Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add wordflowlab/novel-writer-skills --skill scene-structuregit clone --depth 1 https://github.com/wordflowlab/novel-writer-skillsWrote 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.
[](https://agentmods.dev/skills/wordflowlab/novel-writer-skills/scene-structure)<a href="https://agentmods.dev/skills/wordflowlab/novel-writer-skills/scene-structure"><img src="https://agentmods.dev/badge/skills/wordflowlab/novel-writer-skills/scene-structure/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.
<a href="https://agentmods.dev/skills/wordflowlab/novel-writer-skills/scene-structure"><img src="https://agentmods.dev/badge/skills/wordflowlab/novel-writer-skills/scene-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.02684 |
| Opus 5 | $0.00017 | $0.01342 |
| Sonnet 5 | $0.00007 | $0.00537 |
| Haiku 4.5 | $0.00003 | $0.00268 |
Grade A, and why
scene-structure-techniques 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.
How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
场景结构写作技巧
什么是场景？
场景是实时发生的冲突单元，角色追求目标并面对障碍。
不是场景：说明、背景故事、旅行、时间流逝
是场景：争论、谈判、追逐、揭露
场景-续场模型
每个场景都应该遵循这个模式：
场景（行动） 续场（反应）
├── 目标 ├── 情绪
├── 冲突 ├── 困境
└── 灾难/成功 └── 决定
场景结构（行动）
1. 目标
POV角色在这个场景想要什么？
必须是：
- 具体的："拿到钥匙" 而非 "搞清楚事情"
- 可实现的：可能在这个场景成功或失败
- 紧迫的：现在重要，不是最终
你的角色的场景目标：
[明确、具体、紧迫]
他们为什么现在想要这个？：
[情境/紧迫性]
2. 冲突
什么阻止他们得到想要的？
冲突类型：
- 外部：另一个角色反对他们
- 环境：物理障碍
- 内部：他们自己的恐惧或犹豫
- 时间：时间不够
- 信息：缺少关键知识
最好的场景结合 2-3 种冲突类型。
你的场景冲突：
-
[主要障碍]
-
[次要障碍]
-
[可选第三个]
3. 灾难或成功
场景如何解决？
灾难（更常见）：
- 他们未能得到想要的
- 他们得到了，但代价可怕
- 他们得到了更糟的东西
成功（谨慎使用）：
- 他们实现目标
- 但揭示更大的问题
- 或成功是空洞的
你的场景解决：
[灾难或成功 + 后果]
续场结构（反应）
在紧张场景之后，读者需要续场 - 角色处理的安静时刻。
1. 情绪反应
角色对刚发生的事情感觉如何？
展示不要说：
- 不好："莎拉感到悲伤"
- 好："莎拉的手不停颤抖"
你的角色的即时情绪：
[情绪的身体表现]
2. 困境
灾难创造了一个困境 - 没有好选择：
- 选项 A：安全但妥协价值观
- 选项 B：冒险但保持正直
- 选项 C：中间路线，但不确定
你的角色的困境：
- 选项 A：> [安全选择]
- 选项 B：> [冒险选择]
- 选项 C：> [中间地带]
3. 决定
他们决定做什么？
这个决定成为下一个场景的目标。
你的角色的决定：
[他们接下来要做什么]
这成为下一个场景的目标，创造无缝的场景到场景连接。
场景节奏点
现在让我们构建场景的实际节奏（微时刻）：
开场节奏
我们如何进入场景？
- 尽可能晚地开始
- 直接进入冲突/张力
- 快速建立 POV 和地点
糟糕的开场："莎拉醒来，刷牙，吃早餐..." 好的开场："莎拉的手机嗡嗡响。信息来自她死去的姐姐。"
你的开场节奏：
[用户提供]
上升张力节奏
冲突如何升级？
每个节奏应该：
- 提高风险
- 使情况复杂化
- 揭示角色
示例升级：
节奏 1：莎拉要求文件 → 被拒绝
节奏 2：莎拉诉诸友谊 → 老板揭示他知道她的秘密
节奏 3：莎拉威胁辞职 → 老板揭示他一直在保护她
节奏 4：莎拉意识到她错了 → 现在必须在忠诚中选择
你的升级节奏（3-5个）：
-
[第一个节奏]
-
[第二个节奏]
-
[第三个节奏]
-
[可选第四个]
-
[可选第五个]
高潮节奏
最高张力的时刻
这是：
- 角色做出关键选择的地方
- 真相被揭示的地方
- 行动达到峰值强度的地方
- 一切悬而未决的地方
你的高潮节奏：
[用户提供]
解决节奏
即时后果
不要在高潮结束 - 给一个节奏的余波：
- 角色的即时反应
- 什么改变了
- 暗示接下来会发生什么
你的解决节奏：
[用户提供]
张力管理
张力级别
场景应该在强度上有所不同：
高张力（30%） ⚡️ 行动、对抗、揭露
中等张力（50%） 🔥 调查、计划、建立
低张力（20%） 🌊 反思、连接、设置
太多高张力 = 读者疲劳 太多低张力 = 读者无聊
这个场景的张力级别是什么？
[用户选择]
上一个场景的张力是什么？
[用户提供或我参考追踪数据]
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.
- 12d ago First seen · 362 lines · 34 tokens per session scan A 6957bcefb32c
scene-structure-techniques is a skill published in the GitHub repository wordflowlab/novel-writer-skills (258 stars, last pushed 10mo ago), licensed MIT. It adds 34 tokens to every session and 2,684 once invoked, about $0.0002 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…