Manuscript Acceptance logo

Manuscript Acceptance

Community
tobyilee
manuscript-acceptance

Whole-book acceptance gate run by a fresh-context reviewer before EPUB build (Phase 4.5). Cross-reads the integrated manuscript against the plan, research ledger, and logs, scans for forbidden leftover markers, checks terminology/voice/variation, cross-reference and promise integrity, and emits {slug}/05_acceptance.md with per-criterion PASS/BLOCK + owner-tagged fixes. Genre-agnostic; complements the per-chapter fact/continuity passes. Triggers on "수락 검수", "통권 검수", "manuscript acceptance", "최종 통과 게이트".

Overview

Publishertobyilee
Repositorybook-writer
Skill namemanuscript-acceptance
Stars
85
Forks
20
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by tobyilee on GitHub. Read the source before you install it.

Installation

Install the Manuscript Acceptance AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/tobyilee/book-writer/tree/main/.claude/skills/manuscript-acceptance
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/tobyilee/book-writer.git /tmp/book-writer
mkdir -p .claude/skills
cp -r /tmp/book-writer/.claude/skills/manuscript-acceptance .claude/skills/manuscript-acceptance
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Manuscript Acceptance in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Manuscript Acceptance on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Manuscript Acceptance is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Manuscript Acceptance

통합 원고(04_manuscript.md)가 Phase 5로 넘어가기 전 책 전체를 판정하는 게이트다. 원고를 만든 editor와 다른 새 컨텍스트가 수행한다. 챕터 단위 사실·연속성 패스를 다시 하지 않고, 잔여 미결과 통권 단위 문제만 본다. 기본 흐름에는 별도 스타일 검수가 없으므로 voice 이탈도 여기서 잡는다.

없는 로그가 대상인 기준(예: essay의 사실 로그)은 N/A PASS로 두고 이유를 한 줄 적는다.

수락 기준

ID기준확인 방법BLOCK 시 담당
(a)챕터 완비·분량 균형플랜의 챕터 목록 ↔ 원고 # N장 헤딩 1:1 대조. length_report.py로 분량을 직접 재고 70% 미만·150% 초과 장을 본다해당 장 chapter-writer
(b)미해소 마커 0건아래 grep사용자 (빌드 중단)
(c)사실 미결 해소factcheck_log.md의 미해소. (tech-book) 참고문헌 항목의 식별자·확인 등급 라벨을 research/*.md와 표본 대조하고, 같은 수치·버전이 장마다 다르게 쓰였는지 본다fact-checker / 해결 불가면 사용자 (빌드 중단)
(d)용어·voice·변주핵심 용어 표기 흔들림. 여러 장을 표본으로 활성 style-checklist.md에 비춰 voice 이탈(번역투, 강압 어조, 과포화 말버릇, 메타 선언 오프닝)을 본다. editor_notes.md의 변주 표를 참고해 오프닝·클로징이 같은 틀로 반복되는지 본다해당 장 chapter-writer 또는 editor
(e)상호 참조 무결성"앞서 N장에서 ~" 류 콜백이 실제로 그 장의 내용을 가리키는지editor
(f)약속 이행매니페스트 description과 계획의 독자 여정이 약속한 범위를 원고가 다루는지editor, 본질적 미달이면 사용자
(g)부속 자료 완비서문·목차·콜로폰(## 판권)·에필로그·(tech-book/essay) 참고문헌editor
(h)연속성 (narrative)continuity_log.md의 미해소, story_bible.md 복선 원장의 미회수 항목chapter-writer / 의도 확인은 사용자

