user-customization
指导用户如何自定义 Trae Skills 的配置，包括覆盖角色设定、调整技术偏好和定义全局规则。
Best use case
user-customization is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
指导用户如何自定义 Trae Skills 的配置，包括覆盖角色设定、调整技术偏好和定义全局规则。
Teams using user-customization should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/99-meta-customization/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How user-customization Compares
| Feature / Agent | user-customization | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
指导用户如何自定义 Trae Skills 的配置，包括覆盖角色设定、调整技术偏好和定义全局规则。
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.
SKILL.md Source
# User Customization & Preferences
本 Skill 旨在帮助用户根据个人或团队的需求，定制 Trae 的行为模式。通过创建 `USER_PREFERENCES.md`，你可以让所有的 Skill 和 Agent 都遵循你的特定偏好。
## ⚙️ 配置文件机制
Trae 会优先寻找并遵循以下位置的配置文件：
* `.trae/USER_PREFERENCES.md` (推荐)
### 配置文件模板
你可以直接复制以下内容到 `.trae/USER_PREFERENCES.md`：
```markdown
# User Preferences
## 1. 技术栈偏好 (Tech Stack)
* **CSS Framework**: Tailwind CSS (严禁使用 CSS Modules 或 Styled Components)
* **State Management**: Zustand (React), Riverpod (Flutter)
* **Testing**: Vitest (不使用 Jest)
* **Language**: TypeScript (Strict Mode enabled)
## 2. 交互风格 (Communication Style)
* **Language**: 请始终使用**中文**回复，但技术术语保留英文。
* **Detail Level**: 我是资深开发者，请直接给代码，少讲废话。
* **Emoji**: 禁用 Emoji，保持职业化。
## 3. 角色覆盖 (Role Overrides)
* **@Office Architect**:
* 在处理 Excel 时，优先使用 pandas 而不是 openpyxl。
* **@DevOps Engineer**:
* 生成的 K8s Manifest 必须包含 Resource Limits。
## 4. 禁令 (Constraints)
* 严禁使用 `any` 类型。
* 严禁创建 `.env` 文件（使用 config map）。
```
## 🔄 它是如何工作的？
1. **全局生效**: `universal-dev-team` 在调度角色时，会先读取此文件。
2. **角色感知**: 只要你在 Trae 中定义 Agent 时，在 System Prompt 的开头加上一句：
> "Always check .trae/USER_PREFERENCES.md before answering."
那么所有的手动配置 Agent 都会遵循这些规则。
## 🛠️ 高级用法：自定义 Skill
如果你需要更深度的定制（例如完全重写 React 规范），建议：
1. **Fork**: 复制 `03_Developer_ReactBestPractices` 目录到 `Custom_React_Skills`。
2. **Modify**: 修改其中的 `SKILL.md` 和 `rules/`。
3. **Register**: 更新 `universal-dev-team/SKILL.md` 中的路由表，指向你的新目录。
---Related Skills
Clarify Epic/Feature/UserStory/Task ticketing guidance in SKILL
No description provided.
ux
This AI agent skill provides comprehensive guidance for creating professional and insightful User Experience (UX) designs, covering user research, information architecture, interaction design, visual guidance, and usability evaluation. It aims to produce actionable, user-centered solutions that avoid generic AI aesthetics.
lets-go-rss
A lightweight, full-platform RSS subscription manager that aggregates content from YouTube, Vimeo, Behance, Twitter/X, and Chinese platforms like Bilibili, Weibo, and Douyin, featuring deduplication and AI smart classification.
whisper-transcribe
Transcribes audio and video files to text using OpenAI's Whisper CLI, enhanced with contextual grounding from local markdown files for improved accuracy.
chrome-debug
This skill empowers AI agents to debug web applications and inspect browser behavior using the Chrome DevTools Protocol (CDP), offering both collaborative (headful) and automated (headless) modes.
thor-skills
An entry point and router for AI agents to manage various THOR-related cybersecurity tasks, including running scans, analyzing logs, troubleshooting, and maintenance.
modal-deployment
Run Python code in the cloud with serverless containers, GPUs, and autoscaling using Modal. This skill enables agents to generate code for deploying ML models, running batch jobs, serving APIs, and scaling compute-intensive workloads.
ontopo
An AI agent skill to search for Israeli restaurants, check table availability, view menus, and retrieve booking links via the Ontopo platform, acting as an unofficial interface to its data.
tech-blog
Generates comprehensive technical blog posts, offering detailed explanations of system internals, architecture, and implementation, either through source code analysis or document-driven research.
astro
This skill provides essential Astro framework patterns, focusing on server-side rendering (SSR), static site generation (SSG), middleware, and TypeScript best practices. It helps AI agents implement secure authentication, manage API routes, and debug rendering behaviors within Astro projects.
vly-money
Generate crypto payment links for supported tokens and networks, manage access to X402 payment-protected content, and provide direct access to the vly.money wallet interface.
grail-miner
This skill assists in setting up, managing, and optimizing Grail miners on Bittensor Subnet 81, handling tasks like environment configuration, R2 storage, model checkpoint management, and performance tuning.