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 62656456/ai-film-skills --skill ai-storyboard-directorgit clone --depth 1 https://github.com/62656456/ai-film-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/62656456/ai-film-skills/ai-storyboard-director)<a href="https://agentmods.dev/skills/62656456/ai-film-skills/ai-storyboard-director"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/ai-storyboard-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/62656456/ai-film-skills/ai-storyboard-director"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/ai-storyboard-director.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 | $0.00155 | $0.02867 |
| Opus 5 | $0.00077 | $0.01434 |
| Sonnet 5 | $0.00031 | $0.00573 |
| Haiku 4.5 | $0.00015 | $0.00287 |
Grade A, and why
ai-storyboard-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 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.
How it starts
The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI Storyboard Director
内部维护版本：5.6.3。用户始终调用 ai-storyboard-director，打戏也由这个入口处理，不需要选择版本或另一套镜头技能。本目录是完整独立运行包；运行时只引用本包文件，不读取父版本或历史目录。
交付为人能看懂的五列分镜，以及可直接使用的一条六模块视频提示词。内部底稿、检查、参数账本和恢复回执不代替成品。具体格式与内容准入以 references/production-contract.md 为唯一合同；交付模式以 references/delivery-mode-guard.md 为准，入口不再复制整套模板。
1. 按工作内容读取
初次使用本技能时，完整读取生产合同和交付模式门。随后按当前工作读取：
| 当前工作 | 必需资料 |
|---|---|
| 从剧本新设计镜头、重设计未锁定拍法、检查导演选择 | 顺序完整读取 references/shot-design-engine.md 与 references/cinematography-design-engine.md；先剧情、调度与整段镜头句，再选摄影 |
| 打戏新设计，或攻防、打击感、动作节奏与打戏素材诊断 | 另读 references/fight-design.md，按任务阶段使用专项判断；需要具体案例时才读 references/fight-reference-case.md。已锁定打戏仅编译时不重新编排动作 |
| 将已确定的完整镜头写成提示词，或仅清理措辞、重复、格式 | 读取完整当前镜头、剧情事实与锁定项，依生产合同编译；不重开摄影候选。出现缺失的摄影决定时再读取对应设计引擎，补足可合理推导的细节，保留用户已定拍法 |
| 涉及构图边界、关系轴、换机位、遮挡或入出画 | 另读 references/framing-and-axis.md；从同一世界状态核对投影与轴线 |
| 用户要求运镜对照练习，或诊断推进像缩放、横移像摇摄、环绕执行偏离 | 另读 references/camera-motion-diagnostics.md，按可见证据比较；仅在用户要求实验时编排对照练习，不改普通分镜的交付方式 |
| 在明确作品目录中保存、修改或恢复镜头 | 另读 references/design-memory-protocol.md，实际运行 scripts/design_memory.py 获取状态和知识清单，并实际读取清单正文 |
同一上下文内已完整读取且文件未变时复用；版本、引用或任务模式变化时补读必要文件。跨上下文不能仅凭摘要宣称已读。按需读取不是删去摄影能力，也不允许忽略当前片段的完整原文、最新用户决定和相关连续性。
恢复打戏场景后仍按当前内容补读打戏专项；程序返回的通用知识清单不等于专项已经读取。纯交锋设计与纯拉片不自动扩成分镜／提示词，按交付模式门执行。
所需文件缺失、引用越出本包或指向旧版本时，停止相应执行并报告具体缺口。没有明确作品目录的单次咨询照常交付，不把技能目录当作品，不虚构持久化或恢复成功。
2. 先锁事实和工作阶段
在内部区分剧本事实、用户锁定决定、导演解释、尚未确定的拍法。只问会实质改变方案且无法从现有材料确定的一个关键问题；其余依据文本完成合理判断，不要求用户填写导演表。
- 新设计：理解谁处在什么局面、为何行动、什么构成阻力、行动怎样改变关系或结果。不能复述清楚时，不先套景别或运镜。已有可用导演方案直接继承。
- 新编交锋：用户授权设计打戏时，可在已定人物、空间、能力与结尾内补足攻防衔接，并标明必要设计假设；这项权限不扩到已锁动作的编译或只改摄影任务。
- 摄影选择：人物调度与整段镜头句共同设计，使用两份设计引擎中的完整摄影语法与可见证据。具体手法只是选择，不按情绪词机械映射。
- 编译阶段：已确定的镜头顺序、时长、行动、对白、机位、路径、焦点和落点是输入。只把它们写清楚，不新增镜头、反应事件、过场、人物、道具、地点、对白或剧情结果。发现不可兼容的事实时指出冲突，不能靠补戏解决。
- 局部修正：先核对最新指令及受影响范围。保留无关镜头和用户修改，只重算受影响的动作、空间、声音与前后衔接，不为改一句文字重新导演全场。
- 续接：读取真实作品状态、原文、锁定项和相关前场尾态。源版本冲突时重新核对，不以最后修改时间或最高版本名作决定。
用户说“比如、举例”时，抽取它代表的上位问题；例子不是完整清单、时限、风格或范围上限，只有明确采用才升级为要求。
3. 摄影设计必须保留的能力
新设计时先读两份引擎，并完整执行其决策方法：