절차

  1. 금지 마커를 grep한다. 한 건이라도 있으면 (b) BLOCK이며 줄 번호와 원문을 기록한다.
    bash
    grep -nE "\(사실 확인 필요\)|\[리서치 공백\]|\[미완성\]" {slug}/04_manuscript.md
  2. 챕터 완비와 분량을 확인한다.
    bash
    grep -nE "^# [0-9]+장" {slug}/04_manuscript.md
    python3 .claude/skills/book-editing/scripts/length_report.py {slug}
  3. 콜백을 모아 가리키는 장이 맞는지 본다.
    bash
    grep -nE "앞서 [0-9]+장|[0-9]+장에서 (다룬|살펴본|본)" {slug}/04_manuscript.md
  4. 로그의 잔여 미결을 본다.
    bash
    grep -nE "미해소" {slug}/factcheck_log.md {slug}/continuity_log.md 2>/dev/null
  5. (c)의 참고문헌 표본 대조, (d)의 voice·변주, (f)(g)를 판정한다. 말버릇 반복 횟수는 grep으로 센다.
  6. 05_acceptance.md를 쓴다.

평결

  • ACCEPT — 모든 기준 PASS.
  • BLOCK — 하나 이상 BLOCK. 오케스트레이터가 조치를 담당자에게 한 번 보내고, 영향받은 기준만 재판정한다. 재판정 후에도 BLOCK이면 사용자가 판단한다.
  • (b)(c)는 사용자가 명시적으로 승인하지 않는 한 PASS가 될 수 없다. 승인했으면 그 사실과 범위를 기록한다.

출력 형식

markdown
# 수락 검수: {책 제목}

<!-- 검수: {날짜} · 라운드 {N} · manuscript-reviewer (fresh context) -->

## 기준 판정

| ID | 기준 | 판정 | 근거 |
|----|------|------|------|
| (a) | 챕터 완비·분량 균형 | PASS | 플랜 8장 = 원고 8장, 플래그 0 |
| (b) | 미해소 마커 0건 | PASS | grep 0건 |
| (c) | 사실 미결 해소 | PASS | 미해소 0건, 참고문헌 표본 6건 원장 일치 |
| (d) | 용어·voice·변주 | BLOCK | 4·5·6장 모두 '상황 가정' 오프닝, 6장 "기억해두자" 11회 |
| (e) | 상호 참조 무결성 | PASS | 콜백 6건 정합 |
| (f) | 약속 이행 | PASS | ... |
| (g) | 부속 자료 완비 | PASS | ... |
| (h) | 연속성 | N/A | tech-book |

## 평결

BLOCK

## 조치

| 기준 | 심각도 | 담당 | 조치 |
|------|--------|------|------|
| (d) | 중간 | chapter-writer 5장 | 오프닝을 '실패 장면'으로 교체 (계획 배정과 일치시킴) |
| (d) | 낮음 | chapter-writer 6장 | "기억해두자" 11회 → 4회 이하로, 나머지는 평어체 |

재검수면 새 라운드를 append하고, 이전 조치의 해소 여부를 먼저 적은 뒤 영향받은 기준만 다시 판정한다.

Frequently asked questions

What does the Manuscript Acceptance AI skill do?

Whole-book acceptance gate run by a fresh-context reviewer before EPUB build (Phase 4.5). Cross-reads the integrated manuscript against the plan, research ledger, and logs, scans for forbidden leftover markers, checks terminology/voice/variation, cross-reference and promise integrity, and emits {slug}/05_acceptance.md with per-criterion PASS/BLOCK + owner-tagged fixes. Genre-agnostic; complements the per-chapter fact/continuity passes. Triggers on "수락 검수", "통권 검수", "manuscript acceptance", "최종 통과 게이트".

Why use Manuscript Acceptance on TypingMind?

Because you install it once and use it with any model. Manuscript Acceptance is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Manuscript Acceptance in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tobyilee/book-writer/tree/main/.claude/skills/manuscript-acceptance. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Manuscript Acceptance?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Manuscript Acceptance?

As many as you like. As long as a model supports skills, you can use Manuscript Acceptance with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Manuscript Acceptance AI skill free?

Yes. It is published on GitHub by tobyilee under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