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-legalgit 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-legal)<a href="https://agentmods.dev/skills/lj22503/diaolong-skill/narrative-legal"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-legal/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-legal"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-legal.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 | $0.00074 | $0.02109 |
| Opus 5 | $0.00037 | $0.01055 |
| Sonnet 5 | $0.00015 | $0.00422 |
| Haiku 4.5 | $0.00007 | $0.00211 |
Grade A, and why
dragoncraft-reason 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 — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
雕龙·明理 (DragonCraft Reason)
描述:法律叙事教练。内嵌叙事元系统,帮助用户把案件事实/争议焦点/法律依据变成有逻辑、有冲突、有认知、有价值的法律叙事。
🎯 功能
输入字段(四层素材)
- 发生了什么(案件事实/时间线/关键证据):
- 争议焦点是什么(双方主张/核心分歧):
- 法律怎么规定(法律依据/判例/法理):
- 我们的主张是什么(诉求/理由/证据链):
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(法官/陪审团/当事人/媒体)
- 叙事人格(可选):不填时根据素材特征自动推荐(INTJ/ISTJ/ENTJ)
- 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:法律庭审场景强制全面披露,不得省略与核心决策有直接因果关系的信息
结构
场景重建(发生了什么) → 动机与机会(为什么是他) → 关键节点(证据对应情节) → 排除合理怀疑(反驳对方故事) → 呼吁正义
输出
- 开庭陈述故事版(5分钟)
- 结案陈词叙事版
- 证据链叙事映射表(证据→故事节点)
🔗 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(法律庭审强制全面披露) |
| 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
- 写成法律教科书:只罗列法条和理论,没有案件事实和证据链
- 写成宣传稿:只有主张,没有承认对方论点和证据,缺乏说服力
- 只讲对自己有利的事实:没有全面披露,法官/陪审团不信任
- 当事人过度完美:没有承认不利事实和证据,缺乏真实感
- 空喊口号:没有具体的证据锚点和法律依据
🧪 使用示例
示例1:代理词/辩护词版
用户输入:
发生了什么:2023年5月,张先生委托理财顾问购买基金,亏损30%
争议焦点是什么:理财顾问是否尽到适当性义务/是否误导销售
法律怎么规定:《证券期货投资者适当性管理办法》第22条,经营机构应当了解客户信息并评估风险承受能力
我们的主张是什么:理财顾问未进行风险测评,直接推荐高风险基金,违反适当性义务,应赔偿损失
AI输出:
【人格推荐】INTJ
理由:素材特征为逻辑严密、证据导向、法理分析,INTJ叙事风格最适合。
【代理词/辩护词版】(约1200字)
尊敬的审判长、审判员:
我代表张先生,就理财顾问适当性义务纠纷一案,发表以下代理意见。
一、案件事实
2023年5月,张先生走进某基金公司营业部。
他是一名普通上班族,风险承受能力评估为"稳健型"。
理财顾问李某某,向他推荐了一只股票型基金——风险等级"高风险"。
张先生问:"这个基金下个月能涨多少?"
李某某答:"这只基金过去三年年化收益20%,很适合您。"
张先生购买了10万元。
六个月后,亏损3万元。
二、争议焦点
本案的核心争议是:理财顾问是否尽到了适当性义务?
对方主张:张先生自愿购买,风险自担。
我方主张:理财顾问未进行风险测评,直接推荐高风险基金,违反适当性义务。
三、法律依据
《证券期货投资者适当性管理办法》第22条明确规定:
经营机构应当向投资者销售相适应的产品或者服务。
这意味着:
1. 经营机构必须了解客户的风险承受能力
2. 经营机构必须评估产品的风险等级
3. 经营机构必须将适当的产品销售给适当的投资者
四、我们的主张
理财顾问李某某,在本案中:
1. 未对张先生进行风险测评
2. 将高风险产品销售给稳健型投资者
3. 使用"过去三年年化收益20%"等误导性表述
这违反了适当性义务。
应当赔偿张先生的损失。
不是因为他"不懂投资"。
是因为经营机构"没有尽到义务"。
请求法院支持我方的诉讼请求。
【事实陈述版】(约600字)
[完整叙事]
【法律意见书版】
Q1:适当性义务的法律依据是什么?
A1:《证券期货投资者适当性管理办法》第22条。
经营机构应当了解客户信息并评估风险承受能力,销售相适应的产品。
Q2:如何证明理财顾问未尽适当性义务?
A2:证据链:
- 张先生风险测评记录缺失(证据1)
- 产品风险等级为"高风险"(证据2)
- 张先生风险承受能力为"稳健型"(证据3)
- 理财顾问使用"过去三年年化收益20%"表述(证据4)
Q3:赔偿范围?
A3:直接损失(3万元)+ 利息损失。
依据:《民法典》第1184条,侵害他人财产的,按照损失发生时的市场价格计算。
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 · 170 lines · 0 tokens per session scan A 1bc85554f4e6
dragoncraft-reason is a skill published in the GitHub repository lj22503/diaolong-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 74 tokens to every session and 2,109 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
skill-risk-scanner
A content-risk checker that assesses whether writing appears insufficiently original and whether described image, audio, video, or brand usage may create copyright or citation concerns.
skill-short-link
A pre-publication review that checks content for compliance risks and basic quality problems. It can review text, images, videos, or a mixture of them for a chosen platform.
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.
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.