ComfyUI-Agent-Kit

SlavaSexton/ComfyUI-Agent-Kit

ComfyUI-Agent-Kit 是 GitHub 上 SlavaSexton 的 agent skill 项目：驱动本地 ComfyUI 出图出视频，附 Seedance、MiniMax H3 视频提示词 skill：多镜头分镜、参考素材标注、翻车排查。覆盖提示词、出片阶段，提示词适配 ComfyUI（本地）、Seedance / 即梦、MiniMax H3，仓库写明支持 Claude Code、Codex、Gemini CLI。目前 106 星，最近更新于 2026-09-03，许可证 Apache-2.0。

主体是本地 ComfyUI 驱动工具；短剧可用的是其中的 Seedance、MiniMax H3 提示词 skill

类型: 分镜 · 视觉资产 · 视频提示词
创作阶段: 提示词 · 出片
视频模型: ComfyUI（本地） · Seedance / 即梦 · MiniMax H3
支持的 agent: Claude Code · Codex · Gemini CLI
形式: 标准 skill
正文语言: 英文
GitHub 星数: ★ 106
最近更新: 2026-09-03
许可证: Apache-2.0
SKILL.md 数量: 4
人工核对: 2026-10-13

在 GitHub 查看信息有误？提交更正

仓库自述

One ComfyUI skill for every AI coding agent (Claude Code, Codex, Gemini CLI, Qwen Code): drives a local ComfyUI end to end. 75 model prompt recipes, 581 templates, plus standalone Seedance, Krea and MiniMax H3 skills. Hardware-aware selection, workflow building, multi-shot video, ControlNet, HDR. By AI VFX NEWS.

仓库里的 skill（4 个）

名字和说明取自各 SKILL.md 的 frontmatter。

comfyui
Drive a local ComfyUI install for image, video, and audio generation via its HTTP API. Use WHENEVER generating, rendering, or editing images/video/audio/hero assets with ComfyUI, Z-Image, Ideogram, FLUX, LTX, Wan, or when building, parameterizing, or running ComfyUI workflows. Covers the API client…
krea
Use when a task names Krea or Krea 2, when choosing between Krea's hosted API and its open weights, when wiring the Krea 2 Image or Krea 2 Style Reference API nodes, when building with FLUX.1 Krea Dev, when someone asks about Krea Realtime or realtime or streaming video generation, or when a Krea 2…
minimax-h3
Use when writing or debugging prompts for MiniMax H3 (Hailuo 3) video-with-audio generation, running the open weights locally in ComfyUI, choosing a quant or an acceleration LoRA for the VRAM you have, wiring reference-to-video with images, video or audio, or when a generated clip produces gibberis…
seedance
Use when writing or debugging prompts for ByteDance Seedance video models (Seedance 2.5, 2.0, 2.0 Mini, 1.5 Pro, 1.0) on Dreamina, Jimeng AI, Doubao, BytePlus ModelArk or ComfyUI, when a generated video drifts off the reference face, grows unwanted subtitles or watermarks, duplicates a character, j…

安装

/plugin marketplace add SlavaSexton/ComfyUI-Agent-Kit

默认命令基于 skills CLI，未逐个验证，以仓库 README 为准。安装前先读一遍 SKILL.md。安装指南 →

ComfyUI-Agent-Kit

仓库自述

仓库里的 skill（4 个）

安装

同类项目