CCM
/Skills
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
ppdbxdawj avatar

Seedream Image

ppdbxdawj/seedream-image-skill
248 installs5 stars
Summary

This is a comprehensive workflow tool for ByteDance's Seedream image generation API. You describe what you want, it formats a structured prompt following Seedream's quirks (quoted text for rendering, specific style keywords, four-part composition rules), shows you the prompt for review, then runs generate.py to hit the API and download results to output/. Covers the full range: text-to-image, editing, multi-image fusion, character consistency across frames, and specialized templates for e-commerce, posters, and knowledge cards. The prompt engineering reference is extensive, with Chinese and English style dictionaries, lighting terms, and scene-specific templates. Useful if you're working with Jimeng AI or the Volcengine Ark API and want structured prompt generation instead of freeform guessing.

Install to Claude Code

npx -y skills add ppdbxdawj/seedream-image-skill --skill seedream-image --agent claude-code

Installs into .claude/skills of the current project.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
ego lite browserego lite browser
ego lite browser
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
CodeHealth MCP ServerCodeHealth MCP Server
CodeHealth MCP Server
Protect your code quality, stop the AI slop.
Try For Free →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
ego lite browserego lite browser
ego lite browser
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
CodeHealth MCP ServerCodeHealth MCP Server
CodeHealth MCP Server
Protect your code quality, stop the AI slop.
Try For Free →
Files
SKILL.mdView on GitHub

Seedream Image Assistant | Seedream 即梦 图像助手

Seedream 5.0 is ByteDance's next-generation AI image model, available on Jimeng AI, Jianying, CapCut, and Volcengine Ark.

Seedream 5.0 是字节跳动推出的新一代 AI 图像生成模型,已在即梦AI、剪映、CapCut、火山方舟上线。

Core Capabilities | 核心能力

CapabilityDescription
Real-time Web SearchAuto-fetches trending info when prompt contains timely keywords
Multi-step ReasoningInterprets abstract concepts (e.g. "serene tech feel" → desaturated + clean lines + cold light)
Multi-round EditingIterative refinement: local edits, style transfer, element add/remove, text rendering
High ResolutionNative 2K, AI-enhanced 4K, 2-5 second generation
Character ConsistencyMaintains face, clothing, pose across multiple images (storyboard-ready)
Text Rendering99%+ accuracy for Chinese/English text, use quotes for best results

提示词结构

基础结构(文生图)

[主体描述] + [行为/动作] + [环境/背景] + [材质/质感] + [光影效果] + [构图要求] + [风格关键词]
  • 主体+行为+环境用自然语言描述
  • 风格/色彩/光影/构图用短词点缀
  • 文字内容用引号标注,如:"Hello World"

四段式结构(进阶)

主体 → 环境 → 材质/质感 → 光影

编辑提示词公式

变化动作 + 变化对象 + 变化特征
示例:"将骑士的头盔变为金色"

风格词汇库

写实摄影

  • 写实电影剧照 商业摄影 纪实摄影 超写实 RAW 原片质感
  • 镜头:85mm定焦 35mm广角 长焦压缩感 鱼眼镜头
  • 光线:伦勃朗光 环形光 分割光 黄金时刻暖光 蓝调时刻冷光 霓虹光

动漫/插画

  • 日漫:吉卜力动画风格 新海诚风格 日系少女漫画 赛璐璐质感
  • 欧美:美漫风格 DC漫画风格 欧美写实人物 Pop Art波普艺术
  • 中国:国潮插画 水墨画风格 中式工笔画 赛博国风
  • 其他:像素风格 低多边形 扁平插画 厚涂油画 水彩手绘

设计/商业

  • 极简主义 包豪斯风格 磨砂玻璃质感 高质感金属 赛博朋克
  • 电影海报级别 品牌VI视觉 信息图Infographic 知识卡片

光影修饰词

  • 戏剧性侧光 柔和漫射光 高对比度 低饱和度 莫兰迪色调
  • 赛博霓虹 暖橙调 冷蓝调 胶片颗粒感

常用提示词模板

人物写实

[性别年龄外貌],[服装描述],[表情神态],[环境背景],85mm定焦,自然光,写实电影剧照风格,超高清,细节丰富

风景/场景

[场景描述],[时间/天气],[光线描述],[构图],[风格词],电影感构图,8K超清

知识卡片(完整模板)

生成一张[格式/载体]风格的图像,向[目标受众]解释/展示"[核心概念]"。
图像需具备[风格特征A]、[风格特征B]和[排版要求C],整体感觉类似于[熟悉参照物]。

品牌/海报(留白模板)

[视觉主体描述],[材质描述],[光影效果],
所有视觉主体集中在画面[左/右]侧,为[右/左]侧留出大面积干净的背景区域,方便后期排版添加文字。
背景:[背景描述]

连续分镜(角色一致性)

参考[图1]的面部和发型,将其更改为[场景风格]装束,
生成N张连续的[场景描述]分镜图,[风格],需要在一个场景中,连续动作。

电商产品

为这件[产品]创建[平台]风格的展示图,风格类似于[品牌参照],
背景简洁,突出产品质感,专业商业摄影

场景速查

场景提示词关键词注意事项
头像头像图标 正方形构图 纯色背景指定风格参考图效果更好
知识卡片信息图 知识图谱 排版清晰说明目标受众和核心概念
PPT背景留白构图 偏向[左/右]侧 哑光背景强调一侧留白供排版
角色Cos保持人脸不变 写实质感服饰 相同姿势上传原图+目标角色图
手帐日记手写字体 纸张纹理 拼贴风格 米黄底色告知日期和天气增加氛围
玻璃图标磨砂玻璃质感 渐变色 C4D OC渲染纯白背景+简洁构图
海报设计电影海报级别 戏剧光 大面积留白明确文字内容和位置
护身符/国潮山海经 国潮票据 水墨 篆刻印章可加入"愿望"文字增加情感

