chapter-drafter

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Chapter Drafter: Orchestrator Skill

章节起草器：Orchestrator Skill

You autonomously draft and polish chapter scenes through iterative editorial passes. Given an outline, you produce polished first-draft prose by drafting each scene, evaluating it against editorial criteria, and revising until quality thresholds are met.

你将通过迭代编辑环节自主起草并打磨章节场景。给定大纲后，你会逐段起草场景内容，对照编辑标准进行评估，直至达到质量阈值，最终生成高质量的初稿文本。

Core Principle

核心原则

Orchestration is iteration with hierarchy. Fix structure before character, character before originality, originality before dialogue, dialogue before prose. Don't polish what might be cut; don't revise dialogue in a scene that needs structural rework.

编排是带有层级的迭代。 先修复结构，再打磨人物；先完善人物，再追求原创性；先确保原创性，再优化对话；先打磨对话，再润色文笔。不要打磨可能会被删除的内容；不要在需要重构结构的场景中修改对话。

Prerequisites

前置条件

Before invoking this skill, ensure:

Complete outline exists - Scene beats with goals, conflicts, and intended outcomes
Characters defined - Lie/want/need, voice patterns, arc positions
World established - Setting details sufficient for scene work
Story-sense diagnosis complete - No structural story problems remaining

Do NOT use this skill if:

Outline is still in flux
Character arcs undefined
Story-sense would diagnose structural problems

调用此技能前，请确保：

已有完整大纲 - 包含场景情节的目标、冲突和预期结果
人物设定完成 - 包含人物的“谎言/欲望/需求”、说话风格、弧光阶段
世界观已建立 - 具备足够支撑场景创作的设定细节
故事结构诊断完成 - 不存在结构性故事问题

请勿使用此技能的情况：

大纲仍在变动中
人物弧光未定义
故事结构诊断发现结构性问题

The Orchestration Loop

编排循环

FOR each scene in chapter outline:

    1. BUILD CONTEXT
       - Load character voices from previous scenes
       - Load open plot threads
       - Load cliche avoidances
       - Extract scene purpose from outline

    2. DRAFT SCENE
       - Generate initial prose from outline beat
       - Apply character voices
       - Maintain plot thread continuity

    3. EVALUATION LOOP (max 5 cycles)
       │
       ├─► Pass 1: scene-sequencing (35%)
       │   └─► If FAIL: REWRITE scene
       ├─► Pass 2: character-arc (25%)
       ├─► Pass 3: cliche-transcendence (15%)
       ├─► Pass 4: dialogue (15%)
       └─► Pass 5: prose-style (10%)
       │
       Calculate composite score
       │
       ├─► >= 80: ACCEPT
       ├─► 60-79: TARGETED FIX → re-evaluate
       ├─► 40-59: REWRITE → return to draft
       └─► <40: REJECT → full re-draft from outline

    4. POST-ACCEPT
       - Extract character voice patterns → update context
       - Track plot thread changes → update registry
       - Record cliche transcendences → update avoidances
       - Write scene to output
       - Update progress tracker

END FOR

FOR each scene in chapter outline:

    1. BUILD CONTEXT
       - Load character voices from previous scenes
       - Load open plot threads
       - Load cliche avoidances
       - Extract scene purpose from outline

    2. DRAFT SCENE
       - Generate initial prose from outline beat
       - Apply character voices
       - Maintain plot thread continuity

    3. EVALUATION LOOP (max 5 cycles)
       │
       ├─► Pass 1: scene-sequencing (35%)
       │   └─► If FAIL: REWRITE scene
       ├─► Pass 2: character-arc (25%)
       ├─► Pass 3: cliche-transcendence (15%)
       ├─► Pass 4: dialogue (15%)
       └─► Pass 5: prose-style (10%)
       │
       Calculate composite score
       │
       ├─► >= 80: ACCEPT
       ├─► 60-79: TARGETED FIX → re-evaluate
       ├─► 40-59: REWRITE → return to draft
       └─► <40: REJECT → full re-draft from outline

    4. POST-ACCEPT
       - Extract character voice patterns → update context
       - Track plot thread changes → update registry
       - Record cliche transcendences → update avoidances
       - Write scene to output
       - Update progress tracker

END FOR

Pass Criteria

评审标准

Pass 1: Scene-Sequencing (35% weight)

第1轮评审：场景排序（权重35%）

Evaluates Goal-Conflict-Disaster structure and pacing.

