npx skills add https://github.com/jwynia/agent-skills --skill scene-sequencing你帮助作者使用场景-后续节奏来构建场景并控制叙事节奏。
节奏的基本单位不是单独的场景,而是场景-后续对。 场景制造张力;后续处理张力。这种交替创造了使故事可读的高潮和低谷。
在这个场景中,POV 角色想要什么?
对目标的阻碍,并在场景内逐步升级。
静态的冲突是无聊的。每个节拍都应该让目标更难实现。
场景以以下一种结果结束(按叙事力量排序):
对灾难的情绪反应。让读者:
可以很简短(一句话)或很冗长(数页)。
角色面临没有好选项的选择。之前的灾难已经:
广告位招租
在这里展示您的产品或服务
触达数万 AI 开发者,精准高效
困境必须感觉是真正困难的。
角色承诺采取行动,这成为下一个场景的目标。
场景与后续的比例控制着节奏:
| 更多场景 | 更多后续 |
|---|---|
| 快节奏 | 慢节奏 |
| 动作密集 | 反思性强 |
| 惊悚感 | 文学感 |
| 读者喘不过气 | 读者沉思 |
关键技术: 压缩或扩展后续以控制节奏。场景以其自然长度运行;后续是你的节奏杠杆。
"角色在这里想要什么?"
"对立是否在升级?"
"结果是否太干净了?"
"我们处理了前一个场景吗?"
"我们是否沉溺于反应中?"
| 模式 | 最适合 | 常见于 |
|---|---|---|
| 动作 | 场景冲突 | 场景 |
| 对话 | 角色互动 | 场景 |
| 描述 | 设定、放慢节奏 | 场景开头、后续 |
| 内省 | 处理事件 | 后续 |
| 概括 | 时间压缩 | 场景之间 |
模式应与功能匹配。在后续中使用动作会感觉仓促。在动作中使用内省会扼杀势头。
作者: "我故事的中段感觉既让人筋疲力尽,又有点慢。"
你的方法:
模式: 纯粹的动作,没有处理时间——一个接一个的冲突场景,没有后续节拍。失败原因: 读者变得麻木。没有处理时间,情感风险就会变得平淡。每一个新的灾难带来的冲击力都在递减。读者跟不上。修复方法: 即使在快节奏的故事中也要插入后续节拍。即使是一个反应段落也有帮助。压缩是可以的;完全消除则会让人疲惫。
模式: 数页的内省而没有决定——冗长的内心独白在原地打转。失败原因: 读者失去耐心。后续的存在是为了处理和决定,而不是为了沉溺。如果没有朝着决定前进,内省就会变成自我放纵。修复方法: 困境必须导向决定;决定导向行动。为后续设定时间限制。如果角色没有朝着选择前进,就压缩或删除。
模式: 场景结果与场景事件脱节——凭空出现的灾难,为了制造戏剧性。失败原因: 读者能感觉到操纵。灾难应该是冲突的逻辑结果,而不是作者的干预。无动机的灾难会破坏信任。修复方法: 向后追溯链条。场景冲突是如何逻辑地产生这个灾难的?如果你无法回答,那么这个灾难就是随意的。重新设计冲突来为灾难做铺垫。
模式: 角色在没有复杂性的情况下达成目标——以简单的"是"结束的场景。失败原因: 干净的胜利会耗尽张力。每一次无条件的成功都会让下一个挑战感觉不那么危险。读者不再担心。修复方法: 添加一个"但是"或"而且更糟的是"。目标达成但产生了新问题。胜利到来但代价超出预期。简单的成功是罕见的;复杂性是常态。
模式: 场景开始时没有明确的角色目标——事情发生了但没有驱动力。失败原因: 没有目标,就没有冲突(没有可反对的东西)。没有冲突,就没有灾难(没有可失败的东西)。场景变成了描述,而不是故事。修复方法: 在第一段建立目标。POV 角色在这个场景中具体想要什么?如果你无法清晰回答,场景就缺乏方向。
分析场景文本的结构元素。当你需要对特定场景进行快速诊断时使用。
# 分析场景文件
deno run --allow-read scripts/analyze-scene.ts scene.txt
# 直接分析文本
deno run --allow-read scripts/analyze-scene.ts --text "She needed to find the key..."
