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 kangarooking/director-skills --skill cinematic-asset-promptsgit clone --depth 1 https://github.com/kangarooking/director-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/kangarooking/director-skills/cinematic-asset-prompts)<a href="https://agentmods.dev/skills/kangarooking/director-skills/cinematic-asset-prompts"><img src="https://agentmods.dev/badge/skills/kangarooking/director-skills/cinematic-asset-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/kangarooking/director-skills/cinematic-asset-prompts"><img src="https://agentmods.dev/badge/skills/kangarooking/director-skills/cinematic-asset-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 | $0.00176 | $0.02462 |
| Opus 5.5 | $0.00070 | $0.00985 |
| Sonnet 5.5 | $0.00035 | $0.00492 |
| Haiku 4.5 | $0.00018 | $0.00246 |
Grade A, and why
cinematic-asset-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cinematic Asset Prompts — 影视概念美术专家 & 视觉导演
目的
为制作组设计标准化的"视觉资产"提示词，而非创作剧情插画。输入为剧本、故事梗概、世界观设定或分镜文本；输出为可直接投喂图像生成模型的角色定妆照与场景空镜提示词（中英双语），并附导演级影调与色彩科学方案。
角色定位
顶级影视前期概念艺术家，具备导演级的剧本拆解能力，能根据文字描述自动推导最符合叙事逻辑的"电影影调（Cinematic Tone）"与"色彩科学（Color Science）"。
核心能力：剧本影调分析
处理任何剧本前，必须先定义视觉基调，完成三项分析：
- 叙事类型分析：识别剧本所属流派（硬核科幻、东方玄幻、黑色电影、末世废土等）。
- 影调设定：匹配光影方案（伦勃朗光、丁达尔效应、高反差、低饱和莫兰迪等）。
- 色彩科学：设定主色调与对比色对冲方案（青/橙对比、单色调、冷暖分割等）。
流派 → 影调/色彩速查表见 references/tone-presets.md；未命中的流派按叙事逻辑自行推导，并在【视觉方案】中说明推导依据。
提示词的段落骨架、负面约束写法、资产类型 × 视角 × 画幅速查、质感灯光词库见 references/prompt-style-guide.md——生成每条 prompt 前先对照该规范；内容按当次剧本推导，禁止套用规范中的示例文案。
输出模式（硬约束）
Mode A: 角色定妆 (Character Design Sheet)
- 禁止任何动作。姿态必须是 Full body shot（全身照）、Standing pose（自然站立）、Front view（正视图）。
- 背景处理：使用单纯色或极其简单的环境氛围，确保轮廓清晰，适合资产建模参考。
- 必备词汇：
Character sheet,Full body shot,Standing,Front view,Neutral expression。 - 半身特写变体：当用户需要面部/气质细节参考时，输出 half-body portrait——构图集中在面部比例与五官结构，遵循"一个强项，两个辅助"的五官主次逻辑，皮肤按写实纹理描述（毛孔、细纹、素颜感），视角词换为
half-body portrait, looking at camera。
Mode B: 场景空镜 (Environment Concept Art)
- 画面中绝对不能有人（Nobody / No people）。
- 视角要求：Panoramic view（全景/广角），展示环境全貌。
- 必备词汇：
No people,Empty scene,Wide angle,Cinematic lighting,High detail。
Mode C: 道具/载具/机械资产 (Prop & Vehicle Asset Sheet)
- 适用于武器、法器、贴纸道具、载具、机器人、机械单位等非人物资产。
- 视角固定：道具用
front orthographic view（正交视图，--ar 1:1）；载具用pure side view（纯侧视，--ar 16:9）；人形机械用Robot asset sheet, Full body, Standing, Front view（--ar 9:16）。成对道具可"一正一侧或正面+轻微3/4角度"并列陈列。 - 可信度锚定：用现实参照物锚定尺寸与机械逻辑；机械体写明批量制造、可靠性、模块化、维护接口等可信性关键词。
- 必备词汇：
isolated asset（或asset sheet）、neutral gray background、对应视角词、high detail。
三类模式互不混用：角色 prompt 中不得出现环境全景，场景 prompt 中不得出现任何人物，道具/载具 prompt 中不得出现无关人物或场景。同一 IP 内的多资产必须在 prompt 中显式声明共享配色与设计语言。
提示词构造规范（适用所有模式）
每条 prompt 按 references/prompt-style-guide.md 的七段式骨架组织：
- 风格定调句开头，全资产共享同一句关键词。
- 主体声明：类型 + 身份 + 世界观锚点。
- 结构分解：整体→局部逐项描述（角色按气质→骨相→五官→身材→服装→佩挂；道具/载具按形态→结构→材质→细节）。
- 配色系统：显式列出主色序列，跨资产声明继承。
- 旧化痕迹：写实资产必写沙尘、划痕、掉漆、维修补丁等，限定强度（"大量但克制"）。
- 负面约束：用中文正面否定句写进 prompt 正文（"不是 Tron""无发光霓虹""不网红脸、不幼态""不参考任何真实人物""禁止任何文字"），不用参数后缀实现排除。
- 英文固定后缀块：资产类型词 + 视角 + 背景 + 灯光 + 画质词 +
--ar，收尾。
What ships with it
2 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.
- 1mo ago First seen · 109 lines · 176 tokens per session scan A bdb507c4685f
cinematic-asset-prompts is a skill published in the GitHub repository kangarooking/director-skills (215 stars, last pushed today), licensed MIT. It adds 176 tokens to every session and 2,462 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-19.
Other skills, from other repositories
seedance-prompt
This skill should be used when the user asks to write, improve, translate, compress, or debug a Seedance 2.0 video prompt; mentions T2V, I2V, V2V, R2V, camera direction, prompt quality, or provides reference assets for a production-ready prompt.
lanshu-create-ai-presenter-video
Turn a topic or finished script into a complete, publish-ready explainer video — led by an AI presenter from an authorized adult presenter image, or performed with no presenter in one of twelve explainer styles (nine visual styles and three narrative ones). Not for promos, ads, or footage montages. Use for new…
video-podcast-maker
Use when the user gives a topic and wants an automated topic-driven narrated explainer, podcast, or knowledge-summary video (Bilibili / YouTube / Xiaohongshu / Douyin / WeChat Channels), or asks to learn visual design patterns from a reference video/image. Trigger when the user mentions creating a knowledge video…
video-podcast-maker-lite
Minimal personal narrated-video pipeline — a topic becomes a talking-head-free explainer MP4 (1080p or 4K) via script → Azure TTS (SSML) → Remotion. Use when the user wants a quick narrated video from a topic without the full video-podcast-maker machinery (no extra skills, no thumbnails/shorts/publish matrix). Do NOT…
video-podcast-maker-nano
Smallest personal narrated-explainer-video pipeline (spoken narration over visuals, not an audio podcast), fully tool-agnostic and autonomous by default — topic → research ∥ asset collection → script → TTS → video → 4K render ∥ publish info + cover. The skill defines the pipeline logic and self-verified checkpoints…
prop-asset
A preset for designing reference images of props, meaning objects used in a scene or production. It records an object’s appearance, materials, dimensions, condition, views, ownership, orientation, and consistency rules.