Criterion	PASS	WARN	FAIL
Goal clarity	POV goal clear in opening beats	Goal exists but buried	No discernible goal
Conflict escalation	Opposition intensifies	Conflict static but present	No real opposition
Disaster quality	"Yes, but..." or "No, and..."	Simple "No"	Clean "Yes" or no resolution
Sequel presence	Reaction-dilemma-decision present	Abbreviated sequel	Missing after high-tension
Scene-sequel ratio	Matches intended pacing	Slight mismatch	Severely mismatched

Critical: If scene-sequencing FAILS, do NOT proceed to other passes. Structural problems invalidate downstream evaluation.

评估“目标-冲突-转折”结构和节奏。

评估标准	通过	警告	失败
目标清晰度	POV目标在开篇情节中清晰明确	目标存在但被掩盖	无明确可辨的目标
冲突升级	对立矛盾逐步加剧	冲突存在但无变化	无实质对立矛盾
转折质量	符合“是的，但是……”或“不，而且……”逻辑	仅简单的“不”	明确的“是”或无结局
后续情节存在性	包含反应-困境-决策环节	后续情节被简化	高张力场景后缺失后续情节
场景-后续情节比例	符合预期节奏	轻微不匹配	严重不匹配

注意： 如果场景排序评审失败，请勿进入后续评审。结构性问题会使下游评估失去意义。

Pass 2: Character-Arc (25% weight)

第2轮评审：人物弧光（权重25%）

Evaluates transformation consistency and arc progress.

Criterion	PASS	WARN	FAIL
Lie visibility	False belief evident in choices	Lie present but unstated	No lie operative
Want/Need gap	Clear tension between stated/actual	Gap exists but unclear	Want = Need (no tension)
Arc progress	Scene advances or challenges arc	Arc static but consistent	Character contradicts arc
Transformation markers	Choices reflect arc position	Position unclear	Acts against personality

评估人物转变的一致性和弧光推进。

评估标准	通过	警告	失败
错误信念可见性	人物选择中明显体现错误信念	错误信念存在但未明确表达	无错误信念生效
欲望/需求差距	明确体现表面欲望与真实需求的张力	差距存在但不清晰	欲望=需求（无张力）
弧光推进	场景推进或挑战人物弧光	弧光无变化但保持一致	人物行为与弧光矛盾
转变标志	人物选择符合当前弧光阶段	弧光阶段不清晰	行为与人物性格相悖

Pass 3: Cliche-Transcendence (15% weight)

第3轮评审：突破俗套（权重15%）

Evaluates originality via orthogonality test.

Criterion	PASS	WARN	FAIL
Form axis	Non-default form	Slight variation	Exactly genre default
Knowledge axis	Own concerns, accidental intersection	Some plot awareness	Fully story-serving
Goal axis	Own agenda that collides	Goal connected to plot	Purely protagonist-serving
Role axis	Own story that intersects	Somewhat independent	Exists only for hero
Orthogonality test	2+ axes orthogonal	1 axis orthogonal	All axes match default

通过正交性测试评估原创性。

评估标准	通过	警告	失败
形式维度	非默认形式	轻微变体	完全符合流派默认形式
认知维度	人物有自身关注点，与情节意外交织	人物有一定情节认知	完全服务于故事主线
目标维度	人物有自身目标，与主线冲突	目标与情节相关	纯粹服务于主角
角色维度	人物有自身故事线，与主线交织	有一定独立性	仅为衬托主角存在
正交性测试	2个及以上维度正交	1个维度正交	所有维度符合默认

Pass 4: Dialogue (15% weight)

第4轮评审：对话（权重15%）

Evaluates voice distinctiveness, subtext, and function.

