Repository
JGRFW/comfyui-AICG3D agent skills
- skills
- 6
- GitHub stars
- 176
GitHub description: “短剧工作台 | 无限时长视频的 MiniMax H3 工作流 | ComfyUI 本地短剧与长视频生成插件”
- Stars
- 176 (22 forks)
- Licence
- GPL-3.0
- Last push
- Oct 2026
- Created
- Sep 2026
- Homepage
- github.com/JGRFW/comfyui-AICG3D
- ai-video
- comfyui
- custom-nodes
- minimax-h3
- text-to-video
- comfyui-workflow
- image-to-video
- local-ai
- short-drama
- video-generation
- infinite-video
- unlimited-video
Install all skills
npx skills add JGRFW/comfyui-AICG3DAdd --skill <name> for a single skill and -a <agent> to choose the agent (see the agent guides).
Skills in JGRFW/comfyui-AICG3D, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | 为 Midjourney V8.2 设计、精简、分析和修正东方巨构、白玉京、天宫仙境与东方巨景提示词，并把完成图片转为约5秒的稳定图生视频提示词。支持一句话或关键词造景、参考图构图转译、多个主题发散、生成结果诊断、机位焦段修正、建筑丰富度与中式纯度控制、英文MJ生成失败修复，以及云海缓慢翻涌的视频动态。用于“写天宫提示词”“设计东方巨构全景”“参考图片生成同类画面”“分析为什么不够宏大”“建筑太… | JGRFW/ | 176 | — | ~1.2k | Automated safety check: Pass | GPL-3.0 | today |
| 2 | 根据用户提供的人物、场景、剧情、参考画面或续写要求，直接生成5—30秒“光感小清新短片”视频提示词。固定输出整体场景与氛围、多分镜时间轴、画面风格、统一环境动态、统一环境音、负面提示词和语言锁，重点保证清透冷调、自然光感、人物细微状态与前后光线连续。 | JGRFW/ | 176 | — | ~926 | Automated safety check: Pass | GPL-3.0 | today |
| 3 | 将参考图、单个简单剧情、简短场景想法或已有提示词整理成最长15秒的中文电影感视频生成提示词。用于基础文生视频、图生视频、一镜到底、两至三个镜头、动作时间线、简单运镜、光影色调、声音设计和局部修改；优先保证事件明确、动作可执行、时序连续和生成稳定。不用于完整剧本、长篇分镜、整部短剧、广告策划、角色设定或复杂世界观开发。 | JGRFW/ | 176 | — | ~1.1k | Automated safety check: Pass | GPL-3.0 | today |
| 4 | 将主题、情绪、故事或参考图片转化为具有电影叙事感的超现实图像提示词，并在用户上传生成结果后，继续输出默认约5秒、单镜头、不切镜的图生视频提示词。默认提供中文通用提示词与Midjourney提示词两套版本。 | JGRFW/ | 176 | — | ~2.1k | Automated safety check: Pass | GPL-3.0 | today |
| 5 | 根据参考图和用户设定创作高密度、连续因果的电影级打斗视频提示词，并输出保持同一时间线的中文导演稿与 MiniMax H3 Ref2VA 英文六段稿。适用于 15 秒动作设计、武器战、徒手战、巨物战和参考图驱动的连续攻防。 | JGRFW/ | 176 | — | ~590 | Automated safety check: Pass | GPL-3.0 | today |
| 6 | 将用户的生活主题、人物资产、道具资产与场景信息，整理成30秒以内、可直接用于AI视频生成模型的真实手机自拍Vlog提示词。强调真实手机拍摄逻辑、自然表演、生活碎片、现场收音、资产一致性与设备不穿帮。 | JGRFW/ | 176 | — | ~2.2k | Automated safety check: Pass | GPL-3.0 | today |
Questions, answered from the data.
What is the best skill in JGRFW/comfyui-AICG3D?
Eastern Megastructure Director from JGRFW/comfyui-AICG3D ranks first of the 6 skills in JGRFW/comfyui-AICG3D listed here, with the highest score: its repository has 176 GitHub stars, its SKILL.md loads about 1.2k tokens and it passes the automated safety check with no findings. Next come Light Fresh Short Film and Short Scene Director Lite.
Are the skills in JGRFW/comfyui-AICG3D official?
None yet. All 6 skills in JGRFW/comfyui-AICG3D listed here come from community repositories; a skill counts as official when the product's own GitHub organization publishes it.
How do I install all skills from JGRFW/comfyui-AICG3D?
Run npx skills add JGRFW/comfyui-AICG3D in your project: the open-source skills CLI installs the repository's skills into your coding agent's skills folder. To install a single skill, open its page here for the exact command.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.