zenstory-ai/drama-skills is a collection of AI coding-agent skills for producing short dramas and animated stories from an idea or source material, covering scripts, visual assets, storyboards, and image, video, and audio prompts. It is intended for screenwriters, animation studios, and directors using Claude Code, Codex, or other agents that support the Agent Skill format. The catalogue skills are the project's own workflow for planning, reviewing, and producing these projects.
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/drama-skills --skill short-drama-producegit clone --depth 1 https://github.com/zenstory-ai/drama-skillsWrote 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/drama-skills/short-drama-produce)<a href="https://agentmods.dev/skills/zenstory-ai/drama-skills/short-drama-produce"><img src="https://agentmods.dev/badge/skills/zenstory-ai/drama-skills/short-drama-produce/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/drama-skills/short-drama-produce"><img src="https://agentmods.dev/badge/skills/zenstory-ai/drama-skills/short-drama-produce.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00145 | $0.03755 |
| Opus 5 | $0.00072 | $0.01878 |
| Sonnet 5 | $0.00029 | $0.00751 |
| Haiku 4.5 | $0.00015 | $0.00376 |
Grade A, and why
short-drama-produce 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 today.
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.
Copies of this mod
1 near-identical copy found in the catalogue:
- short-drama-produce — 100% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.
确认后生产
本技能只负责把已经写好的生产规格安全送到运行环境配置的 adapter。图片提示词仍归
$short-drama-image-prompts，视频提示词归 $short-drama-video-prompts，台词与录音表归
$short-drama-write，声音身份归 $short-drama-assets。
Quick Start
只在用户明确要求实际生成后，从当前 图片提示词.md、分镜.md 或 视频提示词.md 中
取出本次提示词，建立一个有边界的运行 job。creator-first job 的 source 必须指向拥有这条提示词的
当前 Markdown，source_entry 必须点名该文档允许的二级标题：图片提示词.md 用 IMG-*，
视频提示词.md 用 MOTION-*，分镜.md 用 SHOT-*（modality 为 image，正文取该镜的
### 冻结关键帧提示词）。此选择器只提取首帧；尾帧需先由图片提示词阶段建立独立 IMG-* 状态图条目，
再从 图片提示词.md 准备 image job。创作者也可以提供已有起始帧——
在自己的工具里出图再放进项目同样成立，图片始终不进项目时走分镜的 PLAN-...；
产出落在 剧集/<EP>/制作成果/images/ 后，分镜 owner 才能把它绑成 用途：起始帧 的 REF-...。存在真实参考图时，
还必须逐张填写 reference_bindings 的槽位、顺序、路径、中文名、用途以及允许/禁止控制范围；
内置视频 adapter 把这里的 用途 字段读成供应商自己的 role，只接受它公布的取值
（MiniMax 为 first_frame/last_frame/reference_image/reference_video/reference_audio，
Seedance 为三个 reference_*）；带参考图却没有绑定的 job 会直接失败，不替它猜一个 role。
本地图片由内置 adapter 按 base64 data URI 直接送出，不需要自建上传服务。
条目的「输入参考图」写成 PLAN-... 时，那些图片在创作者自己的工具里，项目内没有文件可送：
prepare 直接失败并说明先把真实文件放进项目、改写成 REF-...，不拿计划当输入，也不静默丢掉参考。
references 可以省略并由绑定顺序生成，也可以作为相同顺序的显式镜像。输出放在
剧集/<EP>/制作成果/；这个 job 是生产工具的临时输入，不是第六份创作文档：
python3 {技能目录}/scripts/production_tool.py prepare <project> --job <临时-job.json>
先展示 prepare 的完整预览；此时不会调用供应商。
硬闸门
每次生产都必须经过以下四步，顺序不可合并：
- 建立一个有边界的 job：一种 modality、明确数量、完整 prompt/spec、参考文件、参数、输出路径和 adapter profile。
- 运行
prepare，把返回的完整预览展示给创作者，尤其是数量、prompt、source entry、 reference bindings、references、outputs、overwrite 与 adapter。creator-first job 会在这一步机械核对 所选标题里的可复制提示词，以及参考图槽位、顺序、路径、中文名和控制边界；任一漂移都 fail closed。 - 等创作者在看到这份预览之后明确确认。只有明确同意这项当前任务，才运行