Criterion	PASS	WARN	FAIL
Voice distinctiveness	Characters distinguishable without tags	Some overlap	Identical voices (D1)
Subtext presence	Gap between said and meant	Occasional direct statements	Everything on-the-nose (D4)
Double-duty test	3+ functions per exchange	2 functions	Single function only (D5)
Naturalness	Contractions, interruptions, rhythm	Slightly formal	Wooden/stilted (D2)
Exposition handling	Information through conflict	Minor "as you know"	Exposition dump (D3)

评估声音独特性、潜台词和功能。

评估标准	通过	警告	失败
声音独特性	无需标签即可区分不同人物	存在部分重叠	人物声音完全一致（D1）
潜台词存在性	话语与真实意图存在差距	偶尔直接陈述	所有内容直白无潜台词（D4）
双重功能测试	每次对话包含3种及以上功能	包含2种功能	仅单一功能（D5）
自然度	使用缩写、打断、符合节奏	略显正式	生硬刻板（D2）
背景信息处理	通过冲突传递信息	少量“你知道的”式表述	大段背景信息堆砌（D3）

Pass 5: Prose-Style (10% weight)

第5轮评审：文笔风格（权重10%）

Evaluates sentence-level craft.

Criterion	PASS	WARN	FAIL
Sentence variety	Length and structure vary	Some variation	Monotonous (P4)
Clarity	Concrete, clear antecedents	Occasional abstraction	Unclear writing (P2)
Voice consistency	Diction level consistent	Minor shifts	Random shifts (P6)
Economy	Words earn place	Minor redundancy	Overwrought (P3)
Active voice	Passive intentional	Some default passive	Passive overuse (P5)

评估句子层面的写作技巧。

评估标准	通过	警告	失败
句子多样性	句子长度和结构多变	有一定变化	单调重复（P4）
清晰度	具体明确，指代清晰	偶尔抽象	表述模糊（P2）
风格一致性	用词水平保持一致	轻微变化	风格随机切换（P6）
简洁性	每一个词都有存在的价值	少量冗余	过于繁复（P3）
主动语态	被动语态使用有目的性	少量默认被动语态	过度使用被动语态（P5）

Composite Scoring

综合评分

Each pass produces a score from 0-100:

All PASS = 100
Each WARN = -15
Each FAIL = -40

Composite = SUM(pass_score × pass_weight)

Composite	Outcome	Action
>= 80	ACCEPT	Scene complete, proceed to next
60-79	REVISE	Fix lowest-scoring pass, re-evaluate
40-59	REWRITE	Regenerate with failure constraints
< 40	REJECT	Full re-draft from outline

每轮评审得分范围为0-100：

所有标准通过 = 100分
每出现1次警告 = 扣15分
每出现1次失败 = 扣40分

综合得分 = 各轮得分 × 对应权重之和

综合得分	结果	操作
>= 80	接受	场景完成，进入下一个
60-79	修订	修复得分最低的评审项，重新评估
40-59	重写	结合失败约束重新生成
< 40	驳回	基于大纲重新起草

Iteration Limits

迭代限制

Level	Limit	On Exceed
Per-pass	3	Escalate to rewrite
Per-scene	12	Accept at threshold 50, flag for review
Per-chapter	50	Stop, report remaining issues

Diminishing returns detection: If improvement < 10% between iterations, accept current state or escalate.

层级	限制次数	超出后操作
单轮评审	3次	升级为重写
单场景	12次	以50分阈值接受，标记需复审
单章节	50次	停止操作，报告剩余问题

收益递减检测： 如果两次迭代间得分提升<10%，则接受当前状态或升级处理。

Context Accumulation

上下文积累

Maintain across scenes:

在各场景间持续维护以下内容：

Character Voices

人物声音

After each scene, extract and store:

Vocabulary patterns per character
Sentence rhythm patterns
Directness level
Verbal tics and avoidances

Use as constraint for subsequent scenes: "Character X speaks like [markers]"

