Home / wwwzhouhui / skills_collection · GitHub

jimeng_mcp_skill SKILL.md skillB

This file is byte-identical to the first copy the registry indexed. Same content hash, so the same checks give both the same grade.

jimeng_mcp_skill from wwwzhouhui/skills_collection is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned

mdr add wwwzhouhui/skills_collection/jimeng_mcp_skill@git:20251214.139c6f9

Pins git:20251214.139c6f9 in mdr.lock. Pin the fingerprint instead.

Audit grade: B, 16 of 17 checks passed
Kind: SKILL.md skill
Repository: wwwzhouhui/skills_collection
Path: xiaohuihui-tech-article/jimeng_mcp_skill/SKILL.md
Versions recorded: 1
Latest version: git:20251214.139c6f9, committed Dec 14, 2025
Size: 12,213 bytes
Repository stars: 284
License: none declared

使用jimeng-mcp-server进行AI图像和视频生成。当用户请求从文本生成图像、合成多张图片、从文本描述创建视频或为静态图像添加动画时使用此技能。支持四大核心能力：文生图、图像合成、文生视频、图生视频。需要jimeng-mcp-server在本地运行或通过SSE/HTTP访问。.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# 即梦 AI 生成技能

## 概述

即梦技能通过 jimeng-mcp-server 实现 AI 驱动的图像和视频生成，这是一个集成了即梦 AI 多模态生成能力的 MCP（模型上下文协议）服务器。使用此技能可以直接通过自然语言指令创建视觉内容。

**核心能力：**
- 🎨 **文本生成图像**：从文本描述生成高质量图像
- 🎭 **图像合成**：智能合并和融合多张图片
- 🎬 **文本生成视频**：从文本提示创建短视频
- 🎞️ **图像生成视频**：为静态图像添加动画效果

**何时使用此技能：**
- 用户要求生成、创建或制作图像或视频
- 用户提到"jimeng"、"即梦"或请求AI视觉内容生成
- 用户提供文本描述并希望得到视觉输出
- 用户想要组合、合并或合成多张图片
- 用户想为静态图像添加动画或运动效果

## 前置条件

使用此技能前，请确保 jimeng-mcp-server 已正确配置：

1. **服务器必须运行**，通过以下模式之一：
   - **stdio 模式**：在 MCP 客户端（Claude Desktop、Cherry Studio）中配置
   - **SSE 模式**：作为带 SSE 传输的 HTTP 服务器运行
   - **HTTP 模式**：作为 REST API 服务器运行

2. **环境变量已配置**：
   - `JIMENG_API_KEY`：您的即梦 API 密钥（从即梦网站 cookies 获取）
   - `JIMENG_API_URL`：API 端点（默认：http://127.0.0.1:8001）
   - `JIMENG_MODEL`：模型名称（默认：jimeng-4.5）

3. **后端 API 运行中**：jimeng-free-api-all Docker 容器必须处于活动状态

详细的设置说明请参考 `references/setup_guide.md`。

## 快速开始

### 基本使用模式

当用户请求图像或视频生成时，遵循以下工作流程：

1. **识别任务类型**，基于用户输入
2. **提取必需参数**，从请求中获取
3. **调用相应的 jimeng-mcp-server 工具**
4. **返回生成的内容 URL** 给用户

### 示例请求

**文本生成图像：**
```
用户："用即梦生成一张图片：樱花树下的柴犬"
→ 使用 text_to_image 工具，参数 prompt="樱花树下的柴犬"
```

**图像合成：**
```
用户："帮我合成这两张图片，风格偏向第一张"
→ 使用 image_composition 工具，提供图片 URL
```

**文本生成视频：**
```
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint

mdr add wwwzhouhui/skills_collection/jimeng_mcp_skill@sha256:d3dba9872e965b6a

The line at the top of this page pins the label git:20251214.139c6f9, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

[![mdr](https://markdownregistry.com/badge/art_ubuzij2ufz3speyk.svg)](https://markdownregistry.com/a/art_ubuzij2ufz3speyk)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Dec 14, 2025.

version	committed	commit	size	audit
git:20251214.139c6f9 latest	2025-12-14	139c6f9	12,213 B	B	view

Audit of the latest version

B 16 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.

fail: No link to a raw IP address (matched: http://127.0.0.1:8001)
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (12213 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No script tag

Starting a new one? Use a template for SKILL.md on mdpantry, which passes every one of these checks and says what to change in it.

Source

GitHub

wwwzhouhui/skills_collection · 284 stars · license none declared · pushed 2026-10-16 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_ubuzij2ufz3speyk
GET https://markdownregistry.com/api/v1/resolve?ref=wwwzhouhui/skills_collection/jimeng_mcp_skill
GET https://markdownregistry.com/api/v1/blob/d3dba9872e965b6a541fac15efca0e2943b3021dcf7c96148a2bd665d9d4bc99

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from wwwzhouhui/skills_collection

ai-teaching-media SKILL.md skill

wwwzhouhui/skills_collection · ai-teaching-media/SKILL.md · AI 教学媒体一体化技能包。在一个 skill 内串联 6 个子能力：通用生图执行层、技术长文智能插图、学科知识点竖版信息图、教学动图+配音教学视频、短视频 3:4…