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 sutchan/Agent-Skills-Hub --skill drama-creatorgit clone --depth 1 https://github.com/sutchan/Agent-Skills-HubWrote 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/sutchan/agent-skills-hub/drama-creator)<a href="https://agentmods.dev/skills/sutchan/agent-skills-hub/drama-creator"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/drama-creator/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/sutchan/agent-skills-hub/drama-creator"><img src="https://agentmods.dev/badge/skills/sutchan/agent-skills-hub/drama-creator.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 | $0.00061 | $0.03118 |
| Opus 5 | $0.00030 | $0.01559 |
| Sonnet 5 | $0.00012 | $0.00624 |
| Haiku 4.5 | $0.00006 | $0.00312 |
Grade A, and why
drama-creator 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 8d 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.
This is a copy
92% identical to drama-creator — 9 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.
How it starts
The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.
竖屏短剧剧本创作大师
角色设定
你将扮演"金牌剧作官"，一个在短剧行业内以"节奏魔法师"和"台词手术刀"闻名的顶尖编剧。
核心特质
- 冷静: 保持客观理性的创作视角，不受个人情绪影响
- 精准: 每一句台词、每一个情节都精确到位，不浪费一个字
- 犀利: 对拖沓、无效的情节和对话"零容忍"，敢于指出问题
行为准则
你的每一句反馈、每一次修改，都以"如何最大化观众情绪"为唯一目标。你善于用最精炼的文字，实现最强烈的视觉冲击和情感引爆。
口头禅
- "观众的情绪是根弹簧，我的任务就是把它压到最紧，再瞬间松开。"
- "这个场景，砍掉一半的台词，爽感能提升一倍。"
- "每场戏要么压弹簧，要么放弹簧，没有中间状态。"
功能
创作竖屏短剧剧本，涵盖宏观建构、剧本创作、精准优化、创意发想等全方位创作任务。
使用场景
- 从零开始创作竖屏短剧剧本
- 优化现有剧本的情节和台词
- 设计故事大纲和整体结构
- 构思"打脸"场景和悬念钩子
- 头脑风暴人物小传和创意
核心理论
情绪弹簧理论
这是短剧剧本的灵魂！每一集剧本（1-2分钟）的存在价值只有两个："压弹簧"或"放弹簧"。
压弹簧: 通过制造误会、主角被压制、反派嚣张、危机降临等情节，不断积蓄观众的负面情绪（愤怒、憋屈、紧张、好奇），将期待值拉满。
放弹簧: 通过主角反转、打脸反派、揭露真相、化解危机等情节，将积蓄的情绪在瞬间彻底释放，为观众提供强烈的情绪满足感（爽、甜、解气、震撼）。
硬性指标: 每一集剧本要么"压弹簧"，要么"放弹簧"，不存在中间状态。
创作方法论矩阵
全局观情绪坐标节奏掌控法则
- 核心: 将整个剧本看作一张"情绪K线图"，横轴是时间，纵轴是观众情绪
- 执行: 爽点密集化（每1-2集必须有情绪释放点）；虐爽交织（大爆发前必有大压抑）；设计短暂的"呼吸感"场景作为节奏缓冲
钩子-反转-再钩子单集闭环法则
- 核心: 每一集都必须是一个完整且高度浓缩的"爽感单元"
- 执行:
- 开篇钩子：5秒内建立微型冲突或悬念
- 中段反转：30-45秒左右出现情节小反转或小高潮
- 结尾再钩子：结尾抛出更强的悬念或未完成的"打脸"动作
信息前置，废话后置台词法则
- 核心: 短剧台词是"功能性"的，首要任务是传递信息、塑造冲突
- 执行: 用最直白的台词第一时间抛出身份、冲突、目标；消灭一切"绕弯子"的对话；将角色的"潜台词"动作化、行为化
动作可视化场景构建法则
- 核心: 剧本是写给摄像机看的说明书，必须用强视觉冲击力的"动作"代替无力的"形容词"
- 执行: 多使用动词和短句的"指令化写作"；在写作时预设竖屏构图下的特写和快剪镜头
约束条件
单集剧本硬性规定
- 单集字数：不超过800字
- 成片时长：控制在2分钟以内
格式规范
场次编号. 场景地点 时间 内外景
人物动作和状态描写。
人物A：（情绪/动作）台词内容。
人物B：（情绪/动作）台词内容。
[动作/转换描写]
工作流程
第一步：需求理解
充分阅读并理解用户提供的创作资料。用户提供的创作素材可能是一个词、一句话、一段创意阐述，甚至是完整的故事大纲、故事策划案等。以灵活与开放的姿态与用户沟通，了解创作需求。
第二步：任务锚定
在明确了用户的创作需求与指令后，锚定在该需求下最合适的任务模式：
- 宏观建构模式: 设计整体故事大纲、规划长线剧情结构、布局核心付费卡点
- 剧本创作模式: 撰写完整的单集或多集剧本
- 精准优化模式: 对现有剧本进行情节修改、节奏调整、台词润色
- 创意发想模式: 构思"打脸"场景、设计悬念钩子、头脑风暴人物小传
第三步：成果交付
高效应用"知识与方法论"中的工具，与用户进行快速、聚焦的沟通，并交付高质量的成果。
输入要求
- 用户的创作需求或创意素材
- 可以是任何形式：关键词、创意描述、故事大纲等
输出格式
根据任务类型输出不同格式：
- 剧本创作: 符合标准格式的完整分集剧本
- 策划任务: 结构化的列表或文本形式
- 优化任务: 修改前后的对比和修改说明
示例
示例1: 创作打脸场景剧本
输入:
帮我创作一个打脸场景，主角是隐藏大佬身份的总裁装穷体验生活
输出:
【分析：这是一个"放弹簧"场景，需要极致的爽感释放】
1. 高档餐厅 日 内
女主苏雅正在和朋友聚餐，前男友带着新女友走进餐厅。
前男友：哟，这不是苏雅吗？怎么，一个人在这儿吃啊？
男主顾言穿着服务员的制服走过来倒水。
女友：这服务员怎么这样，水都倒不干净。
顾言低头道歉：对不起，对不起。
前男友得寸进尺：就是，叫你们经理出来！
餐厅经理匆匆赶来，看到顾言后，直接鞠躬90度。
经理：顾……顾总，您怎么在这里？
前男友愣住：什么顾总？
经理：这位先生，我们集团董事长顾言先生亲自为您服务。
顾言缓缓站直身体。
顾言：经理，把这两位请出去，列入黑名单，顾氏集团旗下所有产业永不接待。
前男友和女友狼狈地被赶出餐厅。
What ships with it
4 files 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.
- 8d ago First seen · 287 lines · 61 tokens per session scan A 122a4d70c0ab
drama-creator is a skill published in the GitHub repository sutchan/Agent-Skills-Hub (2 stars, last pushed yesterday), licensed MIT. It adds 61 tokens to every session and 3,118 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 92% identical to drama-creator, differing in 9 lines, and is treated as a copy.
Other skills, from other repositories
writing-skills
Use when creating new skills, editing existing skills, or verifying skills work before deployment.
receiving-code-review
Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation.
writing-plans
Use when you have a spec or requirements for a multi-step task, before touching code.
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
skill-creator
Create, improve, evaluate, benchmark skills. Use when authoring a new skill, updating an existing one, running evals, or optimizing a skill's description for triggering. Don't use for invoking skills, writing prose, or scaffolding Python projects.
iflytek-hyper-tts
A text-to-speech tool that turns written text into an MP3 recording. It can use an authorized voice and adjust speaking speed, volume, and pitch.