note-writing

A lecture-note writer that turns class material into a structured Markdown document for learners to read and study. Markdown is plain text with simple formatting marks for headings, lists, and links.

In plain words
What is it for?
Writing study notes with introductions, concept explanations, code or scenario examples, pitfalls, recaps, and slide references.
Why use it?
It separates detailed reading material from brief slides and spoken narration. It also keeps examples, common mistakes, summaries, and links to slides in one place.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/tobyilee/course-builder/note-writing
Any agent
npx skills add tobyilee/course-builder --skill note-writing
Clone the repo
git clone --depth 1 https://github.com/tobyilee/course-builder

Made for: Claude Code, Codex.

Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 991 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00056 $0.00991
Opus 5 $0.00028 $0.00495
Sonnet 5 $0.00011 $0.00198
Haiku 4.5 $0.00006 $0.00099

Measured 2d ago against content hash 67115a412fb9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

note-writing 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 2d 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.

.claude/skills/note-writing/SKILL.md · 108 lines

What it actually says

Note Writing — Learner-Facing Deep Text

note는 학습자가 정독하는 본문이다. slide는 요약, transcript는 듣기용, note는 눈으로 깊이 읽는 매체로 차별화한다.

구조 템플릿

# {class title}
> **LOs:** LO-X.Y, LO-X.Z
> **예상 읽기 시간:** N분

## Intro
학습자가 왜 이 내용을 알아야 하는지, 실세계 맥락.

## Concept
정의 → 속성/하위요소 → 왜 중요한가의 3단 구조.

## Example
구체적 코드 or 사례 (최소 1개).

## Pitfalls
흔한 오해 1~2개. 단순히 정답 반복 금지.

## Recap
3가지 핵심을 bullet로 재정리.

길이 가이드 (한국어 기준)

섹션 비중 한국어 글자 수 (총 1200자 기준)
Intro 10% 120자
Concept 40% 480자
Example 30% 360자
Pitfalls 15% 180자
Recap 5% 60자

영어면 400900 단어, 한국어면 8001600자.

Cross-reference 규칙

  • Slide 참조: [slide 3] — 실제 존재하는 슬라이드 번호만
  • 다른 class 참조: [S2.C1] — section.class 형태
  • LO 참조: 맨 위 blockquote에 명시

예:

## Concept
서버 컴포넌트는 [slide 2]에서 본 것처럼 서버에서만 실행됩니다.
이 개념은 [S1.C2]에서 다룬 SSR과 다릅니다.

섹션별 작성 가이드

Intro (학습자 훅)

  • 1~2 문장
  • "왜 지금 이걸 배워야 하나" 제시
  • 한 가지 구체 질문으로 끝나면 좋음

Concept (핵심)

  • 정의 문장 1개 (두괄식)
  • 3개 이하의 서브섹션 (###)
  • 각 서브섹션마다 1~3 단락

Example

  • 실행 가능한 코드 or 구체 시나리오
  • 코드는 ~~~lang 블록
  • 주석은 한국어 tone이면 한국어, formal tone이면 영어

Pitfalls

  • 흔한 오해: 학습자가 실제로 할 법한 실수
  • 해설: "정답은 X"가 아니라 "Y로 오해하기 쉬운 이유와 교정"

Recap

  • 정확히 3개 bullet
  • 각 bullet은 하나의 LO에 대응

톤 가이드

tone 문체 어휘
friendly 2인칭 "여러분", 단문, 가벼운 비유 OK 일상어 섞음
formal 3인칭/수동태 혼용, 장문 가능 용어 엄격
socratic 질문형 문장으로 개념 유도 결론 지연

금기

  • slide.source.md 복사 (요약이 아니라 확장)
  • transcript 복사 (듣기용과 읽기용 리듬이 다름)
  • "자, 그럼", "이제" 같은 구어 전환 (speaker가 아니라 필자)

재실행 규칙

  • 섹션 단위 diff 갱신 기본
  • 전체 재작성은 사용자 명시 요청 시

체크리스트

  • LO를 맨 위 blockquote에 명시했는가
  • 5부 구조 유지
  • 한국어 8001600자 (영어 400900 단어)
  • slide/class cross-ref가 실제 존재 id인가
  • Pitfalls이 정답 반복이 아니라 오해 교정인가
  • Recap이 정확히 3개 bullet인가
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. 2d ago First seen · 108 lines · 56 tokens per session scan A 67115a412fb9

Subscribe to this mod's changes

note-writing is a skill published in the GitHub repository tobyilee/course-builder (22 stars, last pushed 4mo ago), licensed MIT. It adds 56 tokens to every session and 991 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.

Related

Other skills, from other repositories

trulens-notebook-execution

Execute and display Jupyter notebooks for TruLens demos and quickstarts.

truera/trulens · 21 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

master-yinguang

Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…

xr843/Master-skill · 274 tokens

explore-unknowns

Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…

dzhng/skills · 162 tokens

obsidian-to-clew-import

Convert an Obsidian vault or wiki-linked markdown graph into a validated structured-learning graph package for Clew. Use when the user wants to inspect a vault, preview whether it imports cleanly, preserve explicit relation markers, choose only the few import settings that matter, and produce a fail-closed package…

miuuyy/Clew · 72 tokens