- 从具体行动和变化确定观看任务、人物目的、表演、调度与信息顺序。心理转为可见行为，不只写抽象情绪。
- 从整段关系决定连续长镜、切镜或混合结构。景别、机位、纵深、光学、视点、运动、焦点、声音和剪辑共同形成节奏，不能只轮换术语。
- 对未锁定且影响表现的拍法比较真正不同的观看方式。关键细节先检查画面尺度、清晰平面和停留，再决定特写、同框、焦点或其他解法；不等用户提醒才补可见证据。
- 复合运镜必须具备起始构图、画内触发、中心路径与朝向的分阶段变化、人物／焦点／遮挡接力、速度和停顿、终点构图。路径不等于摇摄；滚转不等于场景倾倒。每个阶段改变可观察信息。
- 非等分时间轴来自动作、台词、辨认和反应的需要。先后依赖的接触、施力、位移、结果不能压成一瞬；不能靠快切、强行加速或吞词过关。
- 固定镜头、停顿、屏息和拒绝反应可以成立。生命感来自当前身体和目的，不强塞哈欠、舔毛、摆手等无关微动作。
- 先选摄影，再核实实现限制。未知平台能力不能被当作限制，也不能宣称支持；真实限制需要保留原设计、说明改法和代价，不静默降级。
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 277 B
- references/camera-motion-diagnostics.md 5.3 KB
- references/cinematography-design-engine.md 11 KB
- references/delivery-mode-guard.md 3.6 KB
- references/design-memory-protocol.md 13 KB
- references/fight-design.md 8.5 KB
- references/fight-reference-case.md 2.1 KB
- references/framing-and-axis.md 10 KB
- references/production-contract.md 12 KB
- references/shot-design-engine.md 14 KB
- scripts/design_memory.py 27 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 · -201 lines · +22 tokens per session df52140a9999
- 4d ago Changed · +11 lines a634b2d559fe
- 7d ago Changed · +37 lines · +1 tokens per session ed422ba4998d
- 12d ago First seen · 242 lines · 132 tokens per session scan A 8b95d02c4dd8
ai-storyboard-director is a skill published in the GitHub repository 62656456/ai-film-skills (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 155 tokens to every session and 2,867 once invoked, about $0.0008 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
seedance-20
This skill should be used when creating, improving, or troubleshooting Seedance 2.0 video on any surface — Dreamina, Jimeng, CapCut, Doubao, Volcengine/Ark, BytePlus, Runway's Seedance route, fal, or third-party provider/router surfaces such as EvoLink, OpenRouter, Kie.ai, PiAPI, LaoZhang, Runware, ModelsLab, AI/ML…
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.
script-to-shootable-storyboard
A guide for turning scripts, story outlines, dialogue, or existing storyboards into detailed shot plans. A storyboard is a sequence of planned camera shots showing what viewers see and hear.
travel-skill
A production guide for realistic travel-promotion videos that combine authorised real footage with AI-generated shots.
minimax-h3
Write, debug and structure prompts for MiniMax H3 video generation (T2VA, I2VA, FL2VA, L2VA, Ref2VA) and configure its ComfyUI workflow. Use when the user mentions MiniMax H3, minimaxh3, fl2va, ref2va, MiniMaxH3ReferenceToVideo, reference-to-video, asks to animate a photo, write a video prompt, pick a model quant, or…
minimax-h3-prompting
Guide an idea into a generation-ready MiniMax H3 / Hailuo H3 prompt or diagnose an inspected H3 output. Use for T2VA, I2VA, FL2VA, L2VA, or Ref2VA; text-only PV and kinetic type, Motion Design/MG, packaging and transitions, product/UI/game/MV/title work, localized reality-to-hand-drawn edits, audio/timbre reference…