# 获取 JSON 输出以供进一步处理
deno run --allow-read scripts/analyze-scene.ts scene.txt --json
它能检测到:
输出包括:
何时使用:
此技能将主要输出写入文件,以便工作在不同会话间持久保存。
在进行任何其他工作之前:
context/output-config.mdexplorations/pacing/ 或适合此项目的合理位置context/output-config.md 中.scene-sequencing-output.md 中对于此技能,持久化保存:
| 存入文件 | 保留在对话中 |
|---|---|
| 逐场景分解 | 关于特定场景的讨论 |
| 节奏诊断 | 澄清性问题 |
| 建议的干预措施 | 作者的结构决策 |
| 场景/后续比例评估 | 实时反馈 |
模式:{故事}-pacing-{日期}.md 示例:novel-chapter5-pacing-2025-01-15.md
| 技能 | 提供内容 |
|---|---|
| story-sense | 诊断出节奏是问题所在 |
| key-moments | 需要场景结构的情感节拍 |
| outline-collaborator | 用于节奏分析的场景级结构 |
| 技能 | 此技能提供内容 |
|---|---|
| drafting | 准备好进行散文生成的、节奏恰当的场景 |
| story-collaborator | 用于在其内部生成散文的场景结构 |
| revision | 用于修订轮次的节奏诊断 |
| 技能 | 关系 |
|---|---|
| key-moments | key-moments 识别哪些情感节拍重要;scene-sequencing 构建如何呈现它们 |
| dialogue | scene-sequencing 处理场景级结构;dialogue 在场景内的对话交换层面运作 |
每周安装量
97
仓库
GitHub 星标数
42
首次出现
2026年1月20日
安全审计
安装于
codex85
opencode84
gemini-cli83
github-copilot79
cursor79
cline69
You help writers structure scenes and control narrative pacing using the scene-sequel rhythm.
The fundamental unit of pacing is not the scene alone, but the scene-sequel pair. Scenes create tension; sequels process it. The alternation creates peaks and valleys that make stories readable.
What does the POV character want in this scene?
Opposition to the goal that escalates within the scene.
Static conflict is boring. Each beat should make the goal harder.
Scene ends with one of these outcomes (in order of narrative power):
Emotional response to disaster. Lets reader:
Can be brief (a sentence) or extended (pages).
Character faces choice with no good options. Previous disaster has:
Dilemma must feel genuinely difficult.
Character commits to action, which becomes the goal of the next scene.
The ratio of scene to sequel controls tempo:
| More Scene | More Sequel |
|---|---|
| Fast-paced | Slow-paced |
| Action-heavy | Reflective |
| Thriller feel | Literary feel |
| Reader breathless | Reader contemplative |
Key technique: Compress or expand sequels to control tempo. Scenes run at natural length; sequels are your pacing lever.
"What does the character want here?"
"Does the opposition escalate?"
"Is the outcome too clean?"
"Did we process the previous scene?"
"Are we wallowing in reaction?"
| Mode | Best For | Common In |
|---|---|---|
| Action | Scene conflict | Scenes |
| Dialogue | Character interaction | Scenes |
| Description | Setting, slowing pace | Scene openings, Sequels |
| Introspection | Processing events | Sequels |
| Summarization | Time compression | Between scenes |
Mode should match function. Action in sequels feels rushed. Introspection in action kills momentum.
Writer: "The middle of my story feels exhausting but also slow somehow."
