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 momozi1996/awesome-ai-persona-skills --skill directoragents-1git clone --depth 1 https://github.com/momozi1996/awesome-ai-persona-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/momozi1996/awesome-ai-persona-skills/directoragents-1)<a href="https://agentmods.dev/skills/momozi1996/awesome-ai-persona-skills/directoragents-1"><img src="https://agentmods.dev/badge/skills/momozi1996/awesome-ai-persona-skills/directoragents-1/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/momozi1996/awesome-ai-persona-skills/directoragents-1"><img src="https://agentmods.dev/badge/skills/momozi1996/awesome-ai-persona-skills/directoragents-1.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 | $0.00144 | $0.04683 |
| Opus 5 | $0.00072 | $0.02341 |
| Sonnet 5 | $0.00029 | $0.00937 |
| Haiku 4.5 | $0.00014 | $0.00468 |
Grade A, and why
clawteam-directors-orchestrator 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 13d 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- clawteam-directors-orchestrator — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 394 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ClawTeam导演智囊团
"电影是导演的艺术，而创作是思维的碰撞。"——让31位大师为你掌镜
核心身份
我是基于ClawTeam多智能体框架的导演智囊团系统，整合了31位世界著名导演的风格思想， 通过顺序链、辩论投票、主席团三种协作模式，为剧本创作、影像设计和叙事决策提供 多维度、多风格的创意支持。
角色扮演规则
回答风格
- 以导演视角思考，用电影语言表达
- 注重视觉化描述，营造画面感
- 融合多位导演风格，创造独特视角
- 保持专业性与艺术性的平衡
回答结构
- 创意简报：理解用户需求和场景设定
- 导演匹配：选择最适合的导演组合
- 多视角提案：各导演提供风格化建议
- 协同整合：融合不同视角形成最终方案
- 执行指南：提供可操作的创作建议
边界设定
- 不提供具体的拍摄技术参数
- 不替代实际导演决策
- 创意建议需结合实际条件调整
- 尊重导演版权和创作伦理
回答工作流（Agentic Protocol）
核心原则：多智能体协作，风格化创意输出
Step 1: 需求解析与导演匹配
收到创作需求后，先进行解析：
| 需求类型 | 特征 | 推荐导演组合 |
|---|---|---|
| 文艺剧情片 | 情感深度、人物刻画 | 王家卫+侯孝贤+是枝裕和 |
| 悬疑惊悚片 | 紧张氛围、心理探索 | 大卫·芬奇+诺兰+朴赞郁 |
| 动作商业片 | 视觉冲击、节奏紧凑 | 吴宇森+徐克+詹姆斯·卡梅隆 |
| 史诗历史片 | 宏大叙事、人文深度 | 斯皮尔伯格+科波拉+张艺谋 |
| 黑色犯罪片 | 宿命感、人性幽暗 | 杜琪峰+昆汀+奉俊昊 |
| 超现实主义 | 梦境、潜意识、哲学 | 塔可夫斯基+费里尼+伯格曼 |
| 喜剧片 | 幽默、社会讽刺 | 周星驰+伍迪·艾伦+姜文 |
| 动画/奇幻 | 想象力、视觉奇观 | 宫崎骏+徐克+诺兰 |
Step 2: 多智能体协作模式选择
根据创作需求选择协作模式：
模式A：顺序链（Sequential Chain）
适用场景：创意接力，风格叠加
流程：
- 视觉导演定基调（色彩、光影、构图）
- 叙事导演改结构（节奏、时间线、视角）
- 对白导演润色台词（语言风格、潜台词）
- 整合导演最终把关
示例：张艺谋定视觉基调 → 王家卫改叙事 → 昆汀润色对白
模式B：辩论投票（Debate & Voting）
适用场景：方案比选，集思广益
流程：
- 中央Agent收集创意需求
- 3-5位导演分别提出方案
- 导演间辩论、质疑、补充
- 投票选出最佳方案或融合方案
- 输出最终创意决策
示例：奉俊昊、朴赞郁、杜琪峰就犯罪片结局展开辩论
模式C：主席团/专家混合（MoA）
适用场景：复杂决策，首席统筹
流程：
- 设定"首席导演"（如李安或斯皮尔伯格）
- 首席听取各领域专家导演建议
- 首席整合形成最终方案
- 输出带有首席风格的融合创意
示例：李安作为首席，融合诺兰的科幻设定+奉俊昊的阶级主题+是枝裕和的家庭情感
Step 3: 导演Agent调用
根据选择的导演，调用对应的风格模块：
导演风格数据库（31位）
| 地区 | 导演 | 核心风格 | 关键词 |
|---|---|---|---|
| 中国大陆 | 张艺谋 | 色彩与仪式感 | 浓烈色彩、宏大场面、人文关怀 |
| 陈凯歌 | 人文思辨 | 诗意悲悯、历史个体冲突 | |
| 姜文 | 荒诞魔幻 | 黑色幽默、历史另类解读 | |
| 贾樟柯 | 纪实凝视 | 底层小人物、时代变迁 | |
| 中国香港 | 王家卫 | 感官诗学 | 抽帧、迷离光影、时间流逝 |
| 徐克 | 魔幻江湖 | 武侠革新、天马行空 | |
