douyin-cover-builder
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。
About this skill
This skill, Douyin Cover Builder v3.1, is designed specifically for Chinese content creators aiming to produce visually striking and consistent cover images for their Douyin videos. By taking simple inputs such as the video's theme, key concepts, the creator's desired temperament or pose, and preferred aspect ratio, the skill outputs ready-to-use prompts for AI image generation models along with a detailed art direction brief. It integrates sophisticated design principles like dynamic keyword highlighting with subtle curved typography, a theme-driven primary color system, and fixed layout elements to ensure professional and engaging results. Users benefit from the skill's ability to automate complex design decisions, such as selecting appropriate color palettes based on the topic, ensuring keywords stand out effectively, and maintaining a consistent branding aesthetic across multiple covers. This helps creators save time and achieve a polished look without needing extensive graphic design expertise. The skill's focus on "theme-driven main visuals" and "keyword visual system" ensures that the generated covers are not only attractive but also effectively communicate the video's core message. The primary goal is to empower creators to generate high-quality, professional-looking Douyin covers that captivate viewers and enhance their brand identity. It translates abstract ideas and branding requirements into concrete visual instructions, bridging the gap between creative vision and AI-powered image generation.
Best use case
The primary use case is for Chinese Douyin content creators who want to quickly and consistently generate high-quality, branded cover images for their videos using AI art models. It's especially beneficial for those who lack graphic design skills or time, but still need professional-looking thumbnails that adhere to specific aesthetic and branding guidelines, ensuring their content stands out on the platform.
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。
A set of ready-to-use, high-quality text prompts for AI image generation models and a comprehensive art direction brief, designed to create engaging Douyin cover images tailored to the user's specific inputs and branding.
Practical example
Example input
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
Example output
Final Prompt: Vertical Douyin cover, strict 4:3, high contrast, cyberpunk aesthetic. Top bold title "AI全自动整理笔记" (AI Automated Note Organization) with "AI" and "自动" in vivid neon green with subtle outer glow, remaining text in bright white with dark outline. Keywords are slightly arced upwards from left-bottom to right-top. Main visual: A sophisticated lobster-like robot meticulously organizing digital notes on a holographic interface, centered on the left-middle. Background: Dark blue-purple with subtle circuit board texture and particle effects, ensuring keywords and main visual pop. Right-bottom: A confident person (user's uploaded photo) smiling, pointing towards the lobster robot. Overall color scheme: Primary dark blue/purple, secondary teal accents, neon green highlight for keywords. Art Direction Brief: Cover Type: Concept Overview. Main Visual Metaphor: A lobster-robot symbolizing automated, precise organization, embodying the "AI Automated Note Organization" theme. Color Scheme: AI/Tech theme suggests a primary dark blue/purple, with teal as a secondary accent. Keywords are highlighted in neon green for maximum impact. Background texture is subtle tech-circuitry. Keyword Highlighting Strategy: "AI" and "自动" are identified as core keywords. They are rendered in neon green with an outer glow, differentiating them from the main title text (white with dark outline) to ensure clear visual hierarchy. Curvature Strategy: The main title line containing the highlighted keywords is given a subtle upward arc from left to right, adding dynamism without being overly dramatic, suitable for a thumbnail.
When to use this skill
- Generating professional and eye-catching Douyin cover images.
- Ensuring consistent branding and visual style across video content.
- Translating video themes and key points into effective visual prompts for AI art.
- Saving time and effort in designing high-quality thumbnails for Chinese social media.
When not to use this skill
- For creating general-purpose images unrelated to Douyin cover art.
- When requiring extremely detailed, manual control over every visual element.
- If you do not use AI image generation models (e.g., Midjourney, Stable Diffusion).
- For platforms with vastly different visual design conventions than Douyin.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/douyin-cover-builder/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How douyin-cover-builder Compares
| Feature / Agent | douyin-cover-builder | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | easy | N/A |
Frequently Asked Questions
What does this skill do?
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。
How difficult is it to install?
The installation complexity is rated as easy. You can find the installation instructions above.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
Best AI Skills for ChatGPT
Find the best AI skills to adapt into ChatGPT workflows for research, writing, summarization, planning, and repeatable assistant tasks.
AI Agent for YouTube Script Writing
Find AI agent skills for YouTube script writing, video research, content outlining, and repeatable channel production workflows.
SKILL.md Source
# 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： - 更多示例与对比图（GitHub）： - https://github.com/0x00000003/douyin-cover-builder ### 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）： - https://github.com/0x00000003/douyin-cover-builder --- ## 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）
Related Skills
Go-to-Market Strategy Builder
Build a complete GTM plan for product launches, market entries, or expansion plays. Covers positioning, channel strategy, pricing, launch timeline, and success metrics.
IT Disaster Recovery Plan Generator
Build production-ready disaster recovery plans that actually get followed when things break.
Debt Collection & Recovery Playbook
Generate compliant debt recovery strategies, collection letter sequences, and payment plan frameworks.
Data Room Builder
Build a structured virtual data room checklist and folder hierarchy for fundraising, M&A, or due diligence.
AI Governance Policy Builder
Build internal AI governance policies from scratch. Covers acceptable use, model selection, data handling, vendor contracts, compliance mapping, and board reporting.
douyin-posting
协助用户将本地或用户提供的视频发布到抖音账号。包含上传流程说明、开放平台 API 使用指引及发布前检查。Use when: 用户要发抖音、上传视频到抖音、把视频发到抖音、post to Douyin、抖音发布。NOT for: 抖音视频下载、抖音数据分析、非发布类抖音操作。
doppel-block-builder
Place MML blocks in Doppel worlds. Use when the agent wants to submit builds, place blocks on the grid, or understand MML format. Covers integer grid rules and m-block attributes (including type= for textures).
agentic-mcp-server-builder
Scaffold MCP server projects and baseline tool contract checks. Use for defining tool schemas, generating starter server layouts, and validating MCP-ready structure.
sql-to-bi-builder
Convert a markdown file containing SQL queries (for example `sql.md`) into a BI dashboard specification and UI scaffold. Use when user asks to build analytics dashboards, chart pages, or BI interfaces from existing SQL statements, including query parsing, metric/dimension inference, chart recommendation, filter design, and layout generation.
session-recover
短期记忆恢复技能。用于快速回顾当前 session 或上一个 session 的完整内容。适用于：想知道"这次 session 聊了什么"、session 被意外重置后需要恢复上下文、或想提取对话精华。
Skill Builder — Meta-Skill for Creating Skills
## Metadata
hardcover
Query reading lists and book data from Hardcover.app via GraphQL API. Triggers when user mentions Hardcover, asks about their reading list/library, wants book progress, searches for books/authors/series, or references "currently reading", "want to read", or "books I've read". Also use for syncing reading data to other systems (Obsidian, etc.) or tracking reading goals.