원클릭으로 Manus에서 모든 스킬 실행

asset-gateway

스타0

포크0

업데이트2026년 4월 24일 05:48

Generates images, videos, and other assets using built-in tools. Use when the user asks to create or edit images, generate videos, or produce other media assets.

설치

Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.

Manus에서 실행

출처

fran0220

fran0220/jacoworks

GitHub 저장소 열기 Creator 저장소 보기

다운로드

Manus에서 실행

Asset Generation

Use the built-in generate_image and generate_video tools directly — do NOT use bash CLI.

Image Generation

New image from text

generate_image(prompt="a medieval castle at sunset", size="1024x1024")

Edit an existing image (using URL from previous result)

generate_image(
  prompt="Add a moat around the castle",
  input_image="https://asset.origingame.dev/assets/xxx.png",
  edit_mode="edit"
)

Edit modes

Mode	Use when
`edit`	General edits based on prompt (default)
`inpaint`	Fill in or replace specific areas
`restyle`	Keep subject, change artistic style
`expand`	Extend the image canvas

Transparent background

generate_image(prompt="a game icon of a fire sword", transparent=true)

Reference images for style guidance

generate_image(
  prompt="a warrior in this art style",
  reference_images=["https://...style-ref.png"]
)

Video Generation

Text to video

generate_video(prompt="Slow cinematic fly-through of a mossy temple at sunrise")

Image to video (animate a still image)

generate_video(
  prompt="The character waves and blinks",
  input_image="https://asset.origingame.dev/assets/xxx.png"
)

Editing Workflow

Generate an image → tool returns a URL
The URL is displayed inline in the conversation
User can annotate (draw arrows, add notes) or request edits via text
Pass the URL back as input_image for the next edit — no re-upload needed
Repeat until satisfied

Choosing Tools

Goal	Tool
Still image creation	`generate_image`
Image editing / iteration	`generate_image` with `input_image`
Motion clip / animation	`generate_video`
Animate a still image	`generate_video` with `input_image`

Notes

Results are URLs — they display inline in the conversation automatically.
For editing, pass the URL from a previous result directly as input_image.
Local file paths also work as input_image — they are uploaded automatically.
Do NOT use asset-gateway CLI through bash — use the tools directly.

이 저장소의 다른 Skills

같은 저장소

ai-search

fran0220/jacoworks

Searches the web using the built-in web_search tool. Use when the user asks for fresh information, web research, recent news, documentation lookup, or current facts.

2026-04-240

releasing-desktop

fran0220/jacoworks

Releases JAcoworks Desktop (Tauri) — version bump, macOS/Windows build, COS upload, DB registration, git tag. Use when the user says 'release', 'publish', '发版', '发布版本', or mentions a version number like 'v1.6.1'.

2026-04-110

browser

fran0220/jacoworks

Automates web pages through the bundled agent-browser CLI. Use when the user asks to open a page, click or fill elements, take screenshots, inspect DOM state, reuse Chrome login sessions, or perform browser-based workflows via bash.

2026-04-090

my-skill-name

fran0220/jacoworks

创建和管理 Agent 技能包。创建和管理 Agent 技能包。当用户要求创建技能、新建 skill、编写 SKILL.md 时使用。Triggers on: 创建技能, 新建skill, create skill, build skill.

2026-04-040

blender-scene

fran0220/jacoworks

Create and export 3D scenes using Blender 4.4 bpy scripts + Kenney GLB assets for Three.js. Use when building office environments, assembling furniture layouts, or exporting GLB for the observatory.

2026-03-160

openclaw-integration

fran0220/jacoworks

OpenClaw container integration with JAcoworks gateway. Use when deploying, configuring, debugging, or extending OpenClaw containers, the WS protocol bridge, or container_type dispatch logic.

2026-03-090

name	asset-gateway
description	Generates images, videos, and other assets using built-in tools. Use when the user asks to create or edit images, generate videos, or produce other media assets.

Asset Generation

Use the built-in generate_image and generate_video tools directly — do NOT use bash CLI.

Image Generation

New image from text

generate_image(prompt="a medieval castle at sunset", size="1024x1024")

Edit an existing image (using URL from previous result)

generate_image(
  prompt="Add a moat around the castle",
  input_image="https://asset.origingame.dev/assets/xxx.png",
  edit_mode="edit"
)

Edit modes

Mode	Use when
`edit`	General edits based on prompt (default)
`inpaint`	Fill in or replace specific areas
`restyle`	Keep subject, change artistic style
`expand`	Extend the image canvas

Transparent background

generate_image(prompt="a game icon of a fire sword", transparent=true)

Reference images for style guidance

generate_image(
  prompt="a warrior in this art style",
  reference_images=["https://...style-ref.png"]
)

Video Generation

Text to video

generate_video(prompt="Slow cinematic fly-through of a mossy temple at sunrise")

Image to video (animate a still image)

generate_video(
  prompt="The character waves and blinks",
  input_image="https://asset.origingame.dev/assets/xxx.png"
)

Editing Workflow

Generate an image → tool returns a URL
The URL is displayed inline in the conversation
User can annotate (draw arrows, add notes) or request edits via text
Pass the URL back as input_image for the next edit — no re-upload needed
Repeat until satisfied

Choosing Tools

Goal	Tool
Still image creation	`generate_image`
Image editing / iteration	`generate_image` with `input_image`
Motion clip / animation	`generate_video`
Animate a still image	`generate_video` with `input_image`

Notes

Results are URLs — they display inline in the conversation automatically.
For editing, pass the URL from a previous result directly as input_image.
Local file paths also work as input_image — they are uploaded automatically.
Do NOT use asset-gateway CLI through bash — use the tools directly.