is a multi-page static site with interactive diagrams, code snippets, quizzes, and cross-page navigation. Content is organized by depth level with inline badges. All self-contained — just open
index.html.
Output Directory
Always ask the user where to save the generated course files before writing any files. Use AskUserQuestion to prompt:
Where would you like me to save the generated HTML course? Default:
dist/[system-name]/
Accept the user's chosen path. If they accept the default or say something like "that's fine" or "default", use dist/[system-name]/. Store this path as [output-dir].
Exception: When called by the system-explorer orchestrator with a pre-determined output directory, use that directory without re-asking.
Create the directory if it does not exist.
Input
The skill supports two input formats. Always detect automatically:
- Multi-file format (v2): Check for
[output-dir]/analysis.jsonfirst. If found, this is the new multi-file format — read the manifest to discover section files. Confirm with the user. - Legacy single-file format: If no
analysis.jsonexists, check for[output-dir]/analysis.md. If found, use the legacy single-file parsing. Confirm with the user. - Direct file path: Accept a path to any markdown file structured with level tags (
<!-- level: ... -->).
Verify the input has valid level tags before proceeding. If level tags are missing, warn the user and add sensible defaults based on heading depth.
What ships with it
4 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.
- 12d ago First seen · 228 lines · 115 tokens per session scan C f4674bfccc7f
system-to-course is a skill published in the GitHub repository cyyeh/skills-playground (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 115 tokens to every session and 3,122 once invoked, about $0.0006 per session on Opus 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
starter
Static web development for beginners — HTML/CSS/JS and Next.js App Router. Triggers: static website, portfolio, landing page, beginner.
vibehub
A terminology helper for Vibe Coding tasks, where software is built from natural-language requests. It turns vague descriptions into clearer technical wording and identifies useful terms for interface, web, software, Git, AI-agent, or design concepts.
fireworks-open-eli5
Create evidence-aware, interactive visual explainers as self-contained offline HTML. Use when a user asks to explain a concept, repository module, engineering tradeoff, or incident with a diagram, walkthrough, ELI5 treatment, data/request trace, failure view, or teach-back. Do not use for a plain short answer…
教程类H5-小红书小工具
A method for building offline, single-page course experiences for Xiaohongshu’s Mini Tools, which are interactive pages published inside the platform. It combines written lessons, generated illustrations, and JavaScript page switching in a constrained container.
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…