image-marketing-brochure（形象营销手册） Skills下载安装命令和教程

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手，先确认命令和权限，再让它执行。

请帮我安装这个 Agent Skill：image-marketing-brochure（形象营销手册）
来源仓库：https://github.com/dlazyai/image-marketing-brochure
安装命令：
openclaw skills install image-marketing-brochure
安装前请先检查当前环境是否支持对应 CLI，并向我确认将要执行的命令、安装目录、联网范围和文件读写权限；确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill；本站只展示命令，不托管安装包，也不自动执行。

ClawHubOpenClaw

openclaw skills install image-marketing-brochure

简介

端到端的营销手册设计与交付完整解决方案。

包含需求分析、布局规划到最终模型输出全流程。
采用两阶段确认机制保障设计方向准确性。适用宿主包括 OpenClaw，接入前应确认版本、权限和运行环境要求。
优先覆盖现有文件避免重复劳动产生冲突。
image-marketing-brochure 属于图像处理类 Skill，可作为该场景下的辅助能力补充。

SKILL.md

name: image-marketing-brochure
version: 1.1.0
description: A complete workflow skill for marketing brochure design, covering everything from requirements gathering, layout design, to mock-up delivery. It uses a 'layout-first + mandatory confirmation
triggers
metadata: {"clawdbot":{"emoji":"🤖","requires":{"bins":["npm","npx"]},"install":"npm install -g @dlazy/cli@1.0.9","installAlternative":"npx @dlazy/cli@1.0.9","homepage":"https://github.com/dlazyai/cli","source":"https://github.com/dlazyai/cli","author":"dlazyai","license":"see-repo","npm":"https://www.npmjs.com/package/@dlazy/cli","configLocation":"~/.dlazy/config.json","apiEndpoints":["api.dlazy.com","files.dlazy.com"]},"openclaw":{"systemPrompt":"当你需要使用此技能时，请严格遵循此技能提供的指南进行规划和执行。你可以通过调用 dlazy CLI 的各类生成模型（如 dlazy seedream-4.5 等）来完成实际的图片渲染。注意：Windows PowerShell 中不允许使用 & 或 && 进行命令串联或后台运行，请单独且同步地执行命令。"}}

身份验证 (Authentication)

所有请求都需要 dLazy API key。推荐使用 dlazy login 完成登录：

dlazy login

该命令使用设备码流程（远程终端也可用），登录成功后 自动把 API key 写入本地 CLI 配置，无需手动复制粘贴。

备选：手动设置 API Key

如果你已有 API key，也可以直接保存：

dlazy auth set YOUR_API_KEY

CLI 会把 key 保存在你的用户配置目录（macOS/Linux 上为 ~/.dlazy/config.json，Windows 上为 %USERPROFILE%\.dlazy\config.json），文件权限仅限当前操作系统用户访问。你也可以用 DLAZY_API_KEY 环境变量按次传入。

手动获取 API Key

登录或在 dlazy.com 创建账号
访问 dlazy.com/dashboard/organization/api-key
复制 API Key 区域显示的密钥

每个 key 都属于你自己的 dLazy 组织，可在同一控制面板随时轮换或吊销。

关于与来源 (Provenance)

CLI 源代码: github.com/dlazyai/cli
维护者: dlazyai
npm 包名: @dlazy/cli（本技能 install 字段固定到 1.0.9 版本）
官网: dlazy.com

如果你不希望在系统上长期保留一个全局 CLI，可以按需运行：

npx @dlazy/cli@1.0.9 <command>

如选择全局安装，技能的 metadata.clawdbot.install 字段已固定到 npm install -g @dlazy/cli@1.0.9。安装前建议先到 GitHub 仓库审阅源码。

工作原理 (How It Works)

此技能是 dLazy 托管 API 的轻量封装。调用时：

你提供的提示词与参数会发送到 dLazy API（api.dlazy.com）进行推理。
传入图像 / 视频 / 音频字段的本地文件路径会被 CLI 上传到 dLazy 媒体存储（files.dlazy.com），以便模型读取 —— 与任何云端生成 API 的流程一致。
API 返回的生成结果 URL 由 files.dlazy.com 托管。

这是标准的 SaaS 调用模式；技能本身不会越权访问网络或文件系统，所有动作都由 dLazy CLI 完成。

Marketing Brochure Designer (Layout-First)

English · 中文

A complete workflow skill for marketing brochure design, covering everything from requirements gathering, layout design, to mock-up delivery. It uses a "layout-first + mandatory confirmation gate" mechanism to reduce rework risk.