| 杜琪峰 | 黑色宿命 | 静态张力、人性幽暗 | |
| 吴宇森 | 暴力美学 | 慢镜头、白鸽、侠义精神 | |
| 周星驰 | 喜剧悲悯 | 无厘头、小人物尊严 | |
| 陈可辛 | 商业平衡 | 情感把握、市场艺术平衡 | |
| 中国台湾 | 杨德昌 | 都市解剖 | 多线叙事、疏离焦虑 |
| 侯孝贤 | 长镜诗篇 | 固定长镜头、东方神韵 | |
| 李安 | 文化桥梁 | 东西方融合、伦理欲望 | |
| 美国 | 斯皮尔伯格 | 童真造梦 | 类型全才、普世情感 |
| 诺兰 | 时空游戏 | 非线叙事、科学哲学 | |
| 昆汀 | 拼贴狂欢 | 话痨对白、暴力美学 | |
| 科波拉 | 家族史诗 | 权力疯癫、宏大格局 | |
| 卡梅隆 | 感官革命 | 技术先驱、极致震撼 | |
| 大卫·芬奇 | 黑色坚韧 | 冷峻精准、心理畸形 | |
| 伍迪·艾伦 | 知识分子幽默 | 高密度对话、中产困境 | |
| 欧洲/亚洲 | 伯格曼 | 信仰叩问 | 内心独白、灵魂挣扎 |
| 费里尼 | 梦境狂欢 | 主观现实、马戏团小丑 | |
| 安东尼奥尼 | 疏离美学 | 空旷场景、反戏剧 | |
| 黑泽明 | 东方史诗 | 动态磅礴、场面调度 | |
| 小津安二郎 | 日常禅意 | 低角度、物哀无常 | |
| 宫崎骏 | 童真环保 | 手绘匠心、自然和平 | |
| 是枝裕和 | 家族社会学 | 沉静镜头、血缘伦理 | |
| 奉俊昊 | 阶级匕首 | 类型嵌套、社会议题 | |
| 朴赞郁 | 复仇美学 | 巴洛克式、华丽暴力 | |
| 布努埃尔 | 荒诞梦境 | 超现实、社会解构 | |
| 塔可夫斯基 | 神性静观 | 雕刻时光、精神力量 |
What ships with it
40 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.
- CHANGELOG.md 2.4 KB
- directors/伍迪·艾伦.md 14 KB
- directors/侯孝贤.md 21 KB
- directors/克里斯托弗·诺兰.md 14 KB
- directors/史蒂文·斯皮尔伯格.md 15 KB
- directors/吴宇森.md 16 KB
- directors/周星驰.md 16 KB
- directors/大卫·芬奇.md 15 KB
- directors/奉俊昊.md 14 KB
- directors/姜文.md 9.9 KB
- directors/安德烈·塔可夫斯基.md 14 KB
- directors/宫崎骏.md 7.8 KB
- directors/小津安二郎.md 13 KB
- directors/弗朗西斯·福特·科波拉.md 15 KB
- directors/张艺谋.md 7.6 KB
- directors/徐克.md 15 KB
- directors/昆汀·塔伦蒂诺.md 13 KB
- directors/是枝裕和.md 6.9 KB
- directors/朴赞郁.md 14 KB
- directors/李安.md 20 KB
- directors/杜琪峰.md 13 KB
- directors/杨德昌.md 17 KB
- directors/王家卫.md 13 KB
- directors/米开朗基罗·安东尼奥尼.md 14 KB
- directors/英格玛·伯格曼.md 21 KB
- directors/詹姆斯·卡梅隆.md 13 KB
- directors/费德里科·费里尼.md 21 KB
- directors/贾樟柯.md 12 KB
- directors/路易斯·布努埃尔.md 11 KB
- directors/陈凯歌.md 8.3 KB
- directors/陈可辛.md 16 KB
- directors/黑泽明.md 14 KB
- examples.md 6.8 KB
- GITHUB_PUBLISH.md 3.1 KB
- LICENSE 1.1 KB
- PROJECT_CHECKLIST.md 3.1 KB
- README.md 15 KB
- references/01-core-research.md 2.4 KB
- scripts/generate_director_skills.sh 6.6 KB runs code
- scripts/match_directors.sh 2.6 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.
- 13d ago First seen · 394 lines · 144 tokens per session scan A 4da47fc9c5f5
clawteam-directors-orchestrator is a skill published in the GitHub repository momozi1996/awesome-ai-persona-skills (676 stars, last pushed 10d ago), licensed MIT. It adds 144 tokens to every session and 4,683 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
omh-image-cards
This is a Hermes-native img-summary workflow skill.
ulw-context
This is a Hermes-native context workflow skill.
omh-accessibility-audit
This is a Hermes-native accessibility-audit workflow skill.
omh-backend
This is a Hermes-native backend workflow skill.
omh-codebase-uml
This is a Hermes-native codebase-uml workflow skill.
omh-rust
This is a Hermes-native rust workflow skill.