confirm； “继续”“都做完”“预算没问题”、上游内容已接受或之前确认过另一版，都不算本次生产确认。 - 运行
run。它会在启动 adapter 前消费一次确认；成功或失败后再次执行都必须重新确认， 防止失败重试意外产生第二笔费用。
job、prompt、参数、输出路径或直接输入任一变化，旧确认立即失效。不得代替创作者填写确认。 当前已确认 job 是本轮唯一工作单元；运行结束后回报结果并交还控制权，不自动准备下一批或启动审查。
分镜.md 的「输入参考图」路径只是创作阶段的可读依据与使用意图，不是生产输入快照。进入生产时，
creator-first job 必须从 图片提示词.md 或 视频提示词.md 的对应条目建立绑定；prepare 展示的
reference_bindings、references 与已确认 job 才是本次 adapter 实际读取哪些文件字节、各自允许
影响什么的权威。非 creator 的结构化规格可不填 source_entry/reference_bindings，继续只使用显式
references；但新的 image/video job 只要 source 指向 canonical 图片提示词.md 或
视频提示词.md 就强制使用对应 selector，不能靠省略字段降级绕过。升级前已经 prepare 并落盘的
旧 job 仍可按原指纹读取。
新生产结果不自动回填或刷新分镜；需要把它改为后续输入时，由分镜 owner 修订文档，再建立新 job
并重新预览、确认。
What ships with it
11 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 288 B
- references/adapter-contract.md 11 KB
- references/providers/gpt-image-2.md 1.3 KB
- references/providers/minimax-h3-video.md 5.4 KB
- references/providers/minimax-music.md 1.3 KB
- references/providers/minimax-speech.md 2.1 KB
- references/providers/seedance.md 3.9 KB
- scripts/fixture_adapter.py 2.7 KB runs code
- scripts/production_tool.py 86 KB runs code
- scripts/provider_adapters.py 69 KB runs code
- scripts/selftest.py 4.0 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.
- today Changed · +4 lines 90716253be3e
- yesterday Changed · +21 lines 8e664f0a3a59
- 7d ago Changed · +3 lines 9eb35a905f94
- 10d ago Changed · +17 lines e9f3678b49a1
- 13d ago First seen · 139 lines · 145 tokens per session scan A e52a4775fe70
short-drama-produce is a skill published in the GitHub repository zenstory-ai/drama-skills (1,798 stars, last pushed today), licensed MIT. It adds 145 tokens to every session and 3,755 once invoked, about $0.0007 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 2026-08-30.
Other skills, from other repositories
cinematic-director
A prompt generator for image models that turns a scene description into an English cinematic photography prompt and a negative prompt, which lists details to avoid.
drama-skills
A collection of AI skills for creating short dramas and animated comics, from an idea or long source material to scripts and visual-production instructions. It covers episode scripts, story assets, image prompts, storyboard frames, and video prompts.
happiness-skill
A Chinese-language guide to happiness based on reducing unmet wants, focusing on the present, and treating happiness as a trainable skill.
aesthetic-audit
A commercial visual and user-experience review workflow for websites, product pages, landing pages, and visual assets. It examines clarity, hierarchy, spacing, typography, color, trust signals, conversion paths, and mobile behavior.
setup-matt-pocock-skills
A setup skill that configures engineering skills for a repository, including its issue tracker, labels, and documentation layout. A repository is the project folder managed by version control.
tapcanvas-prompt-specialists
A set of role and output rules for specialists that create image prompts, video prompts, and pacing reviews in TapCanvas. It explains what evidence to pass to each specialist and what results they should return.