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 zenstory-ai/oh-story-dsh --skill short-drama-developgit clone --depth 1 https://github.com/zenstory-ai/oh-story-dshWrote 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/zenstory-ai/oh-story-dsh/short-drama-develop)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-develop"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-develop/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/zenstory-ai/oh-story-dsh/short-drama-develop"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-develop.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 | $0.00195 | $0.02765 |
| Opus 5 | $0.00097 | $0.01383 |
| Sonnet 5 | $0.00039 | $0.00553 |
| Haiku 4.5 | $0.00019 | $0.00277 |
Grade A, and why
short-drama-develop 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 13d 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
100% identical to short-drama-develop — 0 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 — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.
短剧开发
把创作者的意图变成能持续制造选择、代价与状态变化的故事系统。保留创作者的题材、结局和尺度选择；不要把流行套路当成剧情答案。
Quick Start
离线验证多集整稿的精确索引、切片和源文件变更检测：
python3 {技能目录}/scripts/selftest.py
python3 {技能目录}/scripts/episode_intake.py index <多集整稿> --out <episode-intake-index.json>
开始前
本技能可独立安装和执行。先读取用户明确提供的材料与本任务直接输入；若当前目录是
short-drama 项目且项目工具可用，可以读取 status 并使用其发布生命周期，但缺少 core
或任何其他技能都不是开发工作的阻断条件。阶段契约 给出
本阶段边界、制作形态输入与规则表，无需读取其他技能的文件。
先判断入口
- 只有想法、题材或情绪目标：完成方向探索，再建立创作简报与故事引擎。
- 已有梗概、小说、改编材料或系列笔记：保存来源并先列出已承诺事实、可改范围、 来源片段与待确认项。长材料先做语义分段、功能账本和候选分集，不用正则人名/名词命中 直接发布剧集或资产；不要偷换原意。
- 方向已定，只需规划分集：读取既有简报与引擎，直接制作或修订分集地图。
- 已有单集剧本：不要为了流程完整而虚构开发材料。写/改剧本交给
$short-drama-write；拆资产或后续制作可从相应技能直接进入。 - 已有多集整稿，要生成或补分集地图：保留原文件，只加载 多集整稿接入与断点续跑。让 Agent 按文件实际结构决定 边界与本轮批次；工具只做精确索引、单集切片、校验和续跑，不代写创作判断。
信息足够时直接工作。只有会改变主角、冲突引擎、结局承诺或改编边界的缺口才需要提问。
每次执行
1. 锁定创作者契约
读取创作者输入和已接受文件，区分：
- 不可改的事实、主题、角色与结局承诺；
- 可探索的空白；
- 形式约束与制作边界；
- 目标观众反复能获得的情绪、信息或权力回报。
新项目复制 creative-brief.md。若改动已接受事实，先展示语义差异与下游影响，不直接覆盖。
2. 探索真正不同的方向
方向未定时，提出少量机制不同的候选：改变主角策略、对抗来源、代价或持续冲突方式，而不只是换标题、职业和措辞。方向明确时直接深化，不为凑选项制造伪差异。
每个候选都说明：戏剧承诺、主角追求、对抗机制、反复回报、可升级的状态、长线终止条件、主要制作负担。让创作者选择或组合，并记录取舍理由；未选方案不进入既定事实。
需要完整方法时读取 story-craft.md。题材已经确定时，可从 genre-cards.md 按索引取一张题材卡，用来校准该题材更常用的 压力来源、场面颗粒与制作负担；它是可被创作者一句话覆盖的参考，不替代方向选择，也不进入交付物。
若设定里主角带着一段已经发生过的经历，或获得了一套外部授权的能力，那是叠加在题材之上的 前提装置，另读 premise-devices.md——装置取消阻力， 必须先给它边界与代价。装置不替代题材卡，也不为它单独建题材。
3. 建立故事引擎
复制 story-engine.md，写清：
- 压力如何出现，主角通常如何应对；
- 对手或系统如何反制，主角为何不能轻易退出；
- 每轮冲突改变什么，而不是怎样重复得更响；
- 人物各自的目标、筹码、底线和关系压力；
- 哪种人物转变或事实揭开会终结这个引擎；
- 视觉、声音、场景规模和内容边界。
连续剧、长篇改编或人物纵向变化较重时，再读取 serial-character-and-memory.md：先建立只供 作者决策的前史储备，选择旧策略开始付出代价的叙事切入窗口，再记录人物被捍卫的 信念、压力测试、信息权限和跨集记忆。不要把前史储备直接倒进首集对白。
What ships with it
32 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.
- agents/openai.yaml 322 B
- assets/adaptation-map.example.jsonl 902 B
- assets/creative-brief.md 4.9 KB
- assets/episode-map.jsonl 1.6 KB
- assets/story-engine.md 7.3 KB
- references/adaptation-craft.md 12 KB
- references/creative-reference-intake.md 3.3 KB
- references/director-brief-craft.md 6.6 KB
- references/episode-design.md 23 KB
- references/genre-and-hook-playbook.md 18 KB
- references/genre-cards.md 7.2 KB
- references/genre-cards/亲子隐秘.md 6.7 KB
- references/genre-cards/仙侠修真.md 4.3 KB
- references/genre-cards/动作任务.md 4.5 KB
- references/genre-cards/古装权谋.md 4.3 KB
- references/genre-cards/复仇打脸.md 5.2 KB
- references/genre-cards/家庭关系.md 4.1 KB
- references/genre-cards/悬疑规则.md 4.3 KB
- references/genre-cards/生活流.md 3.9 KB
- references/genre-cards/破镜重圆.md 6.8 KB
- references/genre-cards/职场喜剧.md 4.0 KB
- references/genre-cards/豪门婚恋.md 4.6 KB
- references/genre-cards/身份错位.md 4.0 KB
- references/mechanism-loop.md 17 KB
- references/multi-episode-intake.md 6.8 KB
- references/premise-devices.md 14 KB
- references/reveal-reversal-payoff.md 4.5 KB
- references/serial-character-and-memory.md 15 KB
- references/stage-contract.md 9.7 KB
- references/story-craft.md 18 KB
- scripts/episode_intake.py 27 KB runs code
- scripts/selftest.py 1.5 KB runs code
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.
- 13d ago First seen · 158 lines · 195 tokens per session scan A 98e537c3114f
short-drama-develop is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (338 stars, last pushed yesterday), licensed MIT. It adds 195 tokens to every session and 2,765 once invoked, about $0.0010 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to short-drama-develop, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
story-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
story-deslop
A writing editor for Chinese web novels that detects writing patterns often associated with AI-generated text and makes the prose feel more natural.
story-short-analyze
A Chinese-language guide for analysing short popular web fiction, such as stories published on 番茄, 故事会, or 知乎盐选. It examines the core premise, plot structure, emotional arc, twists, writing techniques, and reader appeal.
browser-cdp
Use this skill when you need to control a Chrome browser via CDP (Chrome DevTools Protocol) to reuse existing login sessions. Covers: launching Chrome in debug mode, opening URLs, waiting for page load, evaluating JavaScript, taking snapshots, and extracting auth tokens. Trigger phrases: browser automation, CDP…
novel-language-style
A guide to choosing and controlling the writing style of online fiction. It covers narration, word choice, figurative language, dialogue, and techniques for making scenes easier to picture.
style-fingerprint
A Chinese-language system for measuring the writing style of a novel from a sample of its text. It records patterns in viewpoint, timing, sentences, word choice, dialogue, description, themes, and chapter structure.