每个场景完成后，提取并存储：

各人物的词汇模式
句子节奏模式
直接表达程度
口头习惯和避讳用语

将其作为后续场景的约束：“人物X的说话风格为[标记特征]”

Plot Threads

情节线索

Track:

Open threads - Introduced, not resolved
Closed threads - Resolved this chapter
Foreshadowing - Planted for future payoff

Each scene checks:

No contradiction with established facts
Open threads acknowledged or advanced
At least one element progresses

跟踪：

未闭合线索 - 已引入但未解决
已闭合线索 - 本章内已解决
伏笔 - 为后续剧情铺垫的内容

每个场景需检查：

与已设定事实无矛盾
未闭合线索被提及或推进
至少有一个元素得到推进

Cliche Avoidances

俗套规避

After cliche-transcendence pass, record:

Which defaults were avoided
How they were transcended
New elements that feel fresh

Use as constraint: "Already transcended [X], maintain freshness"

完成突破俗套评审后，记录：

已规避的俗套类型
突破俗套的方式
新增的新颖元素

将其作为约束：“已突破[X]俗套，保持创新性”

Progress Tracker

进度追踪器

Use the progress tracker template to persist state:

markdown

undefined

使用以下进度追踪模板保存状态：

markdown

undefined

Chapter Progress: [Title]

章节进度：[标题]

Started: [timestamp] Current: Scene [N], Pass [M], Iteration [K]

开始时间：[时间戳] 当前状态：第[N]场景，第[M]轮评审，第[K]次迭代

Scenes

场景列表

Scene	Status	Pass	Iterations	Score	Issues

场景	状态	评审轮次	迭代次数	得分	问题

Context

上下文

Character Voices: [accumulated]
Plot Threads: [open/closed]
Cliche Avoidances: [list]

人物声音：[积累的特征]
情节线索：[未闭合/已闭合]
俗套规避：[列表]

Change Log

变更日志

[timestamp] [change]

---

[时间戳] [变更内容]

---

Revision Strategy

修订策略

Targeted Fix (score 60-79)

针对性修复（得分60-79）

Identify lowest-scoring pass
Extract specific failure criteria
Generate minimal fix addressing that criterion
Re-evaluate that pass + downstream passes
If pass improves, recalculate composite

确定得分最低的评审项
提取具体失败的标准
生成仅针对该标准的最小修复方案
重新评估该评审项及下游评审项
如果评审项得分提升，重新计算综合得分

Rewrite (score 40-59)

重写（得分40-59）

Preserve scene goal from outline
Generate new draft with explicit constraints:
- "Must include clear goal in opening"
- "Conflict must escalate"
- etc. based on failures
Re-run full evaluation loop

保留大纲中的场景目标
结合明确约束生成新草稿：
- “必须在开篇明确目标”
- “冲突必须逐步升级”
- 其他基于失败项的约束
重新运行完整评估循环

Reject (score < 40)

驳回（得分<40）

Return to outline beat
Re-draft from scratch
Treat as new scene (reset iterations)

返回大纲情节
从头重新起草
视为新场景（重置迭代次数）

Conflict Resolution

冲突解决

When fixing one pass breaks another:

Detect: Re-run all passes after any fix
Compare: Did any pass regress?
Prioritize: Higher-weight pass wins ties
Seek synthesis: Can fix satisfy both?
Accept trade-off: If irreconcilable, accept per hierarchy

Escalation: If conflict persists after 2 attempts, flag scene for human review.

当修复一个评审项导致另一个评审项失败时：

检测：任何修复后重新运行所有评审项
对比：是否有评审项出现倒退？
优先级：权重更高的评审项优先
寻求折中：是否存在同时满足两者的修复方案？
接受权衡：若无法调和，按照层级原则接受结果

升级处理：如果2次尝试后冲突仍存在，标记场景需人工复审。

Anti-Patterns

反模式

The Infinite Polisher

无限打磨者

Pattern: Keeps iterating because one criterion is at WARN. Fix: WARN is acceptable. Accept at threshold after iteration limit.

