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-workflowgit 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-workflow)<a href="https://agentmods.dev/skills/lj22503/diaolong-skill/narrative-workflow"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-workflow/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-workflow"><img src="https://agentmods.dev/badge/skills/lj22503/diaolong-skill/narrative-workflow.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 | $0.00055 | $0.02817 |
| Opus 5 | $0.00028 | $0.01409 |
| Sonnet 5 | $0.00011 | $0.00563 |
| Haiku 4.5 | $0.00006 | $0.00282 |
Grade A, and why
dragoncraft-studio 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 10d 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
雕龙·工坊 (DragonCraft Studio)
描述：叙事自动化工作流引擎。负责协调元Skill、场景Skill和互动设计Skill的流水线作业。
🎯 工作流模式
模式A：快速输出（默认）
- 执行：阶段0→阶段1→阶段4
- 跳过：阶段2、阶段3
- 输出：初稿 + 记忆摘要 + 简要优化建议
模式B：深度打磨
- 执行：阶段0→阶段1→阶段2→阶段4
- 迭代直到八刀评分均≥7分，去AI化检测通过
- 输出：终稿 + 迭代报告 + 记忆写入
模式C：互动设计
- 执行：阶段0→阶段1→阶段2→阶段3→阶段4
- 输出：完整叙事终稿 + 互动设计方案 + 碎片地图 + 排期表 + 记忆写入
模式D：仅互动设计（已有叙事文本）
- 用户直接提供叙事文本，跳过阶段1
- 执行：阶段0→阶段2（快速评估）→阶段3→阶段4
- 输出：互动设计方案 + 记忆写入
🔗 依赖关系
本 Skill 编排调用以下 Skill 模块：
| 依赖 Skill | 模块 | 用途 | 调用阶段 |
|---|---|---|---|
| narrative-meta | 八刀评估 | 叙事质量打分（历史/辩证/现象/语言/形式/存在/美感/元反思） | 阶段2 |
| narrative-meta | 去AI化检测 | 7条规则检测模板词/逻辑词/抽象情感等 | 阶段2 |
| narrative-meta | 伦理审查 | 三条原则检查（事实篡改/不当省略/隐私泄露） | 阶段2 |
| narrative-meta | 人格映射 | 根据素材特征推荐MBTI叙事人格 | 阶段0/阶段1 |
| narrative-meta | 一致性检查 | 跨场景比对，输出差异报告 | 阶段2 |
| narrative-meta | 记忆管理 | 存储/检索用户历史叙事 | 阶段0/阶段4 |
| narrative-personal-ip | 场景生成 | 个人IP叙事初稿生成 | 阶段1（个人IP场景） |
| 互动设计Skill | 互动设计 | 碎片地图/排期表/奖励机制 | 阶段3 |
调用路径：narrative-workflow → narrative-meta（评估/检测/审查/记忆） → narrative-personal-ip（生成）
📋 输入校验规则
- 场景（scene）：必填，枚举值：个人IP/品牌/产品/融资/销售/组织变革/公益/法律/医疗/社交媒体/创意产品/生活方式/科技/争议话题/艺术/心理/可持续/教育/复盘/危机公关/个人品牌/产品发布/书籍写作
- 模式（mode）：必填，枚举值：A/B/C/D，默认A
- 人格（persona）：可选，枚举值：ENFJ/ENFP/INFJ/INFP/不填则自动推荐
- 素材（material）：必填，JSON对象，至少包含2个字段
- 校验失败处理：场景/模式不合法 → 提示可选值；素材为空 → 拒绝执行并引导
- 长度限制：素材每个字段 20-500 字，超出范围自动截断并警告
📋 各阶段详细指令
阶段0：记忆检索（调用元Skill的记忆模块）
输入：用户ID，当前场景，素材关键词 处理：
- 检索该用户历史叙事中相同主题的故事ID
- 检索用户偏好的叙事人格、常用金句
- 检索是否有跨场景事实不一致的记录 输出格式：
{
"similar_stories": [{"story_id": "xxx", "title": "xxx", "avoid_repeat": true/false, "suggested_reference": "可引用片段"}],
"preferred_persona": "ENFP",
"inconsistencies": [],
"pending_suggestions": ["建议完成三部曲终章"]
}
阶段1：场景Skill生成
根据用户选择的场景调用对应的场景Skill。该Skill会内嵌元Skill的结构生成能力。 输出：初稿（符合该场景的结构模板）
阶段2：元Skill打磨
子步骤：
- 2.1 八刀评估：对初稿打分（1-10分），低于7分的维度触发修改
- 2.2 去AI化检测：应用7条规则，标注问题位置，自动执行润色
- 2.3 伦理审查：检查是否违反三条原则，标注省略内容
- 2.4 跨场景一致性：与记忆库中的历史事实比对，输出差异报告
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.
- 10d ago First seen · 237 lines · 0 tokens per session scan A 1f4eda4c91f1
dragoncraft-studio is a skill published in the GitHub repository lj22503/diaolong-skill (5 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 2,817 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.
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.
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.
xhs-note-creator
A content-production workflow for Xiaohongshu, a Chinese social platform for visual posts and product recommendations. It creates post copy, hashtags, image-card sets, or short-video storyboards from a topic and optional source material.
ai-video-gen
An AI video-generation tool that creates videos from text or images and can animate a digital person's first frame. It works with several video providers and requires your own API key.