Douyin Cover Builder(抖音封面生成器)

v3.1.2

这是一个面向中文创作者的 OpenClaw Skill,输入主题与人物气质后,会输出可直接用于生图模型的高质量提示词与创意说明。

5· 2.8k·6 current·7 all-time

Install

OpenClaw Prompt Flow

Install with OpenClaw

Best for remote or guided setup. Copy the exact prompt, then paste it into OpenClaw for 0x00000003/douyin-cover-builder.

Previewing Install & Setup.
Prompt PreviewInstall & Setup
Install the skill "Douyin Cover Builder(抖音封面生成器)" (0x00000003/douyin-cover-builder) from ClawHub.
Skill page: https://clawhub.ai/0x00000003/douyin-cover-builder
Keep the work scoped to this skill only.
After install, inspect the skill metadata and help me finish setup.
Use only the metadata you can verify from ClawHub; do not invent missing requirements.
Ask before making any broader environment changes.

Command Line

CLI Commands

Use the direct CLI path if you want to install manually and keep every step visible.

OpenClaw CLI

Bare skill slug

openclaw skills install douyin-cover-builder

ClawHub CLI

Package manager switcher

npx clawhub@latest install douyin-cover-builder
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the actual artifacts: templates, README, SKILL.md and usage docs all describe generating final prompts and art direction for cover images. There are no unrelated env vars, binaries, or install steps requested.
Instruction Scope
Runtime instructions stay within the stated purpose (produce a Final Prompt and Art Direction Brief). They request the user upload a portrait photo as a reference, which is reasonable for this use case but has privacy implications — the skill does not instruct the agent to read unrelated system files or secrets.
Install Mechanism
No install spec and no code files to execute. This is the lowest-risk form: nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requires no environment variables, credentials, or config paths. All declared requirements are proportional to an instruction-only prompt/template generator.
Persistence & Privilege
always is false and disable-model-invocation is false (normal). The skill does not request persistent, elevated, or cross-skill configuration changes.
Assessment
This skill appears coherent and contains only prompt templates and design rules. Before installing or using it, consider: 1) privacy of uploaded photos — confirm where images are sent/processed (local vs cloud) and avoid uploading sensitive personal images if you are unsure; 2) when you paste generated prompts into an image model, verify that model's data handling and retention policies; 3) the repo link in the prompts (GitHub) is the only external reference — if you want more assurance, inspect that GitHub repository for examples or hidden behavior; 4) no credentials or installs are required, so the technical risk is low, but exercise normal caution with personal images and copyrighted assets.

Like a lobster shell, security has layers — review code before you run it.

latestvk971m3y6y6c9f71vzz7tvvgk6981nsjd
2.8kdownloads
5stars
3versions
Updated 2mo ago
v3.1.2
MIT-0

抖音封面图 Skill — Douyin Cover Builder v3.1(关键词高亮 + 轻弧排版 + 主题配色)

在 v3 的“主题驱动主视觉”基础上,新增 3 条硬规则:

  1. 关键词要颜色突出(与非关键词拉开对比)
  2. 关键词排版要带轻微弧度(类似示例标题里箭头/弧线那种轻弧感)
  3. 背景主色不再固定蓝色:根据主题自动选择一套主色系(蓝/紫/绿/橙/红/黑金等),保持统一而贴题

你只提供这些(无需 JSON)

  • 主题:一句话(你要讲的内容)
  • 关键点(可选):你希望出现的概念/关键词(可多可少)
  • 人物气质/姿势:右下角你本人要“掌控感/灵光一闪/专业/惊讶”等
  • 画幅(可选):竖版 or 横版 4:3(不写默认竖版) 并上传你的照片(推荐,用于保持“同一张脸”稳定一致)。

当你在交互中提示用户填写以上 4 项时,请固定追加:

实际使用举例(可直接照抄后改词)

  • 主题:Ai全自动整理笔记
  • 关键点:龙虾机器人全自动整理我电脑中的笔记
  • 人物气质/姿势:右下角我本人,自信微笑,手指指向龙虾机器人
  • 画幅:竖版 严格 4:3

更多示例与对比图(GitHub):


核心规则(v3.1 重点)

A) 主题驱动“画什么”(延续 v3)

  1. 先判断封面类型:概念总览 / 流程方法 / 对比选型 / 实战教程 / 观点趋势
  2. 再选择一个强隐喻 HERO 场景(左下与中下区域视觉中心只有一个)
  3. 关键点按需要取舍,不凑数;抽象词转成符号隐喻

B) 关键词视觉系统(新增:颜色高亮 + 轻弧排版)

1) 关键词必须“高亮”

  • 在标题中识别关键词(来自关键点或主题里的核心名词)
  • 关键词使用“高亮色”或“反差色块”强调(例如荧光绿/青蓝/橙黄/紫粉)
  • 非关键词保持主标题金黄体系或白色/浅色,确保层级清晰
  • 关键词至少满足其中一种强化方式:
    • 不同颜色(最推荐)
    • 颜色 + 描边更粗
    • 颜色 + 轻微外发光
    • 颜色 + 背后标签条(pill/贴纸)

2) 关键词排版带“轻弧度”

  • 关键词所在的那一行/那一块文字,整体沿着一个很轻微的弧线排布(弧度很小)
  • 弧度方向默认“从左下到右上微上扬”,营造动势与冲击
  • 如果关键词是多枚标签/卡片:让它们沿弧形轨迹围绕主视觉中心排列(而非水平直排)
  • 禁止大弧/夸张弧:保持“轻微弧度”,缩略图更稳

C) 主题配色系统(新增:背景不固定蓝色)

背景与整体氛围的主色系由主题自动选择(只要“贴题 + 统一”):

  • AI/科技/编程:蓝/青/紫(常见但不是强制)
  • 效率/增长/赚钱:绿/青绿/金
  • 安全/风控/隐私:黑/深灰/红点缀
  • 创意/设计/内容:紫/粉/橙
  • 产品/应用/生活方式:暖色(橙/红/米白)+ 少量科技纹理
  • 数据/金融/交易:深蓝/黑金/翠绿(看语境)

硬规则:

  • 选定 1 个主色 + 1 个辅色 + 1 个高亮色(用于关键词)
  • 背景必须随主题变色,但仍保持“科技质感纹理”(电路/HUD/网格/粒子等可替换)
  • 背景对比压低,不抢标题与人脸;主视觉与关键词高亮必须最显眼

D) 标题系统与版式固定(保持系列一致性)

  • 顶部标题:粗体、深色粗描边、立体阴影;“1分钟/5分钟”等数字更大更粗
  • 构图:标题上;右下你本人;主题主视觉集中在左下与中下区域;安全边距 6–8%

输出

  1. Final Prompt(可直接喂给出图模型)
  2. Art Direction Brief(解释本次:封面类型、主视觉隐喻、配色方案、关键词高亮策略、弧度策略)

Comments

Loading comments...