AITOPAI热报
Products

Claude Code 桌面端新增自定义主题功能

TestingCatalog@testingcatalog
Post
View the post
Why we picked it

Anthropic 给桌面版 Claude Code 加了自定义主题，直接用一句话告诉 Claude 你想要的界面样式就行，不用手动改配置。天天盯着终端写代码的人可以试试，配色顺眼了盯着看八小时也没那么累。

Anthropic 为桌面端 Claude Code 推出自定义主题功能，用户可以用自然语言描述想要的应用外观，由 Claude 生成匹配的界面样式。该功能随周五功能更新一同上线，目前处于早期阶段，官方提示需要用户实际测试反馈。

Body

具体使用方式是在 Claude Code 中直接说明偏好，例如配色、布局风格等，模型会据此调整桌面应用的显示效果。相比手动修改配置文件，这个流程把界面定制变成了一段对话。

Claude Code 此前主要聚焦编码与终端工作流，桌面端加入外观定制属于开发者工具的体验层面改进。对长期使用该工具的开发者来说，个性化设置有助于降低长时间编码的视觉疲劳，也延续了 Anthropic 通过小步快跑方式迭代产品的节奏。

Original · TestingCatalog

ANTHROPIC 🔥: Claude Code on desktop now supports custom themes!

Users can tell Claude how they want an app to look, so it can tailor it to their preferences. That needs testing!

Friday feature drop 👀 https://t.co/KWg9Gv3Y3n

Industry Coordinates & Source Verification

This report is categorized under AITOP's "Products" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include Claude Code, Anthropic, developer tools, coding assistants.

Source attribution: curated from TestingCatalog (@testingcatalog).

#Claude Code#Anthropic#developer tools#coding assistants

Keep reading

Recent stories with the same tag or section
ProductsBuildersSelected00:01
Chinese content谷歌发布Modern Web Guidance，AI前端代码现代规范通过率从56%提升到95%

谷歌开源的这套工具直接装到Claude Code、Codex、Cursor里就能用，不改模型不改流程，只是让Agent写前端前先查浏览器原生能力和现代CSS规范。被冗余代码和过时写法困扰的前端开发者，可以拿56%到95%这组通过率数据实测一下自己的项目。

#Modern Web Guidance#Claude Code#Codex#Cursor
AIGCLINK@aigclinkSource
ProductsBuildersMulti-source15:06
Chinese contentClaude Code 桌面端支持自定义主题，可改配色和动态背景

Anthropic 给 Claude Code 桌面端加了换肤功能，改配色、加动态背景都行，直接用一句话让 Claude 帮你写主题配置就行。和 Cursor 那种固定界面风格不同，这个更像 QQ 秀思路。天天用 Claude Code 写代码、想给终端换心情的人可以试试。

#Claude Code#Anthropic#coding assistants
Event
shao__meng@shao__mengSource
How-toBuildersSelected12:26
Dotey argues agent UX needs hybrid of main chat and sessions

The framing suggests the next round of differentiation in agent tooling will come from orchestration interfaces, not model quality — a hybrid of routed messaging and task drill-down. Developers designing agent platforms and teams comparing Claude Code with Dots or Grokbot should use this two-axis lens when choosing or building their own coordination layer. Multi-agent workflow teams in ASEAN and China face the same trade-off and can adopt the coordinator-plus-drill-down pattern directly.

#Claude Code#Grokbot#Dots#Agent
宝玉@doteySource