dragoncraft-care

dragoncraft-care is a skill for Claude Code from lj22503/diaolong-skill. It costs 75 tokens per session (1,847 once invoked), scanned A, a copy of dragoncraft-art, MIT.

A medical storytelling guide for turning illness, treatment choices, risks, decisions, and results into clear narratives or communication materials.

In plain words
What is it for?
Use it to prepare clinician-patient conversation scripts, patient stories, educational explanations, and structured informed-consent templates.
Why use it?
It helps explain difficult medical decisions without leaving out relevant risks, side effects, uncertainty, or quality-of-life concerns.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to prepare clinician-patient conversation scripts, patient stories, educational explanations, and structured informed-consent templates.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lj22503/diaolong-skill/narrative-medical"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-medical.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,847 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 78% copy Near-identical to another mod 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 $0.00075 $0.01847
Opus 5 $0.00037 $0.00924
Sonnet 5 $0.00015 $0.00369
Haiku 4.5 $0.00007 $0.00185

Measured 11d ago against content hash 452b63132832, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dragoncraft-care 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 11d 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.

Origin

This is a copy

78% identical to dragoncraft-art — 145 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

skills/narrative-medical/SKILL.md · 154 lines

How it starts

The opening of the file, as written. The whole thing — 154 lines — stays where its author put it; the contents beside it link to each section on GitHub.

雕龙·仁心 (DragonCraft Care)

描述:医疗叙事教练。内嵌叙事元系统,帮助用户把病情/治疗方案/风险收益变成有逻辑、有冲突、有认知、有价值的医疗叙事。

🎯 功能

输入字段(四层素材)

  1. 患者遇到了什么问题(病情/症状/诊断):
  2. 有哪些治疗方案(选项/风险/收益):
  3. 患者和医生怎么决定的(沟通/共识/价值观):
  4. 结果如何(疗效/副作用/生活质量):

输入校验规则

  • 必填字段:4 个输入字段全部必填,缺任何一项需提示用户补充
  • 长度限制:每个字段 20-500 字,过短需追问细节,过长需提炼核心
  • 格式要求:用户输入为自然语言,AI 自动解析为结构化素材
  • 受众画像(可选):提供时用于调整叙事角度和语言风格(患者/家属/医学生/公众)
  • 叙事人格(可选):不填时根据素材特征自动推荐(INFJ/ISFJ/ENFJ)
  • 校验失败处理:字段缺失 → 提示补充;长度不足 → 追问细节;格式错误 → 引导正确格式
  • ⚠️ 强制合规:医疗知情场景强制全面披露,不得省略与核心决策有直接因果关系的风险信息

结构

病情呈现 → 治疗选择困境 → 医患沟通 → 决策 → 疗效与生活质量

输出

  • 医患沟通脚本(500字)
  • 患者故事版(800字)
  • 知情同意书(结构化模板)

🔗 依赖关系

本 Skill 依赖以下元 Skill 模块:

依赖模块 来源 Skill 用途
八刀评估 narrative-meta 质量打分(历史/辩证/现象/语言/形式/存在/美感/元反思)
去 AI 化检测 narrative-meta 7 条规则检测模板词、逻辑词、抽象情感等
伦理审查 narrative-meta 三条原则检查(医疗知情强制全面披露
人格映射 narrative-meta 根据素材特征推荐 MBTI 叙事人格
记忆管理 narrative-meta 存储/检索用户历史叙事,确保跨场景一致性

调用方式:通过 narrative-workflow 编排调用,或直接调用 narrative-meta 对应模块。

⚠️ 常见错误

  1. 写成医学教科书:只罗列医学术语和方案,没有患者故事和情感连接
  2. 写成宣传稿:只有疗效,没有承认风险和副作用,缺乏真实感
  3. 只讲成功:没有治疗过程中的挣扎和不确定性,像机器人写的
  4. 医生/患者过度完美:没有承认决策的复杂性和价值观冲突,缺乏真实感
  5. 空喊口号:没有具体的患者见证和数据锚点

🧪 使用示例

示例1:医患沟通脚本版

用户输入:

患者遇到了什么问题:65岁男性,早期肺癌,有吸烟史
有哪些治疗方案:手术切除(风险高/治愈率高)/放疗(风险低/复发率高)/保守治疗
患者和医生怎么决定的:医生详细解释三种方案的风险收益,患者选择手术
结果如何:手术成功,恢复良好,戒烟成功

AI输出:

【人格推荐】INFJ
理由:素材特征为深度疗愈、信任建立、价值观对齐,INFJ叙事风格最适合。

【医患沟通脚本版】(约700字)

王医生:张先生,您的检查结果出来了。早期肺癌。

张先生:(沉默)……严重吗?

王医生:早期,发现得很及时。治愈率很高。但我们需要讨论治疗方案。

张先生:有哪些选择?

王医生:三种。
第一种,手术切除。治愈率最高,85%以上。但风险也最高,
   您的年龄和吸烟史,手术并发症风险约15%。
第二种,放疗。风险低,但复发率高,5年内约30%。
第三种,保守治疗。不干预,但肿瘤会生长。

张先生:……您建议哪种?

王医生:作为医生,我建议手术。但作为人,我需要知道您的价值观。
   您更看重治愈率,还是更看重手术安全?

张先生:我孙子刚出生。我想看着他长大。

王医生:那手术是更好的选择。我们会做好术前准备,降低风险。

张先生:好。我做手术。

【患者故事版】(约1000字)
[完整叙事]

【知情同意书版】
疾病诊断:早期肺癌(T1N0M0)
治疗方案:手术切除(肺叶切除+淋巴结清扫)

风险说明:
- 手术并发症风险:约15%(感染/出血/肺漏气)
- 麻醉风险:约1%(严重不良反应)
- 死亡率:约0.5%

收益说明:
- 治愈率:85%以上
- 5年生存率:90%以上

替代方案:
- 放疗:风险低,复发率30%
- 保守治疗:不干预,肿瘤会生长

患者声明:
我已充分了解上述信息,理解风险和收益,自愿选择手术方案。

患者签名:_________ 日期:_________
医生签名:_________ 日期:_________

Read the full file on GitHub · 154 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. 11d ago First seen · 154 lines · 0 tokens per session scan A 452b63132832

Subscribe to this mod's changes

dragoncraft-care is a skill published in the GitHub repository lj22503/diaolong-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 75 tokens to every session and 1,847 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 78% identical to dragoncraft-art, differing in 145 lines, and is treated as a copy.