Core Positioning

Applicable scenarios:

Corporate brand brochures, product introduction booklets
Event flyers, service description folds
Investment brochures, enrollment guides, project portfolios

Core deliverables:

Layout design: full unfolded artwork (interior view + exterior view)
Folded mock-up: rendering that simulates the actual folded state
Lifestyle mock-up: real-world usage shots (held in hand, environment, etc.)

Step 0: Task Planning (Mandatory)

Before any output, call write_todos to set up a task plan that includes at least:

Requirements alignment and fold-type confirmation
Layout design generation and iteration
Layout confirmation gate and mock-up output
Lifestyle mock-up generation and final delivery

Execution rules:

Only one task may be in_progress at a time; the rest are pending or completed.
Update write_todos status as soon as each phase finishes.
When the user asks for rework or new assets, add or re-order tasks and return to the corresponding phase.

Adaptive Execution Flow

Drive the work forward dynamically based on the request type:

Request Type	Execution Flow
Full brochure	Confirm fold type and content framework → produce layout → user confirms → export mock-ups
Single page	Generate the requested page first → suggest filling in the missing pages to form a complete piece
Vague request	Clarify the fold type first (tri-fold / bi-fold / Z-fold, etc.) → then proceed
Mock-up only	Check whether a confirmed layout already exists; if not, produce and confirm the layout first, then output the mock-ups

Critical gate:

Once the layout is generated, you must wait for the user's explicit approval before moving on to mock-up production.

Brochure Types and Output Specs

Tri-Fold (most common)

Output: 6 panels (3 exterior + 3 interior)
Use cases: product introduction, service overview, corporate promotion

Bi-Fold

Output: 4 panels
Use cases: event programs, menus, brief introductions

Z-Fold

Output: 6 panels unfolded in sequence
Use cases: step-by-step guides, timelines, process descriptions

Gate-Fold

Output: 4+ panels with a dramatic central reveal
Use cases: premium launches, luxury brands

Accordion Fold

Output: 6–8 panels unfolded progressively
Use cases: maps, extended timelines

Saddle-Stitched Booklet

Output: 8+ pages bound into a booklet
Use cases: product catalogs, annual reports

Tri-Fold Delivery Standard (default example)

The layout must include:

Exterior view (folded state): back panel → cover → inner flap
Interior view (unfolded state): inner left → inner middle → inner right

Panel	Core Content
Cover	Logo, hero visual, headline
Inner flap	Brief introduction, suspense hook
Inner left	Company story, background info
Inner middle	Core value proposition, key advantages
Inner right	Product features, call to action
Back panel	Contact info, social links, copyright

Image Generation Specs

Default aspect ratio: 4:3

Step 1: Layout Design (must be completed first)

Search for brochure styling references that match the user's request and feed them in as layout inputs.
Generate the full unfolded layout (interior + exterior) as the single source of truth for every downstream mock-up.
The interior-view prompt must include these structural keywords:

- No background - No white border - Flat 2D - Edge-to-edge - No perspective shadow or margin - All three panels in a single image, filling the canvas

Step 1.5: User Confirmation (mandatory gate)

Show the layout and ask explicitly:

- "Does this layout meet your requirements? I'll move on to mock-ups once you confirm."

If the user requests changes: return to Step 1 and iterate until they approve.
Only after explicit approval may you proceed to Step 2.

Step 2: Folded Mock-Ups (requires Step 1 approval)

Based on the approved layout, output:

Standing: Z-folded standing on a white surface, cover prominent
Flat-laid: partially unfolded, top-down view
Stacked: 2–3 brochures stacked at varied angles

Step 3: Lifestyle Mock-Ups (based on Step 1)

Based on the approved layout, output:

Held in hand: first-person POV, brochure open in hand
Lifestyle: third-person POV, mid-close shot of someone reading
Environment: placed on a reception desk, booth, or public space

Consistency requirements:

When generating Step 2 and Step 3 images, you must feed the approved layout in as a reference image.
The fold type must stay consistent (a tri-fold layout can only produce tri-fold mock-ups).

