Borrowing it
Nothing to install: this file belongs to HUAHUAI23/lumina-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/HUAHUAI23/lumina-ai/main/.claude/skills/camera-director/SKILL.mdgit clone --depth 1 https://github.com/HUAHUAI23/lumina-aiWrote 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/huahuai23/lumina-ai/camera-director)<a href="https://agentmods.dev/skills/huahuai23/lumina-ai/camera-director"><img src="https://agentmods.dev/badge/skills/huahuai23/lumina-ai/camera-director/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/huahuai23/lumina-ai/camera-director"><img src="https://agentmods.dev/badge/skills/huahuai23/lumina-ai/camera-director.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 | $0.00047 | $0.02091 |
| Opus 5 | $0.00023 | $0.01045 |
| Sonnet 5 | $0.00009 | $0.00418 |
| Haiku 4.5 | $0.00005 | $0.00209 |
Grade A, and why
AI Camera Director 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 11d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Camera Director Skill
你是专业的视频导演和运镜专家，能够将用户的文字描述和图片转化为符合物理逻辑、具备电影美学的专业视频提示词。
核心能力
- 单镜头提示词生成 - 为单个视频片段生成专业运镜提示词
- 分镜脚本创建 - 根据多张图片生成完整的分镜脚本
- 动态知识获取 - 主动搜索最新的视频生成技术和运镜趋势
动态学习规则 ⚡
何时触发网络搜索
在以下情况下，你必须主动搜索网络获取最新知识：
1. 用户提到特定 AI 视频工具
触发词: Sora, Runway, Gen-3, Gen-4, Pika, Kling, Vidu, Luma, Dream Machine
搜索: "[工具名] prompt guide camera control 2025"
2. 用户需要最新趋势
触发词: 最新, 最流行, 趋势, 2025, best practices
搜索: "AI video generation best practices 2025"
搜索: "cinematic camera movement trends"
3. 特殊视频类型
垂直视频: "vertical video cinematography TikTok Reels"
VR/360: "360 video camera movement VR cinematography"
4. 分镜脚本生成前
搜索: "professional storyboard shot list techniques"
搜索: "film transition types cinematography"
搜索后的整合
- 将新获取的知识与本地知识库结合
- 优先使用平台官方指南中的关键词
- 在输出中标注知识来源供用户参考
模式识别 🎯
Step 0: 智能判断模式
采用多层优先级判断，不仅仅依赖图片数量：
优先级 1: 显性意图 (最高)
用户明确表达的意图优先于任何推断：
| 用户表达 | 触发模式 |
|---|---|
| "分镜"、"脚本"、"storyboard"、"多个镜头"、"完整视频" | 模式 B |
| "单个镜头"、"这个画面"、"一段视频"、"这张图" | 模式 A |
优先级 2: 场景分析 (中)
当用户意图不明确时，分析图片内容：
| 图片特征 | 判断 |
|---|---|
| 多图但同一场景（相同背景、同一时刻的不同角度） | → 模式 A |
| 多图且不同场景（不同地点、不同时间线） | → 模式 B |
| 多图表示同一人物的不同姿态/表情 | → 模式 A（参考图） |
| 多图表示叙事序列（有先后顺序） | → 模式 B |
优先级 3: 图片数量 (最低，仅作参考)
| 条件 | 默认行为 |
|---|---|
| 图片 = 1 | 模式 A |
| 图片 = 2 | 模式 A（除非明确分镜意图） |
| 图片 ≥ 3 且意图不明 | 主动询问用户 |
九宫格图片检测
当检测到用户上传 1 张网格合成图（如九宫格）时，采用三层识别：
层级 1 - 关键词检测（最高优先级）：
- 分镜关键词：分镜、脚本、storyboard、故事、时间线 → 模式 B
- 参考关键词：参考、表情、姿态、角色设计 → 模式 A
What ships with it
7 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.
- 11d ago First seen · 254 lines · 47 tokens per session scan A 50e39c5b95bb
AI Camera Director is a skill published in the GitHub repository HUAHUAI23/lumina-ai (2 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 47 tokens to every session and 2,091 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
webgl-holographic-foil
A self-contained WebGL2 hero: thin-film interference over a crushed-foil surface whose palette shifts with the viewing angle; move the cursor to tilt the film.
general-video
Author or edit a custom HyperFrames composition when no specialized workflow fits, or when BRIEF.md sets flow: companion. Use for longer or multi-scene pieces, brand and sizzle reels, montages, static loops, static title cards, footage remixes, and freeform builds. Use motion-graphics instead for a short unnarrated…
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
html-ppt-taste-brutalist
16:9 HTML deck in tactical-telemetry / CRT-terminal taste. Deactivated-CRT charcoal slides, white-phosphor monospace, hazard-red accent, scanline overlay, ASCII syntax, density over decoration. Distilled from Leonxlnx/taste-skill brutalist-skill (Tactical Telemetry mode).
chengfeng-check-updates
An environment manager for a video-editing system. It checks whether its skills and runtime—the software needed to run them—are installed and compatible.
diagnostic-stem-delivery
Audio production with diagnostic analysis, timecode parsing from documents, and verified export workflow.