neta-creative创意生成

Neta API creative skill — generate images, videos, songs, and MVs, and deconstruct creative ideas from existing works. Use this skill when the user wants to create or edit images/videos/songs/MVs, or create based on character settings and existing works. Do not use it for feed browsing or tag/category research (those are handled by neta-community and neta-suggest).

作者: admin | 来源: ClawHub

Neta Creative Skill

Used to interact with the Neta API for multimedia content creation and creation‑related character queries.

Instructions

1. For tasks that create or edit concrete assets (images, videos, songs, MVs, background removal), follow this flow:

- Before creation, use character queries to fetch canonical character settings, then generate images/videos/songs based on them. - To reverse‑engineer creative ideas from an existing work, call read_collection and combine the result with the guidance in the reference docs.

2. If, during creation, you discover that the real need is more like “browse recommendations / casually explore / research topics”, combine this skill with neta-community or neta-suggest instead of overloading this skill.

Prerequisites

Make sure the NETA_TOKEN environment variable is set.

Also ensure the latest Neta CLI is installed:

CODEBLOCK0

CODEBLOCK1

CODEBLOCK2

Commands

Content creation

Generate image

CODEBLOCK3

📖 Detailed guide — prompt structure, aspect ratio choices, examples.

Generate video

CODEBLOCK4

📖 Detailed guide — motion description principles, model selection.

Generate song

CODEBLOCK5

📖 Detailed guide — style prompts, lyrics format.

Create MV

Combine an audio track and video to create a full MV.

📖 Detailed guide — end‑to‑end workflow.

Remove background

CODEBLOCK6

Character queries

Search characters

CODEBLOCK7

📖 Detailed guide — search strategies and parameter choices.

Get character details

CODEBLOCK8

Query by UUID

CODEBLOCK9

Creative idea deconstruction

Derive creative ideas from a work

CODEBLOCK10

📖 Detailed guide

Reference docs

Scenario	Doc
🎨 Image generation	image-generation.md
🎬 Video generation

Neta 创意技能

用于与 Neta API 交互，进行多媒体内容创作及与创作相关的角色查询。

使用说明

1. 对于创建或编辑具体资产（图像、视频、歌曲、MV、背景移除）的任务，请遵循以下流程：

- 在创作前，先使用角色查询获取规范的角色设定，然后基于这些设定生成图像/视频/歌曲。 - 若要从现有作品中逆向推导创意，请调用 read_collection，并将结果与参考文档中的指导相结合。

2. 如果在创作过程中发现实际需求更接近“浏览推荐/随意探索/研究主题”，请将此技能与 neta-community 或 neta-suggest 结合使用，而非过度依赖本技能。

前置条件

确保已设置 NETA_TOKEN 环境变量。

同时确保已安装最新版 Neta CLI：

bash
neta-cli --version
0.8.0

bash
npm i @talesofai/neta-skills@latest -g

bash
pnpm add -g @talesofai/neta-skills@latest

命令

内容创作

生成图像

bash
neta-cli make_image --prompt @角色名称, /元素名称, 参考图片UUID, 描述1, 描述2 --aspect 3:4

📖 详细指南 — 提示词结构、宽高比选择、示例。

生成视频

bash
neta-cli makevideo --imagesource 图片URL --prompt 动作描述 --model model_s

📖 详细指南 — 动作描述原则、模型选择。

生成歌曲

bash
neta-cli make_song --prompt 风格描述 --lyrics 歌词内容

📖 详细指南 — 风格提示词、歌词格式。

创建 MV

将音频轨道与视频结合，创建完整的 MV。

📖 详细指南 — 端到端工作流程。

移除背景

bash
neta-cli removebackground --inputimage 图片URL

角色查询

搜索角色

bash
neta-cli searchcharacterorelementum --keywords 关键词 --parenttype character --sort_scheme exact

📖 详细指南 — 搜索策略与参数选择。

获取角色详情

bash
neta-cli requestcharacteror_elementum --name 角色名称

通过 UUID 查询

bash
neta-cli requestcharacteror_elementum --uuid UUID

创意解构

从作品中推导创意

bash
neta-cli read_collection --uuid 集合UUID

📖 详细指南

参考文档

场景	文档
🎨 图像生成	image-generation.md
🎬 视频生成

neta-creative创意生成

neta-creative

Neta Creative Skill

Instructions

Prerequisites