brand-promo
做产品/品牌宣传片。当用户要把产品文案、卖点或品牌介绍做成一条短宣传视频,或提到「宣传片 / 产品视频 / 品牌短片 / promo / 广告片」时用我。
Creation-area AI assistant for writing, rewriting, screenwriting, prompt generation, and shot-list drafting. Returns documentAction proposals for user confirmation before any write.
$ npx -y skills add aqm857886159/nomi --skill workbench-creation --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/workbench-creationContext preview
The summary Claude sees to decide when to auto-load this skill.
Creation-area AI assistant for writing, rewriting, screenwriting, prompt generation, and shot-list drafting. Returns documentAction proposals for user confirmation before any write.
name: workbench-creation
description: Creation-area AI assistant for writing, rewriting, screenwriting, prompt generation, and shot-list drafting. Returns documentAction proposals for user confirmation before any write.
metadata:
nomi:
selectable-in-workbench: true
version: 1.0.0
tools:
- read_script
- write_script
required-providers:
- text
library:
kind: skill
title:
zh-CN: 创作助手
en: Writing assistant
summary:
zh-CN: 协助写作、改写和编剧,生成提示词及分镜草稿,修改前交由用户确认。
en: Develop and revise stories, scripts and generation prompts.
appliesTo:
- text
group:
zh-CN: 创作流程
en: Workflow
slots: []
source:
url: https://github.com/aqm857886159/Nomi/blob/7a072f12d4e35d1bf341403d942e5c0c702e6c7b/skills/workbench-creation/SKILL.md
revision: 7a072f12d4e35d1bf341403d942e5c0c702e6c7b
author: Nomi contributors
changes: Nomi adds library presentation metadata; the skill body is unchanged.
evidence:
- https://github.com/aqm857886159/Nomi/blob/7a072f12d4e35d1bf341403d942e5c0c702e6c7b/skills/workbench-creation/SKILL.md
preview:
path: assets/cover.png
type: image
provenance: illustration
license: AGPL-3.0-only帮用户处理创作文稿:写作、润色、续写、改写、整理,以及剧本、提示词、分镜创作。
**对话回复**:直接输出文字,不写入文档。
**写入文档**:只输出一个 JSON 对象(不加 markdown 代码块):
{"type":"replace_selection","content":"..."}
{"type":"insert_at_cursor","content":"..."}
{"type":"append_to_end","content":"..."}规则:
---
用户要求写剧本时,输出三幕结构:
【第一幕 建置】 场景:[地点/时间/氛围] 人物:[主要角色及初始状态] 冲突:[触发事件] 【第二幕 对抗】 场景:[地点变化] 人物弧线:[角色如何因冲突而改变] 冲突升级:[障碍与转折点] 【第三幕 结局】 场景:[最终场景] 人物弧线完成:[角色最终状态] 冲突解决:[结局方式]
---
用户要求生成图片/视频提示词时,为每个场景输出英文提示词:
格式:`[subject], [style], [lighting], [composition], [quality tags]`
示例:
Act 1: young woman standing at crossroads, cinematic realism, golden hour backlight, wide shot low angle, 8k detailed, photorealistic Act 2: tense confrontation in rain, noir style, dramatic side lighting, medium close-up, high contrast, film grain Act 3: peaceful resolution at dawn, soft watercolor style, diffused morning light, symmetrical composition, serene atmosphere
适用于 Stable Diffusion、Midjourney、Veo 等工具。
---
用户要求生成分镜时,为每个场景输出镜头描述:
格式:
镜头 [N] 景别:[远景/全景/中景/近景/特写] 运动:[固定/推/拉/摇/跟/升降] 时长:[秒数] 内容:[画面描述]
---
Open-source AI video workbench. Bring any model or your local ComfyUI, and let Claude Code / Codex / Cursor direct it over MCP — storyboard, references, generation, editable first cut on a real timeline. Local-first: projects, prompts, and keys stay on your machine. No account, no telemetry.
Repo: aqm857886159/nomi
做产品/品牌宣传片。当用户要把产品文案、卖点或品牌介绍做成一条短宣传视频,或提到「宣传片 / 产品视频 / 品牌短片 / promo / 广告片」时用我。
Direct creation-area document editing: read current content, append or replace text, and…