dragoncraft-book

dragoncraft-book is a skill for Claude Code from lj22503/diaolong-skill. It costs 83 tokens per session (2,923 once invoked), scanned A, original, MIT.

A writing coach for turning a narrative-skill system into books or newsletter articles. It follows specified rules for structure, tone, examples, and chapter formatting.

In plain words
What is it for?
Use it to draft chapters, add real cases, format newsletter posts, explain ideas to non-specialists, and guide readers toward a GitHub project.
Why use it?
It reduces the work of deciding how to organize long-form content and keep its language and format consistent.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to draft chapters, add real cases, format newsletter posts, explain ideas to non-specialists, and guide readers toward a GitHub project.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/lj22503/diaolong-skill/narrative-book
Install

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.

Any agent
npx skills add lj22503/diaolong-skill --skill narrative-book
Clone the repo
git clone --depth 1 https://github.com/lj22503/diaolong-skill

Made for: Claude Code.

Wrote 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.

agentmods badge for dragoncraft-book

README.md
[![agentmods](https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-book/github.svg)](https://agentmods.dev/skills/lj22503/diaolong-skill/narrative-book)
Your own site
<a href="https://agentmods.dev/skills/lj22503/diaolong-skill/narrative-book"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-book/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.

agentmods 80×15 button for dragoncraft-book

Your own site · 80×15
<a href="https://agentmods.dev/skills/lj22503/diaolong-skill/narrative-book"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-book.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 83 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,923 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00083 $0.02923
Opus 5 $0.00042 $0.01461
Sonnet 5 $0.00017 $0.00585
Haiku 4.5 $0.00008 $0.00292

Measured 12d ago against content hash ef0b6129eb1e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dragoncraft-book 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.

skills/narrative-book/SKILL.md · 224 lines

How it starts

The opening of the file, as written. The whole thing — 224 lines — stays where its author put it; the contents beside it link to each section on GitHub.

雕龙·著书 (DragonCraft Book)

描述:书籍写作教练。内嵌叙事元系统,帮助你将叙事 Skill 体系写成书籍/公众号文章,符合燃冰的写作特色。

🎯 写作风格指令(全局)

# 写作风格指令

你正在撰写《叙事引擎:AI时代的内容操作系统》一书。请严格遵循以下风格指南:

## 核心定位
- **受众**:非专业写作者(创业者、产品经理、个人IP打造者、内容运营)。
- **调性**:专业但不学术、温暖但不煽情、结构化但不枯燥。
- **语言**:用"你"直接与读者对话,避免"读者""我们"等第三人称泛称。

## 句式与节奏
- 以短句为主,单句不超过25字。
- 段落不超过5行(手机屏幕3-5行),多用空行分隔。
- 每300字左右插入一个视觉锚点(小标题、列表、图示、引用块)。

## 词汇选择
- 多用具体名词和动词,少用抽象形容词。
- 禁止使用以下词汇:赋能、抓手、闭环、对齐、底层逻辑、在当今时代、值得注意的是、总而言之。
- 善用口语化表达:"说白了""你想啊""说白了就是"。

## 情感表达
- 用细节呈现情感,不说"他很感动",而是"他盯着屏幕,半天没说话"。
- 允许适度的脆弱和自嘲,例如:"好吧,我承认这件事我也搞砸过。"
- 克制抒情,不煽情不卖惨。

## 结构要求
- 每章开头有导言(3-5句,说明本章解决什么问题)。
- 每节有小标题,长度不超过10字。
- 每章结尾有小结(3-5个要点,可用列表)。
- 关键概念配案例,每章至少2个完整案例。

## 参考风格
- 语言轻盈:如汪曾祺
- 结构清晰:如杰克·哈特《故事技巧》
- 真诚温度:如萨提亚·纳德拉《刷新》

🎯 分场景风格微调

# 分场景风格参数

在全局风格基础上,根据以下内容类型微调:

## 理论阐释型(第1-3章)
- **语速**:稍慢,允许中长句解释概念。
- **比喻密度**:高频,每段至少一个类比,把抽象变具体。
- **案例密度**:每200字一个微型案例。

## 案例拆解型(第4-13章)
- **开篇**:用场景痛点开头,3秒拉入。
- **数据**:必须附具体数字(如"服务了2300个用户"而非"大量用户")。
- **金句**:每章至少1句可被单独引用的句子。

## 技术工具型(第15-18章)
- **语言**:更简洁,多用短句和命令式。
- **可视化**:必须配图示或代码块/schema示意。
- **检查清单**:每章至少一个可打印的清单。

## 反思升华型(第19-21章)
- **人称**:多用"我""你",建立对话感。
- **留白**:章节末尾留一个开放性问题,不急于给答案。
- **情感**:允许适度个人经历叙述,但要克制。

🎯 去AI化自检清单

# 去AI化自检指令

在输出本章内容后,请用以下规则进行自检并标注分数:

## 七条规则
1. **模板词密度**:扫描下列词汇,每出现一次扣2分:「在当今时代」「值得注意的是」「综上所述」「不可否认」「众所周知」「总而言之」。目标:0次。

2. **句长方差**:计算每句字数,方差小于15扣5分。目标:长短句交错。

3. **逻辑词过密**:统计「因此」「所以」「从而」「于是」「进而」占全文比例,超过3%扣5分。目标:用换行和破折号代替。

4. **具体锚点计数**:计数数字、专有名词、时间、具体动作,每200字少于3个扣10分。目标:每200字至少3个锚点。

5. **情感抽象词**:「我很感动」「我震撼了」「令人兴奋」「无比幸福」每出现一次扣2分。目标:全部替换为具象描写。

6. **人格一致性**:检查代词「我/你/我们」和语气是否跳跃,不一致扣3分。目标:全文统一。

7. **过度解释**:「这意味着」「换句话说」「也就是说」「简而言之」每出现一次扣2分。目标:删除,留白。

## 输出格式
请在每章末尾附:
- 去AI化自检得分:__/100
- 扣分明细:列出具体扣分项和位置
- 建议修改:至少3条

🎯 八刀写作监听

# 八刀写作监听指令

在撰写本书内容时,请自我监听以下维度,确保每章得分不低于6分:

| 维度 | 监听问题 | 及格标准 |
|------|----------|---------|
| **历史** | 本章的因果链是否清晰?有没有跳跃? | 每个观点都有"因为→所以"支撑 |
| **辩证** | 案例和数据是否真实可信? | 不虚构、不夸大、可查证 |
| **现象** | 有没有具体场景、数字、动作? | 每300字至少2个具体锚点 |
| **语言** | 有没有套话、黑话、长句? | 无禁用词,句长≤25字 |
| **形式** | 有没有导言、小标题、小结? | 结构完整,可扫读 |
| **存在** | 读者会感到"这与我有关"吗? | 使用"你",场景代入感强 |
| **美感** | 有没有一个让人记住的表达? | 每章至少1个金句或比喻 |
| **元反思** | 是否承认了知识的局限性? | 至少一处"当然,这并非总是……" |

如某维度得分低于6分,请标注并重写该段。

Read the full file on GitHub · 224 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

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.

  1. 12d ago First seen · 224 lines · 0 tokens per session scan A ef0b6129eb1e

Subscribe to this mod's changes

dragoncraft-book is a skill published in the GitHub repository lj22503/diaolong-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 83 tokens to every session and 2,923 once invoked, about $0.0004 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 2026-08-31.