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-short-drama-productiongit 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-short-drama-production)<a href="https://agentmods.dev/skills/62656456/ai-film-skills/ai-short-drama-production"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/ai-short-drama-production/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-short-drama-production"><img src="https://agentmods.dev/badge/skills/62656456/ai-film-skills/ai-short-drama-production.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 | $0.00082 | $0.02813 |
| Opus 5 | $0.00041 | $0.01406 |
| Sonnet 5 | $0.00016 | $0.00563 |
| Haiku 4.5 | $0.00008 | $0.00281 |
Grade A, and why
ai-short-drama-production 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 4d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AI 短剧生产编排
把创意编排为可追溯的生产任务:导演判断、资产与空间/动作合同 → 五列人读分镜 → 六模块视频母提示词(数字10为内部信息覆盖)→ 实际画面 QC。按用户本次交付范围进入对应阶段,不要求每次从头走完整条流程。
这是控制合同层,不重写既有导演或资产方法:
- 剧本解读、视觉概念、节拍/镜头归并、台词时序、剪辑动机与可生成性,按
references/independent-production-core.md在本包内完成。 - 人物、场景、道具的真实外观、状态与审核,按本包内置资产合同完成。
- 类型色彩、镜头偏好与材质参数,按本包内置类型适配表完成。
本 Skill 把这些决定变成本包内可传递、检查和回写的控制合同。用户只要控制合同、分镜表或局部修改时,停在点名范围;进入分镜/提示词交付时读取本包 production-handoff.md。该文件自带与5.6日常结构对齐的最小交付合同,不要求读取或安装其他 Skill。
1. 先判断输入,补齐缺口
从用户输入提取:受众/时长、剧本形态、人物目标与阻力、场景、主类型、目标平台、已有关联资产或草图。缺失项写为 pending,不可用空泛的“爆款”“电影感”代填。大纲、草图或口述造成的补充事实必须写 assumed,不可伪装为原始设定。
| 输入状态 | 首要产物 | 本包处理层 |
|---|---|---|
| 只有故事点子 | narrative_beat_contract |
导演与剧本层 |
| 角色/场景尚未固定 | Cxx/Sxx/Pxx 资产合同 | 本包资产层 |
| 已有资产,画面易漂移 | blocking_map |
本包镜头层 |
| 已有草图或分镜草稿 | sketch_to_shot_brief |
镜头与提示词层 |
| 对打、追逐、抢夺 | action_ledger |
镜头、提示词与成片检查层 |
| 画面“平”“假”“不高级” | lighting_plan |
镜头、提示词与成片检查层 |
2. 按交付范围编排生产
- 先按本包内置导演判断完成剧本三层读法、视觉概念与场策略;再从其判断结果写可检验的开场钩子、目标/阻力、策略或权力转折、结尾钩子。
- 按本包内置资产合同登记 Cxx/Sxx/Pxx;已有用户锁定的资产直接沿用,未锁定部分可作为明确标记的候选支持文本分镜与提示词。正式生成前须完成相应资产审阅,不以视频抽卡替代资产库,也不以尚无参考图为由拒交用户点名的文本方案。
- 对镜头建立
blocking_map:先固定世界方向、空间锚点、人物位置/朝向/高度、道具与光源,再按每个机位推导画面左右、前后、遮挡与出框。平面图只在足以表达当前空间时使用;摄影机移动或切镜本身不改变世界状态。 - 用本包类型适配层提供镜头、色彩和材质参数;类型参数不得改变审核过的资产外观。
- 仅在需要时叠加下列专项合同:草图转镜头、布光、动作。详细字段见 control-contracts.md。
- 先形成五列人读分镜;用户指定一个总时长时,再把已选方案编译成一条覆盖全部时长的完整视频母提示词,六模块只出现一次,不拆成六条提示词。一个总时长生成片段可包含多个明确切点的镜头;用户锁定连续长镜时不得插入切镜。固定、单项或复合运镜按观看目的选择,并写明具体起止、路径、朝向、速度和接力。节拍密度由动作、台词与辨认时间决定,不固定动作数或镜头数;无法兼容用户锁定条件时先指出具体冲突,不能擅自拆镜、改时长或省略结果。
- 本包成片检查层用实际画面复核,不以平台任务成功、漂亮单帧或重复生成当作通过。
3. 六种可控性合同
3.1 剧本节拍合同
写 hook / want / obstacle / strategy_shift / power_turn / cost / cliffhanger,并记录观众信息差、人物进出状态差、情绪曲线与视觉概念引用。每项必须是画面或台词可观察的事实。不要把“反转很强”当作内容。
3.2 资产库合同
资产库(asset_registry)是已批准 Cxx/Sxx/Pxx 的索引,不是图片文件夹。每个条目至少有:asset_id、版本、状态、参考图、锁定特征、可变状态、来源镜头、最后审阅日期。版本变化使用后缀(如 C01b),绝不覆盖已批准版本。
3.3 场面调度图
每张图固定:画面朝向、左中右/前中后空间锚、A/B 的位置和面向、道具初末位置、行动路径、进出画、遮挡物、摄影机位置/镜头方向、180°轴及权力几何。发生移动时,用编号阶段 T0 → T1 → T2,而不是把整段动作写成一句话。调度先于机位:先让走位和物件关系承担变化,再选择摄影机如何观察。
What ships with it
5 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.
- 4d ago Changed · +4 lines 6f243cdfd033
- 7d ago Changed · -6 tokens per session 9dd56df5f14f
- 12d ago First seen · 97 lines · 88 tokens per session scan A 0264256900ac
ai-short-drama-production is a skill published in the GitHub repository 62656456/ai-film-skills (17 stars, last pushed yesterday), licensed Apache-2.0. It adds 82 tokens to every session and 2,813 once invoked, about $0.0004 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…