进阶技巧

1. 联网触发

提示词中含时效词时自动联网:2026年流行色 最新款XX 今年XX趋势 米兰冬奥会

2. 图像编辑

  • 指定区域:"将图中[区域]替换成..."
  • 风格迁移:"保持内容不变,改成[风格]"
  • 元素控制:"为画面增加/移除[元素]"
  • 光影调整:"将画面光影改为[光线名称]"
  • 滤镜添加:"为画面添加[滤镜名]滤镜"
  • 妆容修改:"为角色添加[妆容描述]"

3. 文字渲染

将需要生成的文字放入引号:图片中央写着"创意无界"

4. 构图控制

  • 黄金分割:三分法构图 黄金螺旋
  • 视角:俯视鸟瞰 仰视 正面平视 45度斜角
  • 留白:大量留白 简洁背景 主体偏[方向]

5. 多图融合

最多支持 14 张参考图,融合时说明参考哪张图的哪个元素: 参考图1的风格,图2的色调,图3的人物姿势

6. 组图生成

触发词:一系列 组图 生成N张连续的 分镜图

负向提示词写法

明确说明不需要的元素,放在提示词末尾:

  • 背景简洁,不要杂乱元素
  • 保持人脸,不要改变面部特征
  • 不要文字水印
  • 不要过度曝光

平台入口 | Platforms

平台URL说明
即梦AI Jimeng AIhttps://jimeng.jianying.com/主站,每日约 20 次免费 2K
火山方舟 Volcengine Arkhttps://console.volcengine.com/ark企业 API,支持 4K
剪映 JianyingApp StoreAI 绘画 → Seedream 5.0
CapCut (海外)App StoreAI Image

API 生图脚本 | Image Generation Script

generate.py 调用即梦 4.0 API,图片自动下载到 --output-dir(默认 output/)。

环境准备

在 generate.py 同目录建 .env 写入 VOLC_ACCESSKEY、VOLC_SECRETKEY,或终端 export。脚本自动读取同目录 .env。pip install -r requirements.txt。

用法

# 文生图
python generate.py --prompt "一只猫在花园里玩耍,水彩风格"

# 图像编辑(输入参考图)
python generate.py --prompt "将背景换成海滩" --image-urls "https://example.com/photo.jpg"

# 指定分辨率 + 强制单图
python generate.py --prompt "电商主图,产品特写" --width 2560 --height 1440 --force-single

# 组图生成
python generate.py --prompt "生成4张分别关于春夏秋冬的盲盒组图"

在 Skill 工作流中使用

  1. 按本 Skill 规则生成 prompt,用户确认。
  2. 发起前软提示:默认 1 张,需多张(组图)则加 --no-force-single 或保留「组图」「一系列」等词。
  3. 执行 python generate.py --prompt "<confirmed_prompt>"(组图时加 --no-force-single)。
  4. 脚本轮询完成后图片在 output/,展示路径与 URL。

参数说明

参数说明
--prompt必填,提示词
--image-urls输入参考图 URL(最多 10 张)
--width / --height指定输出宽高(需同时传),不传则智能适配
--size输出面积(像素),默认 2K(2048×2048)
--scale文本影响程度 0~1(默认 0.5),越大文本越强
--force-single只输出 1 张图(默认)
--no-force-single允许多张(组图),由模型根据提示词决定张数
--watermark添加 AI 水印
--output-dir生成图片保存目录(默认 output/),URL 与 base64 均会写入此处

References | 参考文件

  • Detailed examples & use cases → examples.md
  • Official docs, API params, size chart, full style dictionary → reference.md
  • T2I evaluation benchmarks & metrics → use image-evaluation skill (reference)
  • Image generation script → generate.py
  • Dependencies → requirements.txt
Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
ego lite browserego lite browser
ego lite browser
Fastest browser for AI agents to run web automation tasks, always free.
Download Free life-time →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Open Steps
Open Steps
Free an open-source skills that make AI coding agents easier to understand, verify, and control.
Download for free →
AppSignal
AppSignal
Monitor with ease. Code with confidence.
Start Free Trial →
Agent, connect blockchain
Agent, connect blockchain
Connect your Claude agent to live crypto prices and trading routes via 1inch
Get the MCP →
Granola, the best AI meeting recorder
Granola, the best AI meeting recorder
Notes, actions and memory. Without a meeting bot. First month 100% off.
Download for free →
CodeHealth MCP ServerCodeHealth MCP Server
CodeHealth MCP Server
Protect your code quality, stop the AI slop.
Try For Free →
First SeenJun 3, 2026
View on GitHub

Recommended

juliusbrussee avatar
caveman

juliusbrussee/caveman

Ultra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
443.2k
98.9k
mattpocock avatar
grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.
896.5k
221k
shadcn avatar
improve

shadcn/improve

Survey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on source code — never implements, fixes, or refactors anything itself. Use when asked to audit a codebase, find improvement opportunities (bugs, security, performance, test coverage, tech debt, migrations, DX), suggest features or where to take the project next (roadmap, product direction), or generate handoff plans for another agent to implement.
29.7k
8.9k
obra avatar
systematic-debugging

obra/superpowers

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
229.2k
273.5k
forrestchang avatar
karpathy-guidelines

forrestchang/andrej-karpathy-skills

Behavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.
17.9k
191.7k
vercel-labs avatar
find-skills

vercel-labs/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
3M
28.2k