book-writer: Skill for Claude Code

.claude/skills/style-review/SKILL.md

style-review is a skill for Claude Code from tobyilee/book-writer. It costs 56 tokens per session (1,760 once invoked), scanned A, original, MIT.

A writing-review skill that checks chapter drafts against a genre's style guide and suggests specific rewrites.

In plain words
What is it for?
Use it to review a chapter for tone, structure, wording, and other style issues, with concrete before-and-after suggestions.
Why use it?
It makes style problems easier to spot by comparing the draft with an active checklist and voice guide.

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/style-review/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 style-review

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/tobyilee/book-writer/style-review"><img src="https://agentmods.dev/badge/skills/tobyilee/book-writer/style-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,760 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 $0.00056 $0.01760
Opus 5 $0.00028 $0.00880
Sonnet 5 $0.00011 $0.00352
Haiku 4.5 $0.00006 $0.00176

Measured 12d ago against content hash c267ac7b5264, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

style-review 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 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.

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/style-review/SKILL.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Style Review

챕터 초안을 활성 장르 프로필 기준으로 검수한다. 발견한 편차에 대해 구체적 대체 문장을 제안한다.

활성 프로필을 먼저 확인하자. 우선순위: 오케스트레이터가 전달한 genre{slug}/book_manifest.jsongenre → 기본값 tech-book. 검수 기준은 profiles/{genre}/style-checklist.mdvoice.md. 장르마다 항목·우선순위가 다르다.

절차

  1. 원문 읽기{NN}_draft.md를 처음부터 끝까지
  2. 기준 재확인 — 활성 profiles/{genre}/style-checklist.mdvoice.md
  3. 체크리스트 순회 — 프로필 체크리스트 항목 점검
  4. 편차 기록 — 원문 인용 + 대안 제시 + 이유
  5. 우선순위 — Critical / Should / Nice (프로필 정의를 따름)
  6. 메시지 전송SendMessagechapter-writer에게

검수 체크리스트

활성 프로필의 style-checklist.md를 항목표로 쓴다. 아래는 tech-book(기본값) 예시다 — narrative·practical·essay는 각 프로필 체크리스트를 따른다.

빈도 항목은 **최소치(floor)가 아니라 자연스러운 범위(band)**다. 부족함뿐 아니라 과포화도 잡아낸다.

번호 항목 점검 방식
1 오프닝 메타 선언("이 장에서는 ~")으로 시작 여부. profiles/{genre}/scaffolds.md오프닝 메뉴(상황 가정·수사적 질문·충격 수치·일화·실패 장면·앞 장 콜백·정의 뒤집기)를 권한다. 인접 챕터와 같은 기법이면 변주 제안, '상황 가정' 오프닝은 책 전체 1/3 이하
2 청유형 -자, -보자, -해보자자연스러운 수준인가. 과포화(한 문단 연속·장 전체 도배) 시 일부를 평어체로 환원 제안
3 수사적 질문 논리 전환 지점에만 배치됐는가. 연속 사용·장식적 남발 금지 → 통합·삭제 제안
4 공감 표현 "난감하다", "찜찜하다" 등 — 챕터당 1~2회 수준. 일부 챕터는 의도적으로 비워도 좋다. 매 절 반복은 과포화
5 tic 과포화 (ceiling) 같은 표현(그렇다면 / 기억해두자 / ~해보자 등)이 한 챕터에 과다하거나 모든 챕터에 기계적으로 반복되는가 → 변주·삭제 제안
6 bold 강조 밀도 **굵게** 강조가 과다한가 — 대략 80단어당 1개 초과면 핵심만 남기고 해제 제안
7 권장 어조 "반드시 ~해야 한다" 강압 표현 존재 여부
8 외래어 남용 불필요한 영어·일본어 외래어
9 수동태 영어식 수동태("처리되어진다")
10 논리 전환구 "그렇다면 ~", "물론 ~다. 하지만 ~" 구사 — 과다 반복 아닌지
11 나열식 문단이 리스트·번호로만 채워진 구간
12 호흡 3줄 이상 이어진 긴 문장 여러 개
13 클로징 중간 장이 매번 "다음 장에서는 ~" 공식인가 → 변주된 이음말 제안. 마지막·종합 장은 닫는 매듭인가
14 사실·신선도 (최신 기술) 시점 명기·출처 있는 수치·추측 API 금지 — 위반은 Critical

리뷰 메시지 포맷

## 스타일 리뷰: {NN}장 라운드 {N}

### Critical
1. [원문 {줄번호}]
   > "..."
   [제안]
   > "..."
   **이유:** {짧게}

### Should
1. ...

### Nice
1. ...

### 전체 톤 평가
{한 줄 — "전반적으로 토비 목소리가 살아있지만 2.3절 중반이 딱딱해짐" 등}

Read the full file on GitHub · 102 lines

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. 12d ago First seen · 102 lines · 56 tokens per session scan A c267ac7b5264

Subscribe to this mod's changes

style-review is a skill published in the GitHub repository tobyilee/book-writer (81 stars, last pushed 26d ago), licensed MIT. It adds 56 tokens to every session and 1,760 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.