book-writer: Skill for Claude Code

.claude/skills/chapter-writing/SKILL.md

chapter-writing is a skill for Claude Code from tobyilee/book-writer. It costs 134 tokens per session (1,494 once invoked), scanned A, original, MIT.

A chapter-writing guide for drafting or revising one book chapter in a selected Korean writing style. It uses genre-specific rules for tone, structure, and wording.

In plain words
What is it for?
Use it to turn an outline into a chapter, rewrite existing prose, or polish a draft to match the active genre profile.
Why use it?
It removes the guesswork involved in keeping a chapter consistent with the book’s genre and authorial voice. It also helps avoid mixing writing styles that do not belong together.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is tobyilee/book-writer's own configuration. It tells Claude Code how to work on book-writer 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 book-writer configures →

Reuse

Borrowing it

Nothing to install: this file belongs to tobyilee/book-writer. 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/book-writer/main/.claude/skills/chapter-writing/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/tobyilee/book-writer

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 chapter-writing

README.md
[![agentmods](https://agentmods.dev/badge/skills/tobyilee/book-writer/chapter-writing/github.svg)](https://agentmods.dev/skills/tobyilee/book-writer/chapter-writing)
Your own site
<a href="https://agentmods.dev/skills/tobyilee/book-writer/chapter-writing"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/chapter-writing/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 chapter-writing

Your own site · 80×15
<a href="https://agentmods.dev/skills/tobyilee/book-writer/chapter-writing"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/chapter-writing.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 134 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,494 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00134 $0.01494
Opus 5.5 $0.00054 $0.00598
Sonnet 5.5 $0.00027 $0.00299
Haiku 4.5 $0.00013 $0.00149

Measured 1mo ago against content hash 9312a4bbc5b8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

chapter-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 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.

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/chapter-writing/SKILL.md · 72 lines

How it starts

The opening of the file, as written. The whole thing — 72 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Chapter Writing (장르 프로필 기반)

하나의 챕터를 활성 장르 프로필의 voice로 저술한다.

활성 프로필을 먼저 확인하자. 우선순위: 오케스트레이터가 전달한 genre → {slug}/book_manifest.json의 genre → 기본값 tech-book. 해당 profiles/{genre}/voice.md(문체)와 scaffolds.md(구조)를 읽고 그 규약을 따른다. 프로필 목록·선택 규칙은 profiles/_registry.md.

아래 본문(핵심 원칙·표현 사전·피해야 할 패턴)은 tech-book 프로필(기본값 = Toby 문체) 기준이다. narrative·practical·essay 장르는 본문 대신 해당 프로필의 voice.md를 따른다 — 공감어("찜찜하다")·실습 청유("해보자")는 tech-book 전용이다.

tech-book 핵심 원칙

원칙 내용
평어체 기반 기본 서술은 -다, -한다 형태. 딱딱하지 않게, 친절하게 개념을 풀어낸다.
청유형 -자, -보자로 "함께 개선하자"는 동반자 어조를 만든다. 자주 쓰되 한 문단에 몰아 쓰지 않는다.
문답법 새 개념을 도입할 때 "왜 그럴까?", "어떻게 해야 할까?" 같은 수사적 질문을 먼저 던지고 스스로 답한다.
상황 가정 "~라고 상상해보자", "~한다고 해보자"로 실무 상황을 먼저 세운 뒤 개념을 붙인다.
감정적 공감 나쁜 코드·잘못된 관행을 설명할 때 "난감하다", "찜찜하다", "번거롭다", "끔찍한 일이다" 같은 감각적 단어를 활용한다.
논리 전환 "그렇다면 ~", "물론 ~다. 하지만 ~"로 반론을 선제 차단하며 논리를 잇는다.

자주 쓰는 표현 사전

주의 환기·사고 유도:

  • "살펴보자", "알아보자", "생각해보자", "함께 고민해보자"

권장·대안 제시(강압 금지):

  • "~하는 편이 낫다", "~하는 것이 바람직하다", "~하는 것이 좋다"

핵심 당부:

  • "기억해두자", "잊지 말자", "주의해야 한다"

문제 상황 묘사:

  • "난감하다" / "초난감한 상황이다"
  • "찜찜하다"
  • "번거롭다"
  • "끔찍한 일이다"

논리 전환:

  • "그렇다면 어떻게 해야 할까?"
  • "물론 ~다. 하지만 ~"

상세 가이드와 예시는 활성 profiles/{genre}/voice.md 참조 (tech-book = profiles/tech-book/voice.md).

챕터 구성

  • 입력 — 02_plan.md에서 이 장의 핵심 질문·주요 내용·배정된 오프닝/클로징/스캐폴드, 계획의 "용어 표기", 01_reference.md에서 이 장과 관련된 부분.
  • 스캐폴드 — profiles/{genre}/scaffolds.md에서 배정된 유형을 따르되, 억지로 맞추기보다 흐름을 우선한다.
  • 오프닝 — 배정된 기법으로 연다 (tech-book 메뉴: 상황 가정·수사적 질문·충격 수치·일화·실패 장면·앞 장 콜백·정의 뒤집기). "이번 장에서는 ~를 다룬다" 같은 메타 선언으로 시작하지 않는다.
  • 본문 — 개념을 하나씩 도입한다. 대개 상황이나 질문 → 친절한 설명 → 필요하면 코드·예시 → "그렇다면 ~" 식 전환의 흐름이 Toby 문체에 맞는다.
  • 공감 표현 — "난감하다", "찜찜하다" 같은 표현은 장당 1~2회면 충분하다. 매 절 반복하면 tic이 되고, 비워 두는 장이 있어도 좋다.
  • 클로징 — 배정된 기법으로 닫는다. 중간 장이 매번 "다음 장에서는 ~"로 끝나면 책 전체가 단조로워진다. 마지막 장은 여정을 회수하는 닫는 매듭이다. ## 마무리 헤딩은 필수가 아니다.
  • 기준 — 저장하는 원고는 활성 style-checklist.md를 충족해야 한다. 기본 흐름에는 별도 스타일 검수가 없다.

피해야 할 패턴

Read the full file on GitHub · 72 lines

Files

What ships with it

2 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.

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. 1mo ago Changed · -5 lines 9312a4bbc5b8
  2. 2mo ago First seen · 77 lines · 134 tokens per session scan A 635509c59b9a

Subscribe to this mod's changes

chapter-writing is a skill published in the GitHub repository tobyilee/book-writer (85 stars, last pushed 3d ago), licensed MIT. It adds 134 tokens to every session and 1,494 once invoked, about $0.0005 per session on Opus 5.5. 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

chapter-writing compared with skills from other repositories

chapter-writing next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
chapter-writingtobyilee/book-writerSkill853d agoMITA134Claude Code
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code