Key Design Parameters

Color rules:

Follow the 60-30-10 color rule
Cover prefers the brand primary color
The CTA uses the accent color

Mandatory information:

The back panel must include the copyright notice and contact info
Regulated industries should include compliance disclaimers

User Alignment Question Templates

Before generating, prefer to align on:

"Which fold type do you need? Tri-fold is the most common choice and fits most scenarios."
"What's the brochure's main purpose? (Product promo / company intro / event)"
"Which information do you want to highlight? I can plan content distribution per panel."
"Do you have ready-made copy, or should I draft from a description?"
"Any brand colors or reference designs? You can upload images so I understand your style preference."
"Overall style preference: minimal corporate / energetic / premium luxury?"
"I'll generate the layout first and only move to mock-ups after your confirmation — does that work?"

Iterative Improvement Guidance

When the user is unsatisfied, lead with these questions to locate the change:

"Which panel needs adjustment — cover / interior / back?"
"Is it mainly the color palette, layout, or content expression?"
"Can you describe the desired outcome or upload a reference image?"

Execution Strategy Summary

Plan before execute: lock in fold type and content framework first.
Layout-first principle: every mock-up must be based on the approved layout.
Mandatory confirmation gate: do not enter the mock-up phase before layout approval.
Reference consistency: mock-up generation must reference the approved layout to ensure visual unity.

🛠️ 执行与生成指南 (CRITICAL EXECUTION INSTRUCTIONS)

你是可以执行终端命令的智能 Agent！

【严格禁止行为】

严禁：将提示词保存到任何文件中（如 txt, md）。
严禁：要求用户自己去第三方平台（如 Midjourney）生成图片。
严禁：一次性批量生成所有图片，或一次性执行多个命令。

【必须遵循的交互与执行流程】 你必须严格分步执行，并在每一步停下来等待用户回复：

第一步：主动收集需求。当用户提出需求时，不要做任何设计和生成，先向用户提问（如产品特点、目标人群、想要几张图等）。必须等待用户回答。
第二步：输出草案并请求确认。根据用户的回答，制定套图计划，并输出第一张图的提示词草案。询问用户：“是否确认这个提示词，可以开始生成第一张图了吗？” 必须等待用户回答“确认”。
第三步：单次执行终端命令。用户确认后，你必须使用终端执行命令（如 dlazy seedream-4.5 --prompt "..."），每次只能执行一个生成命令。重要：必须使用同步命令，绝不要在命令末尾加 &，绝不要使用 &&，这是在 Windows PowerShell 下运行！
第四步：交付与循环。命令返回结果后，把图片 URL 发给用户，并询问“对这张满意吗？我们可以继续生成下一张了吗？”。收到确认后再继续下一步。

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明，方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用；具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

86.28%

按下载量换算5,856

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置，应进入高风险复核队列，默认不自动发布。

安装前确认

本站仅展示第三方公开信息，不托管安装包，不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。当前只有一个来源，正式发布前建议补源仓库或其他目录站核验。

来源信息

GitHub 仓库

github.com

/dlazyai/image-marketing-brochure

SKILL.md 来源

clawhub.ai

/dlazyai/image-marketing-brochure

继续浏览同类 Skills

更多图像处理 Skills（1,562）返回 Skills 目录

上一个 Skill

image-manipulation-image-magick（图像处理图像魔法）

用于辅助图像生成、图片编辑、视觉素材处理或图像模型工作流。它适合让 Agent 根据文本生成图片、处理背景、整理视觉提示词或调用相关图像工具。使用时需要确认输入图片、版权来源、输出格式和模型限制；涉及人物、品牌、商品或公开展示素材时，应额外核对授权、真实性和内容合规边界。

下一个 Skill

image-metadata-tool（图像元数据工具）

用于辅助数据整理、表格处理、CSV/Excel 分析、指标计算和图表准备。它适合让 Agent 清洗字段、汇总数据、发现异常、生成统计口径或把分析结果转成可读说明。使用时需要确认数据来源、字段含义和时间范围，避免把样本数据当全量事实；涉及敏感数据、导出文件或批量写回时，应先确认权限和脱敏边界。