Multimodal Gen

What it does

When your agent uses it

• Tasks that involve AI video generation

Example prompts

• “/multimodal-gen”

Requirements

• Python 3
• Pre-approved tools (allowed-tools): sessions_spawn, Bash, Read, Write, Edit

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

1. 1提示词优化: multimodal-agent 会自动优化用户的描述
2. 2模型选择: 如果用户没指定，默认使用 flux (图片) 或 veopro (视频)
3. 3异步执行: 视频生成可能需要较长时间，会在后台执行
4. 4结果返回: 生成完成后会自动发送结果给用户

What it can do on your machine

Read from SKILL.md and the folder at commit 331ecd3. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves these tools, so the agent can use them without asking each time:

  • sessions_spawn
  • Bash
  • Read
  • Write
  • Edit

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships script files (Python), which the agent can run.

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Multimodal Gen loads about 580 tokens when it runs. Until then it costs about 28 tokens; SKILL.md has 107 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~28

When it runs · the whole SKILL.md, loaded when a task matches

~580

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

• NotePre-approves every shell command (allowed-tools: Bash)SKILL.md

  allowed-tools: sessions_spawn, Bash, Read, Write, Edit

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from aAAaqwq/AGI-Super-Team at commit 331ecd3, republished under its MIT licence (© aAAaqwq). 107 words, ~580 tokens.

name

multimodal-gen

description

多模态内容生成（图片、视频）。当用户需要生成图片、生成图像、生成视频、AI绘画、AI作图、画一张图、做个视频、文生图、文生视频时使用此技能。自动调用 multimodal-agent 进行生成。

allowed-tools

sessions_spawn, Bash, Read, Write, Edit

sessions_spawn(
    agentId="multimodal-agent",
    task="生成图片: {用户描述}, 使用 {模型} 模型"
)

用户请求 "生成一张猫咪图片"
    │
    ▼
┌─────────────────────────────────────┐
│ 1. 识别为图片生成请求              │
│ 2. 提取描述: "猫咪"                │
│ 3. 选择默认模型: flux-pro-max      │
└─────────────────────────────────────┘
    │
    ▼
┌─────────────────────────────────────┐
│ sessions_spawn(                     │
│   agentId="multimodal-agent",       │
│   task="生成图片: 一只可爱的猫咪,   │
│         使用 flux 模型"             │
│ )                                   │
└─────────────────────────────────────┘
    │
    ▼
multimodal-agent 执行生成并返回结果

用户: 帮我生成一张日落海滩的图片

执行:
sessions_spawn(
    agentId="multimodal-agent",
    task="生成图片: 日落时分的海滩，金色阳光洒在海面上，使用 flux 模型"
)

用户: 用 sora 生成一个猫咪玩耍的视频

执行:
sessions_spawn(
    agentId="multimodal-agent",
    task="生成视频: 一只可爱的猫咪在草地上玩耍，使用 sora 模型"
)

用户: 用 doubao 画一张中国风山水画

执行:
sessions_spawn(
    agentId="multimodal-agent",
    task="生成图片: 中国风山水画，云雾缭绕的山峰，使用 doubao 模型"
)

© aAAaqwq, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 4 other files in skills/multimodal-gen of aAAaqwq/AGI-Super-Team.

• SKILL.md
• generate.py
• generate_image.py
• generate_video.py
• prompt_optimizer.py

Open the folder on GitHubat commit 331ecd3

Used in 1 other repository

We found 2 copies of this SKILL.md (exact, near-identical or edited) in other folders, from 1 other GitHub owner. This page covers the copy in aAAaqwq/AGI-Super-Team, which our catalogue first saw on October 7, 2026.

• NeverSight/learn-skills.devdata/skills-md/aaaaqwq/agi-super-skills/multimodal-gendata/skills-md/aaaaqwq/claude-code-skills/multimodal-gen