global-config
Compare original and translation side by side
🇺🇸
Original
English🇨🇳
Translation
ChineseGlobal Configuration
全局配置
Base settings for all Alicoder001 skills.
所有Alicoder001技能的基础设置。
Interaction Defaults
交互默认规则
- Mirror the user's tone and technical depth.
- Ask up to 2 clarifying questions when requirements are ambiguous.
- Confirm constraints that affect output (stack, environment, timeline).
- Default conversation to the user's language.
- Keep reusable skill artifacts (, scripts, references) in English unless explicitly requested otherwise.
SKILL.md
- 匹配用户的语气和技术深度。
- 当需求不明确时,最多提出2个澄清问题。
- 确认会影响输出结果的约束条件(技术栈、环境、时间线)。
- 默认使用用户的语言进行对话。
- 可复用的技能工件(、脚本、参考资料)默认使用英文,除非用户明确要求其他语言。
SKILL.md
Project Context Detection
项目上下文检测
NEVER ask these questions:
- "What programming language?"
- "What is your tech stack?"
- "Do you want guided setup?"
- "What framework are you using?"
Instead, auto-detect from these files:
| File | What to Detect |
|---|---|
| Dependencies, scripts, framework |
| TypeScript project |
| Full project context |
| Agent rules |
| Next.js project |
| Vite project |
| NestJS project |
Detection logic:
- Check if context files exist and use them silently.
- Check dependencies and infer stack.
package.json - If no context found, proceed with reasonable defaults for immediate task execution.
- If context is missing and the task clearly needs project-level setup, trigger recovery flow with one short confirmation.
project-init
Routing boundary (important):
- sets defaults and routing only.
global-config - If setup/context recovery intent is detected, delegate to instead of handling setup questions here.
project-init
Rule: If you cannot detect, proceed with the task. Do not block.
绝对不要询问以下问题:
- "使用什么编程语言?"
- "你的技术栈是什么?"
- 是否需要引导式设置?"
- "你使用什么框架?"
取而代之,从以下文件自动检测:
| 文件 | 检测内容 |
|---|---|
| 依赖项、脚本、框架 |
| TypeScript 项目 |
| 完整项目上下文 |
| Agent 规则 |
| Next.js 项目 |
| Vite 项目 |
| NestJS 项目 |
检测逻辑:
- 检查上下文文件是否存在,并静默使用这些文件的内容。
- 检查的依赖项,推断技术栈。
package.json - 如果未找到上下文,使用合理的默认值立即执行任务。
- 如果缺少上下文且任务明显需要项目级设置,触发恢复流程,并仅进行一次简短确认。
project-init
路由边界(重要):
- 仅用于设置默认值和路由规则。
global-config - 如果检测到设置/上下文恢复的意图,将任务委托给,而非在此处理设置问题。
project-init
规则:如果无法检测到上下文,继续执行任务,不要阻塞流程。
Language Policy
语言策略
- Do not ask a generic language preference question in normal task flow.
- Exception: setup-style onboarding (for example ) must ask one language confirmation at the start when the first user message is non-English.
project-init - For Uzbek first messages in setup/recovery, use:
O'zbekcha davom etamizmi? - After language is confirmed once, do not repeat the language question in the same setup flow.
- 在常规任务流程中,不要询问通用的语言偏好问题。
- 例外情况:设置式引导(例如)在首次用户消息为非英文时,必须在开始时进行一次语言确认。
project-init - 对于设置/恢复流程中的乌兹别克语初始消息,使用:
O'zbekcha davom etamizmi? - 一旦语言被确认,在同一设置流程中不要重复询问语言问题。
Global Rules
全局规则
Code Style
代码风格
- Prefer TypeScript with strict mode when TypeScript is used.
- Follow naming conventions from .
typescript - Apply mobile-first responsive design for UI work.
- 当使用TypeScript时,优先启用严格模式。
- 遵循TypeScript的命名规范。
- UI工作采用移动优先的响应式设计。
Communication
沟通方式
- Be concise and professional.
- Use code examples for non-trivial explanations.
- Format responses in markdown.
- 简洁专业。
- 对于非浅显的说明,使用代码示例。
- 用Markdown格式排版回复内容。
Local Skill Capture
本地技能保存
- Support both explicit save triggers: and
@save-skill.skillga saqla - Treat these triggers as a request to persist project-specific guidance as a local skill.
- Ask one short confirmation before writing: .
Save this as a local skill? (yes/no) - Save using the standard local path: .
.agents/skills/local/<skill-name>/SKILL.md - If a matching local skill already exists, update/merge it instead of creating duplicates.
- 支持两种显式保存触发指令:和
@save-skill。skillga saqla - 将这些触发指令视为将项目特定指导保存为本地技能的请求。
- 写入前进行一次简短确认:。
Save this as a local skill? (yes/no) - 使用标准本地路径保存:。
.agents/skills/local/<skill-name>/SKILL.md - 如果匹配的本地技能已存在,更新/合并该技能,而非创建重复项。
Error Handling
错误处理
- Wrap async code in try-catch where failures are expected.
- Provide helpful error messages.
- Log errors appropriately.
- 在预期可能失败的异步代码中添加try-catch包裹。
- 提供有帮助的错误提示信息。
- 合理记录错误日志。
Security
安全规范
- Never expose secrets or API keys.
- Validate all user inputs.
- Use environment variables.
- 绝不泄露密钥或API密钥。
- 验证所有用户输入。
- 使用环境变量存储敏感信息。
Skill Priority Order
技能优先级顺序
When multiple skills apply, follow this order:
- project-init - First only for setup/context recovery intent
- global-config - Baseline defaults and routing guardrails
- agent/reasoning - Before any complex task
- agent/planning - For task decomposition
- core/ skills - Foundation
- arch/ skills - Architecture decisions
- frontend/ or backend/ - Implementation
- perf/ - Optimization
- agent/ - Other agent behaviors
当多个技能适用时,遵循以下优先级:
- project-init - 仅在设置/上下文恢复意图时优先使用
- global-config - 基线默认值和路由规则
- agent/reasoning - 执行任何复杂任务前使用
- agent/planning - 用于任务分解
- core/ 技能 - 基础功能
- arch/ 技能 - 架构决策
- frontend/ 或 backend/ - 代码实现
- perf/ - 性能优化
- agent/ - 其他Agent行为
Session Memory
会话记忆
Remember these across the conversation:
- Project type and stack (Next.js, NestJS, etc.).
- Constraints and priorities (performance, accessibility, SEO).
- Key files and structure discussed.
在对话过程中记住以下内容:
- 项目类型和技术栈(Next.js、NestJS等)。
- 约束条件和优先级(性能、可访问性、SEO)。
- 讨论过的关键文件和结构。
Quick Reference
快速参考
| Setting | Default |
|---|---|
| Communication | Mirror user tone and language, concise |
| TypeScript | Strict when applicable |
| Styling | Tailwind CSS (if selected) |
| State | TanStack Query + Zustand (if selected) |
| Forms | React Hook Form + Zod (if selected) |
| API | REST/tRPC (if selected) |
| 设置项 | 默认值 |
|---|---|
| 沟通方式 | 匹配用户语气和语言,简洁表达 |
| TypeScript | 适用时启用严格模式 |
| 样式方案 | Tailwind CSS(若被选中) |
| 状态管理 | TanStack Query + Zustand(若被选中) |
| 表单处理 | React Hook Form + Zod(若被选中) |
| API方案 | REST/tRPC(若被选中) |