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-image-promptsgit 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-image-prompts)<a href="https://agentmods.dev/skills/zenstory-ai/oh-story-dsh/short-drama-image-prompts"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-image-prompts/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-image-prompts"><img src="https://agentmods.dev/badge/skills/zenstory-ai/oh-story-dsh/short-drama-image-prompts.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 | $0.00086 | $0.01137 |
| Opus 5 | $0.00043 | $0.00568 |
| Sonnet 5 | $0.00017 | $0.00227 |
| Haiku 4.5 | $0.00009 | $0.00114 |
Grade A, and why
short-drama-image-prompts 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 7d 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-image-prompts — 2 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.
What it actually says
短剧资产图片提示词
把视觉事实写成可复用、可修改、可直接复制的角色板、场景板、道具板或状态图提示词，统一保存到
剧集/<EP>/图片提示词.md。每项用 IMG-... 标题，正文放在 ### 可复制提示词 引用块。
IMG-... 只是该提示词条目的稳定 ID，不声明图片已生成或可用；实际图片只能来自创作者已提供的输入，或经确认后的生产结果。
Quick Start
用 $short-drama-image-prompts 为 EP001 已确定的人物、地点和道具写可直接复制的图片提示词
入口
有当前视觉设定即可直接开始；剧本只在提示词需要确认剧情状态时读取。Look Development 是可选分支。 先确认用途：身份板、造型/状态变体、地点板、道具板、组合 production sheet 或比较风格帧。
创作者可读说明跟随项目语言；可复制正文跟随 short-drama.json#/format/prompt_language。没有
short-drama.json 时正文默认
使用 en，并在同一任务中保持一致；不能从创作者说明语言推断提示词语言。
工作流
- 锁定这一张图要固定的身份、状态、空间或比较变量。
- 只读所需资产事实、视觉方向、负面约束和已提供参考图。
- 按“主体与身份锚点 → 当前变体 → 构图/视角 → 光色/材质 → 背景边界 → 禁止项”写正文。
- 每张参考只控制身份、造型、地理、构图或风格中的明确部分，并在
REF-...槽位里写出封闭词表中的用途。 - 检查身份与变体、文字政策、视角和光线是否冲突。
- 用户要全部资产就完成全部，资产组只是内部批次。
提示词要求
- 开头先写对象和用途，不用风格词淹没身份。
- 只包含当前图能同时满足的要求；多视图/状态对照写清版面关系。
- 保留稳定识别锚点，变体只改允许变化的部分。
- 被《视觉设定.md》连续性锁点名的条目，锁面原样出现在可复制正文里，让这张参考图本身就把跨镜事实定住。
- 避免无验证作用的质量词堆砌。
- 可见文字、logo、水印、界面和字幕明确允许或禁止。
- 正文可直接复制，不含占位符、流程说明、文件路径或 QA 结论。
按需知识
默认只读本 SKILL 和当前视觉设定。遇到对应问题时只打开一份：
- 阶段边界与规则分级：阶段契约
- 普通单图的最小配方：通用配方
- 人物身份板与造型一致性：人物与造型
- 地点地理、视角和光线：地点板
- 功能道具、尺度、材质与文字：道具板
- 造型和状态变体：造型与状态变体
- 多对象组合板：Production Sheet 配方
- 比较视觉方向的代表帧：Lookdev 风格帧
- 局部修改和 preserve set：定点修改
- 完成前的可生成性检查：审查与示例
完成与投产
每个点名对象都有明确用途、可复制正文、参考边界和禁止项，且相互不矛盾，即完成。本次请求同时
修改图片提示词与分镜时，当轮刷新受影响镜头的「图片提示词项」，不另建对账产物。实际生成必须
转 $short-drama-produce，展示精确任务并取得显式确认；本技能不调用外部服务。
五份创作文档齐备后，可转 $short-drama 对跨文档结构做一次机械核对；内容质量仍由创作者审查。
安装维护
只有安装、升级或排障时运行 python3 scripts/selftest.py。
What ships with it
18 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 301 B
- assets/image-prompt-spec.jsonl.md 5.6 KB
- assets/image-prompts.md 2.5 KB
- assets/lookdev-frame-spec.jsonl.md 4.0 KB
- assets/lookdev-prompts.md 1.8 KB
- examples/minimal-image-prompt-specs.jsonl 2.3 KB
- references/character-and-look.md 8.3 KB
- references/common-recipe.md 15 KB
- references/edit-and-revision.md 5.1 KB
- references/location-plate.md 8.8 KB
- references/look-and-state-variant.md 5.3 KB
- references/lookdev-frame.md 2.4 KB
- references/production-sheet-recipes.md 11 KB
- references/prop-plate.md 6.7 KB
- references/review-and-fixtures.md 5.2 KB
- references/stage-contract.md 3.6 KB
- scripts/image_prompt_check.py 18 KB runs code
- scripts/selftest.py 3.8 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.
- 7d ago Changed · +2 lines a3341fc0c556
- 12d ago First seen · 70 lines · 86 tokens per session scan A 1865de783ad4
short-drama-image-prompts is a skill published in the GitHub repository zenstory-ai/oh-story-dsh (338 stars, last pushed today), licensed MIT. It adds 86 tokens to every session and 1,137 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to short-drama-image-prompts, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
ito-compute
Query live GPU inventory, submit an authenticated Itô fixed-rate RFQ, inspect RFQ or procurement status, revoke device credentials, and run explicitly gated node qualification through the separately installed canonical CLI. Use when a user asks to find H100/H200 capacity, request a fixed compute rate, check Itô…
ito-inference
Inspect the availability of model serving on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed serving manifest. Use after ito-compute has booked GPU nodes and the user asks for an OpenAI-compatible endpoint, ito-serve, hosted Kimi, or self-hosted…
ito-training
Inspect the availability of ML training on a completed Itô compute booking and, when the canonical backend becomes available, hand off an explicitly confirmed training manifest. Use after ito-compute has booked GPU nodes and the user wants pre-training, fine-tuning, or RL on that metal. ECC implements no training…
bio-workbench
A set of rules for running reproducible bioinformatics analyses, which study biological data with software. It uses small self-contained scripts, recorded inputs and outputs, environment details, and version history so results can be repeated.
guardian-mcp
Use Guardian MCP tools to monitor, intervene, and analyze ML training. Covers 35 tools across monitoring, checkpoint analysis, recovery, dashboard config, and cross-experiment queries. Use when the user asks about training status, anomalies, checkpoints, experiments, model analysis, or when Guardian MCP server is…
visionary-cli
Analyze images with DeepSeek's vision model via the visionary-server CLI. Use this whenever the user provides an image, photo, screenshot, or document with images - run vision to look at it rather than guessing.