course-builder: Skill for Claude Code

.claude/skills/asset-build/SKILL.md

asset-build is a skill for Claude Code from tobyilee/course-builder. It costs 50 tokens per session (1,377 once invoked), scanned C, original, MIT.

A final course-packaging step turns a reviewed course into a deployment bundle. Marp is a tool that converts Markdown slide files into HTML, while SSML is structured text for speech synthesis.

In plain words
What is it for?
Use it at the end of a course build to render slides, check quizzes and transcripts, assemble metadata, and package the course for deployment.
Why use it?
It checks required tools and course files, refreshes slides, validates quizzes and speech markup, builds a course manifest, and creates bundle.zip after coherence review passes.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is tobyilee/course-builder's own configuration. It tells Claude Code how to work on course-builder itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything course-builder configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tobyilee/course-builder. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tobyilee/course-builder/main/.claude/skills/asset-build/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tobyilee/course-builder

Made for: Claude Code.

Wrote 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.

agentmods badge for asset-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/tobyilee/course-builder/asset-build/github.svg)](https://agentmods.dev/skills/tobyilee/course-builder/asset-build)
Your own site
<a href="https://agentmods.dev/skills/tobyilee/course-builder/asset-build"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/asset-build/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.

agentmods 80×15 button for asset-build

Your own site · 80×15
<a href="https://agentmods.dev/skills/tobyilee/course-builder/asset-build"><img src="https://agentmods.dev/badge/skills/tobyilee/course-builder/asset-build.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,377 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00050 $0.01377
Opus 5.5 $0.00020 $0.00551
Sonnet 5.5 $0.00010 $0.00275
Haiku 4.5 $0.00005 $0.00138

Measured 2mo ago against content hash dc462cc5c249, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

asset-build 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 2mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/build-bundle.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf course/build
.claude/skills/asset-build/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Asset Build — Deployable Bundle

coherence-reviewer가 overall: "pass" 판정한 뒤 수행. Idempotent — 여러 번 돌려도 결과 동일.

실행 조건

  • _workspace/99_coherence_report.json의 overall == "pass"
  • 아니면 거부: BUILD_REFUSED: coherence not passed

빌드 순서

1. 환경 검증

  • marp CLI 설치 확인
  • xmllint 또는 fallback 경로 확인
  • zip 설치 확인

2. Marp 전체 재렌더

모든 slide.source.md를 재렌더하여 slide.html을 갱신. 이유: 중간에 슬라이드만 수정되었을 수 있으므로 항상 최신 상태 보장 (idempotency).

find course/sections -name slide.source.md -print0 | while IFS= read -r -d '' f; do
  dir=$(dirname "$f")
  marp --html --allow-local-files "$f" -o "$dir/slide.html"
done

3. SSML 검증

존재하는 transcript.ssml 각각에 대해 validate-ssml.sh 실행. 실패는 WARNING으로 격하 (txt는 항상 유효).

4. Quiz schema 검증

각 quiz.json 비즈니스 룰 검증:

  • items 길이 5~9
  • mcq_single의 correct 길이 == 1
  • mcq_multi의 correct 길이 2~3
  • 모든 item.explanation 비어있지 않음
  • bloom_distribution 키 집합 유효

5. Manifest 합성

course/manifest.json:

{
  "course": {
    "topic": "...", "audience": "...",
    "depth": "...", "language": "ko", "tone": "...",
    "total_duration_min": 120,
    "build_ts": "2026-04-22T14:30:00Z",
    "harness_version": "1.1.0"
  },
  "learning_objectives": [ /* from _workspace/01_architect_learning_objectives.json */ ],
  "sections": [
    {
      "id": "S1", "slug": "01-intro", "title": "...",
      "lo_ids": ["LO-1.1","LO-1.2"],
      "quiz_path": "sections/01-intro/quiz.json",
      "classes": [
        {
          "id": "S1.C1", "slug": "01-what-is-rsc", "title": "...",
          "lo_ids": ["LO-1.1"],
          "assets": {
            "slide_source": "sections/01-intro/classes/01-what-is-rsc/slide.source.md",
            "slide_html":   "sections/01-intro/classes/01-what-is-rsc/slide.html",
            "note_md":      "sections/01-intro/classes/01-what-is-rsc/note.md",
            "transcript_txt": "sections/01-intro/classes/01-what-is-rsc/transcript.txt",
            "transcript_ssml": "sections/01-intro/classes/01-what-is-rsc/transcript.ssml"
          }
        }
      ]
    }
  ],
  "stats": {
    "sections": 4, "classes": 10, "total_slides": 45,
    "lo_count": 14,
    "bloom_distribution": {"Remember":2,"Understand":4,"Apply":5,"Analyze":3},
    "estimated_audio_duration_sec": 7200
  },
  "asset_errors": []
}

Read the full file on GitHub · 154 lines

Files

What ships with it

1 file 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.

Changes

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.

  1. 2mo ago First seen · 154 lines · 50 tokens per session scan C dc462cc5c249

Subscribe to this mod's changes

asset-build is a skill published in the GitHub repository tobyilee/course-builder (27 stars, last pushed 6mo ago), licensed MIT. It adds 50 tokens to every session and 1,377 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

asset-build compared with skills from other repositories

asset-build next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
asset-buildtobyilee/course-builderSkill276mo agoMITC50Claude Code
hr-onboardingnexu-io/open-designSkill106ktodayApache-2.0A62Claude Code, Codex
book-mirrorgarrytan/gbrainSkill32ktodayMITA138Claude Code
exam-forecastanthropics/claude-for-legalSkill9.9ktodayApache-2.0A73Claude Code
lean-formalizewanshuiyin/Auto-claude-code-research-in-sleepSkill19kyesterdayMITA81Claude Code
deck-course-modulenexu-io/html-anythingSkill9.4kyesterdayApache-2.0A25Claude Code, Codex
eli5companion-inc/feynmanSkill10k7d agoMITA63Claude Code, Codex