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 | $0.02955 |
| Opus 5.5 | $0.00078 | $0.01182 |
| Sonnet 5.5 | $0.00039 | $0.00591 |
| Haiku 4.5 | $0.00019 | $0.00296 |
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 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.
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 — 164 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，保留创作者对题材、结局和尺度的选择。流行套路只能作为候选方法。
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的直接输入；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。缺少 core
或其他技能时，仍可基于现有输入完成开发。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。
需要深化戏剧承诺或冲突机制时，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
35 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 316 B
- assets/adaptation-map.example.jsonl 1.2 KB
- assets/creative-brief.md 5.9 KB
- assets/episode-map.jsonl 1.6 KB
- assets/story-engine.md 7.3 KB
- references/adaptation-craft.md 17 KB
- references/creative-reference-intake.md 3.3 KB
- references/director-brief-craft.md 6.5 KB
- references/episode-design.md 30 KB
- references/genre-and-hook-playbook.md 18 KB
- references/genre-cards.md 7.6 KB
- references/genre-cards/亲子隐秘.md 6.7 KB
- references/genre-cards/仙侠修真.md 4.4 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 4.0 KB
- references/genre-cards/破镜重圆.md 6.8 KB
- references/genre-cards/系统流.md 4.4 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/genre-cards/逆袭.md 3.8 KB
- references/genre-cards/重生穿越.md 4.1 KB
- references/mechanism-loop.md 17 KB
- references/multi-episode-intake.md 7.0 KB
- references/premise-devices.md 14 KB
- references/reveal-reversal-payoff.md 4.6 KB
- references/serial-character-and-memory.md 15 KB
- references/stage-contract.md 13 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.
- 12d ago Changed 8fda1d827d06
- 29d ago Changed · +6 lines ef05a00f6ba8
- 1mo 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 (629 stars, last pushed today), licensed MIT. It adds 195 tokens to every session and 2,955 once invoked, about $0.0008 per session on Opus 5.5. 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-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-long-analyze
A long-form fiction analysis workflow for breaking down a novel’s opening chapters, characters, pacing, turning points, relationships, and overall structure.
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…
workflow-manager
A writing workflow tracker for chapter-based projects. It records whether each chapter is being assembled, drafted, reviewed, confirmed, polished, or archived.
review-chapter
A six-part review of a manuscript chapter. It compares the chapter with the outline and reports quality, coverage, review status, and problems supported by evidence from the text.
revise-span
A revision workflow for changing selected passages in a manuscript. It shows the original and proposed text, then applies changes only after the author confirms them.