模式： 因某一项标准为警告状态而持续迭代 修复： 警告状态是可接受的。达到迭代限制后按阈值接受。

The Pass Skipper

跳过评审者

Pattern: Jumps to prose-style when scene-sequencing failed. Fix: Hard gate on structural passes. FAIL blocks progression.

模式： 场景排序评审失败后直接进入文笔风格评审 修复： 对结构性评审设置硬性门槛。失败则无法进入后续评审。

The Context Amnesiac

上下文遗忘者

Pattern: Each scene drafted in isolation, losing voice and threads. Fix: Explicit context loading before each scene draft.

模式： 每个场景独立起草，丢失人物声音和情节线索 修复： 每个场景起草前明确加载上下文。

The Cascade Blind Spot

连锁反应盲区

Pattern: Fixes dialogue, doesn't check if prose-style regressed. Fix: Always re-evaluate current pass + downstream after any fix.

模式： 修复对话后未检查文笔风格是否倒退 修复： 任何修复后必须重新评估当前及下游评审项。

The Silent Failer

静默失败

Pattern: Hits iteration limit, proceeds without documentation. Fix: Log all limit exits with categorized remaining issues.

模式： 达到迭代限制后未记录问题即继续 修复： 记录所有超出限制的情况及分类后的剩余问题。

Output Persistence

输出持久化

Progress Tracker

进度追踪器

Location:

context/chapter-drafter/[chapter]-progress.md

Update: After each scene acceptance
Purpose: Resume point if interrupted

存储位置：

context/chapter-drafter/[chapter]-progress.md

更新时机： 每个场景被接受后
用途： 中断后可恢复状态

Scene Output

场景输出

Location:
```
drafts/[story]/[chapter]/scene-[N].md
```
Update: On scene acceptance
Purpose: Accumulated draft prose

存储位置：
```
drafts/[story]/[chapter]/scene-[N].md
```
更新时机： 场景被接受时
用途： 积累的草稿文本

Context State

上下文状态

Location:

context/chapter-drafter/[chapter]-context.md

Update: After each scene
Purpose: Character voices, threads, avoidances

存储位置：

context/chapter-drafter/[chapter]-context.md

更新时机： 每个场景完成后
用途： 人物声音、情节线索、俗套规避记录

Integration

集成

Inbound (feeds into chapter-drafter)

输入（为章节起草器提供数据）

Skill	What it provides
outline-collaborator	Scene beats with goal-conflict-disaster
character-arc	Lie/want/need for each character
worldbuilding	Setting details for scene work
story-sense	Confirmation structure is solid

技能	提供内容
outline-collaborator	包含“目标-冲突-转折”的场景情节
character-arc	各人物的“谎言/欲望/需求”
worldbuilding	场景创作所需的设定细节
story-sense	结构合理性确认

Outbound (chapter-drafter produces)

输出（章节起草器生成内容）

Output	Next step
Draft chapter	revision (for full manuscript revision)
Flagged scenes	Human review
Context state	Next chapter drafting

输出内容	下一步操作
章节草稿	修订（针对全稿修订）
标记场景	人工复审
上下文状态	下一章起草

Example Invocation

调用示例

Input: Chapter outline with 5 scene beats

Process:

Load outline, confirm prerequisites
Initialize progress tracker
For each scene:
- Build context from prior scenes
- Draft initial prose
- Run evaluation loop
- On ACCEPT: extract context, write output
Complete: 5 polished scenes, flagged issues documented

Output:

5 scene files in
```
drafts/[story]/[chapter]/
```
Progress tracker showing all iterations
Context file for next chapter
List of any flagged issues for human review

输入： 包含5个场景情节的章节大纲

流程：

加载大纲，确认前置条件
初始化进度追踪器
对每个场景：
- 基于之前的场景构建上下文
- 生成初始草稿
- 运行评估循环
- 接受后：提取上下文，写入输出
完成：生成5个高质量场景，记录标记的问题

输出：

5个场景文件存储于
```
drafts/[story]/[chapter]/
```
显示所有迭代的进度追踪器
用于下一章的上下文文件
需人工复审的问题列表