dragoncraft-persona

dragoncraft-persona is a skill for Claude Code from lj22503/diaolong-skill. It costs 67 tokens per session (1,960 once invoked), scanned A, original, MIT.

A writing assistant for turning personal experiences into structured stories. It helps shape background, difficulties, decisions, results, and lessons into a clear personal narrative.

In plain words
What is it for?
Use it for personal introductions, personal-brand stories, public-account articles, and short-video scripts. It produces long, short-video, and brief biography versions from supplied material.
Why use it?
It addresses stories that merely list events, sound like a résumé, or lack a clear turning point and insight. It can also adapt the story for a chosen audience and style.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it for personal introductions, personal-brand stories, public-account articles, and short-video scripts. It produces long, short-video, and brief biography versions from supplied material.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/lj22503/diaolong-skill/narrative-personal-ip"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-personal-ip.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 67 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,960 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 $0.00067 $0.01960
Opus 5 $0.00034 $0.00980
Sonnet 5 $0.00013 $0.00392
Haiku 4.5 $0.00007 $0.00196

Measured 11d ago against content hash bb446def0c70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

dragoncraft-persona 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.

skills/narrative-personal-ip/SKILL.md · 151 lines

How it starts

The opening of the file, as written. The whole thing — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.

雕龙·立人 (DragonCraft Persona)

描述:个人IP叙事教练。内嵌叙事元系统,帮助用户把零散的个人经历变成有逻辑、有冲突、有认知、有价值的个人故事。

🎯 功能

输入字段(四层素材)

  1. 我做过什么(经历/成就/失败):
  2. 我看重什么(价值观/信念):
  3. 我遭遇了什么(关键困境/低谷):
  4. 我学到了什么(核心认知/可交付价值):

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
  • 叙事人格(可选):不填时根据素材特征自动推荐(INFP/INFJ/ENFP/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

结构

起点(个人背景/现状) → 冲突(困境/低谷/失败) → 转折(关键决策/顿悟) → 结果(改变/成长) → 认知(核心哲学) → 人物定位(IP人设)

输出

  • 完整版(800-1500字)
  • 短视频版(300字)
  • 个人简介版(150字内)

🔗 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(事实篡改/不当省略/隐私泄露)
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. 写成简历:只罗列经历,没有冲突和认知
  2. 写成抒情散文:只有情感,没有逻辑推进
  3. 只讲发生了什么:没有写清楚"我当时为什么会这样想"
  4. 人设过度完美:缺乏脆弱性和真实感
  5. 空喊口号:没有具体的细节和场景锚点

🧪 使用示例

示例1:完整个人IP故事

用户输入:

我做过什么:从大厂裸辞,gap一年,转型做职业规划师
我看重什么:自由比稳定更重要,复盘比成功更有价值
我遭遇了什么:裸辞后半年没收入,创业失败,客户跑单
我学到了什么:失败不给你加分,复盘才给;自由不是不干活,是决定干什么
受众画像:25-35岁职场人,考虑转型但害怕风险
叙事人格:INFP(可选,不填则自动推荐)

AI输出:

【人格推荐】INFP
理由:素材特征为个人成长、脆弱经历、真诚反思,INFP叙事风格最适合。

【记忆检索】
未找到相关历史记录。建议:这是系列故事的良好起点,可考虑形成"人生转折三部曲"。

【完整版】(约1200字)

辞职那天,我发了一条朋友圈:"以后没有KPI了"。收获了192个赞。

那是2023年5月,我在深圳某大厂做了三年产品经理。每天早上9点到公司,晚上10点离开,周末随时待命。我以为这就是"稳定"。

直到有一天加班到凌晨,保安大叔问我:"姑娘,你每天都这么晚,是住公司吗?"

我站在电梯里,突然哭了。不是委屈,是害怕——我害怕三十年后我还是这样活着。

裸辞后的第一个月,我在家里办公,每天睡到自然醒,下午去咖啡厅写方案。我以为这就是自由。

第三个月,合伙人说没钱发工资了。我才发现,我根本没有算过账。我以为创业就是"有一个好想法,然后别人给钱"。

第五个月,我们接了一个10万块的小单,客户改了11版,最后没付尾款。我蹲在出租屋阳台抽烟,觉得还不如回去写周报。

那是我第一次意识到:裸辞不是勇气,创业也不是冒险。真正的勇气是敢承认"我连账都不会算"。

后来我把这11版修改记录打印出来,贴了整面墙。每看一次,就提醒自己:失败不给你加分,复盘才给。

现在我做职业规划师,帮助了30多个人找到方向。我不教他们"如何成功",我教他们"如何面对失败"。

因为我知道,真正的自由不是离开哪里,而是决定去哪里。

【短视频版】(约300字)

"你有没有算过,你一个月能赚多少钱?"

这是我裸辞后第三个月,合伙人问我的问题。

我之前在大厂做产品经理,年薪30万。我以为我懂钱。

直到我自己创业,接了一个10万块的小单,客户改了11版,最后没付尾款。

我蹲在出租屋阳台抽烟,突然明白了一件事:

裸辞不是勇气。承认自己不会算账,才是。

现在我做职业规划师,不教人成功,教人面对失败。

因为真正的自由,不是离开哪里,是决定去哪里。

【个人简介版】(约150字)

前大厂产品经理,2023年裸辞创业失败,现为职业规划师。帮助30+人找到方向。核心理念:失败不给你加分,复盘才给;自由不是不干活,是决定干什么。

Read the full file on GitHub · 151 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 · 151 lines · 0 tokens per session scan A bb446def0c70

Subscribe to this mod's changes

dragoncraft-persona is a skill published in the GitHub repository lj22503/diaolong-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 67 tokens to every session and 1,960 once invoked, about $0.0003 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.