Back to Details

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:
  1. Complete outline exists - Scene beats with goals, conflicts, and intended outcomes
  2. Characters defined - Lie/want/need, voice patterns, arc positions
  3. World established - Setting details sufficient for scene work
  4. 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：
  1. 已有完整大纲 - 包含场景情节的目标、冲突和预期结果
  2. 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
  3. 世界观已建立 - 具备足够支撑场景创作的设定细节
  4. 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.
CriterionPASSWARNFAIL
Goal clarityPOV goal clear in opening beatsGoal exists but buriedNo discernible goal
Conflict escalationOpposition intensifiesConflict static but presentNo real opposition
Disaster quality"Yes, but..." or "No, and..."Simple "No"Clean "Yes" or no resolution
Sequel presenceReaction-dilemma-decision presentAbbreviated sequelMissing after high-tension
Scene-sequel ratioMatches intended pacingSlight mismatchSeverely 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.
CriterionPASSWARNFAIL
Lie visibilityFalse belief evident in choicesLie present but unstatedNo lie operative
Want/Need gapClear tension between stated/actualGap exists but unclearWant = Need (no tension)
Arc progressScene advances or challenges arcArc static but consistentCharacter contradicts arc
Transformation markersChoices reflect arc positionPosition unclearActs 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.
CriterionPASSWARNFAIL
Form axisNon-default formSlight variationExactly genre default
Knowledge axisOwn concerns, accidental intersectionSome plot awarenessFully story-serving
Goal axisOwn agenda that collidesGoal connected to plotPurely protagonist-serving
Role axisOwn story that intersectsSomewhat independentExists only for hero
Orthogonality test2+ axes orthogonal1 axis orthogonalAll 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.
CriterionPASSWARNFAIL
Voice distinctivenessCharacters distinguishable without tagsSome overlapIdentical voices (D1)
Subtext presenceGap between said and meantOccasional direct statementsEverything on-the-nose (D4)
Double-duty test3+ functions per exchange2 functionsSingle function only (D5)
NaturalnessContractions, interruptions, rhythmSlightly formalWooden/stilted (D2)
Exposition handlingInformation through conflictMinor "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.
CriterionPASSWARNFAIL
Sentence varietyLength and structure varySome variationMonotonous (P4)
ClarityConcrete, clear antecedentsOccasional abstractionUnclear writing (P2)
Voice consistencyDiction level consistentMinor shiftsRandom shifts (P6)
EconomyWords earn placeMinor redundancyOverwrought (P3)
Active voicePassive intentionalSome default passivePassive 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)
CompositeOutcomeAction
>= 80ACCEPTScene complete, proceed to next
60-79REVISEFix lowest-scoring pass, re-evaluate
40-59REWRITERegenerate with failure constraints
< 40REJECTFull 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

LevelLimitOn Exceed
Per-pass3Escalate to rewrite
Per-scene12Accept at threshold 50, flag for review
Per-chapter50Stop, 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

SceneStatusPassIterationsScoreIssues
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）

  1. Identify lowest-scoring pass
  2. Extract specific failure criteria
  3. Generate minimal fix addressing that criterion
  4. Re-evaluate that pass + downstream passes
  5. If pass improves, recalculate composite
  1. 确定得分最低的评审项
  2. 提取具体失败的标准
  3. 生成仅针对该标准的最小修复方案
  4. 重新评估该评审项及下游评审项
  5. 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）

  1. Preserve scene goal from outline
  2. Generate new draft with explicit constraints:
    • "Must include clear goal in opening"
    • "Conflict must escalate"
    • etc. based on failures
  3. Re-run full evaluation loop
  1. 保留大纲中的场景目标
  2. 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
  3. 重新运行完整评估循环

Reject (score < 40)

驳回（得分<40）

  1. Return to outline beat
  2. Re-draft from scratch
  3. Treat as new scene (reset iterations)
  1. 返回大纲情节
  2. 从头重新起草
  3. 视为新场景（重置迭代次数）

Conflict Resolution

冲突解决

When fixing one pass breaks another:
  1. Detect: Re-run all passes after any fix
  2. Compare: Did any pass regress?
  3. Prioritize: Higher-weight pass wins ties
  4. Seek synthesis: Can fix satisfy both?
  5. 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：
  1. 检测：任何修复后重新运行所有评审项
  2. 对比：是否有评审项出现倒退？
  3. 优先级：权重更高的评审项优先
  4. 寻求折中：是否存在同时满足两者的修复方案？
  5. 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）

SkillWhat it provides
outline-collaboratorScene beats with goal-conflict-disaster
character-arcLie/want/need for each character
worldbuildingSetting details for scene work
story-senseConfirmation 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）

OutputNext step
Draft chapterrevision (for full manuscript revision)
Flagged scenesHuman review
Context stateNext 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:
  1. Load outline, confirm prerequisites
  2. Initialize progress tracker
  3. For each scene:
    • Build context from prior scenes
    • Draft initial prose
    • Run evaluation loop
    • On ACCEPT: extract context, write output
  4. 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：
  1. 加载大纲，确认前置条件
  2. 初始化进度追踪器
  3. 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
  4. 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