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 lj22503/diaolong-skill --skill narrative-bookgit clone --depth 1 https://github.com/lj22503/diaolong-skillWrote 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/lj22503/diaolong-skill/narrative-book)<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.
<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>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 | $0.00083 | $0.02923 |
| Opus 5 | $0.00042 | $0.01461 |
| Sonnet 5 | $0.00017 | $0.00585 |
| Haiku 4.5 | $0.00008 | $0.00292 |
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.
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。
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.
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 · 224 lines · 0 tokens per session scan A ef0b6129eb1e
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.
Other skills, from other repositories
short-drama
A production workflow for making multi-episode AI short dramas, covering story planning, character consistency, scripts, generated video shots, voices, sound, subtitles, and final assembly.
paper-explainer
A research-content workflow that turns an arXiv paper or a local PDF into an explanation for a video or written article. arXiv is a public online archive of research papers.
clipify
A video-editing workflow that finds notable moments in a long English video and turns them into separate short clips. It can change widescreen video to vertical format and add word-by-word captions.
ecom-details-image
A planning tool for e-commerce product visuals, including main-image concepts, scene ideas, detail-page directions, and prompts for image-generation systems.
multi-voice-dubbing
A script-to-audio workflow that gives different characters different voices and emotions, then combines their lines into one audio track with subtitles naming each speaker.
novel-writer
A file-based writing workflow for creating long novels or serialized web fiction, from the initial idea and character details through an outline and individual chapters.