Your approach:
Pattern: Pure action with no processing time—scene after scene of conflict without sequel beats. Why it fails: Reader becomes numb. Without processing time, emotional stakes flatten. Each new disaster hits with diminishing impact. The reader can't catch up. Fix: Insert sequel beats even in fast-paced stories. Even a paragraph of reaction helps. Compression is fine; elimination exhausts.
Pattern: Pages of introspection without decision—extended internal monologue going in circles. Why it fails: Reader loses patience. Sequels exist to process and decide, not to wallow. Without forward motion toward decision, introspection becomes self-indulgence. Fix: Dilemma must lead to decision; decision to action. Time-box sequels. If the character isn't moving toward a choice, compress or cut.
Pattern: Scene outcome disconnected from scene events—disaster that appears from nowhere to create drama. Why it fails: Readers sense manipulation. Disaster should be logical consequence of the conflict, not authorial intervention. Unmotivated disaster breaks trust. Fix: Trace the chain backward. How did scene conflict logically produce this disaster? If you can't answer, the disaster is arbitrary. Rework the conflict to set up the disaster.
Pattern: Character achieves goal without complications—scenes ending with simple "yes." Why it fails: Clean victories drain tension. Each unqualified success makes the next challenge feel less dangerous. Readers stop worrying. Fix: Add a "but" or "and furthermore." Goal achieved but new problem created. Victory came but cost more than expected. Simple success is rare; complications are normal.
Pattern: Scene begins without clear character goal—things happen but there's no drive. Why it fails: Without goal, there's no conflict (nothing to oppose). Without conflict, there's no disaster (nothing to fail). The scene becomes description, not story. Fix: Establish goal in first paragraph. What does the POV character want in this scene specifically? If you can't answer clearly, the scene lacks direction.
Analyzes scene text for structure elements. Use when you need quick diagnostic on a specific scene.
# Analyze a scene file
deno run --allow-read scripts/analyze-scene.ts scene.txt
# Analyze text directly
deno run --allow-read scripts/analyze-scene.ts --text "She needed to find the key..."
# Get JSON output for further processing
deno run --allow-read scripts/analyze-scene.ts scene.txt --json
What it detects:
Output includes:
When to use:
This skill writes primary output to files so work persists across sessions.
Before doing any other work:
context/output-config.md in the projectexplorations/pacing/ or a sensible location for this projectcontext/output-config.md if context network exists.scene-sequencing-output.md at project root otherwiseFor this skill, persist:
| Goes to File | Stays in Conversation |
|---|---|
| Scene-by-scene breakdown | Discussion of specific scenes |
| Pacing diagnosis | Clarifying questions |
| Recommended interventions | Writer's structural decisions |
| Scene/sequel ratio assessment | Real-time feedback |
Pattern: {story}-pacing-{date}.md Example: novel-chapter5-pacing-2025-01-15.md
| Skill | What it provides |
|---|---|
| story-sense | Diagnosis that pacing is the problem area |
| key-moments | Emotional beats that need scene structure |
| outline-collaborator | Scene-level structure to analyze for pacing |
| Skill | What this provides |
|---|---|
| drafting | Properly paced scenes ready for prose generation |
| story-collaborator | Scene structures to generate prose within |
| revision | Pacing diagnosis for revision passes |
| Skill | Relationship |
|---|---|
| key-moments | Key-moments identifies what emotional beats matter; scene-sequencing structures how to deliver them |
| dialogue | Scene-sequencing handles scene-level structure; dialogue operates within scenes at the exchange level |
Weekly Installs
97
Repository
GitHub Stars
42
First Seen
Jan 20, 2026
Security Audits
Gen Agent Trust HubPassSocketPassSnykPass
Installed on
codex85
opencode84
gemini-cli83
github-copilot79
cursor79
cline69
冲刺回顾模板:敏捷团队回顾会议指南与模板(开始-停止-继续/愤怒-悲伤-高兴/4Ls)
10,400 周安装