菜单
NLP course learning assistant. Use when (1) doing NLP labs/assignments, (2) understanding NLP concepts (tokenization, embeddings, transformers), (3) implementing NLP algorithms, (4) debugging NLP code, (5) preparing for NLP exams.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Complete software development lifecycle from requirements to deployment. Use when (1) starting a new project from scratch, (2) need structured end-to-end development process, (3) require comprehensive documentation and quality gates at each phase.
专业的AI Agent(AI Agents)顾问助手，探索 AI Agent 框架和应用。当用户询问以下问题时使用：(1) 技术选型和对比 (2) 使用指南和最佳实践 (3) 问题诊断和解决 (4) 资源推荐 (5) 常见问题解答
Comprehensive CV learning assistant. Use when studying image processing, object detection, segmentation, or any CV tasks. Helps with algorithm understanding, implementation, and model optimization.
Comprehensive DL learning assistant. Use when studying neural networks, CNN, RNN, LSTM, Transformer, or any DL architectures. Helps with network design, training strategies, debugging, and optimization techniques.
Comprehensive LLM learning assistant. Use when studying transformer architecture, attention mechanisms, pre-training, fine-tuning, or prompt engineering. Helps with understanding LLM principles and practical applications.
Comprehensive ML learning assistant. Use when studying supervised learning, unsupervised learning, regression, classification, clustering, or any ML concepts. Helps with algorithm understanding, implementation guidance, model evaluation, and practical applications.
| name | NLP Learning Assistant |
| description | NLP course learning assistant. Use when (1) doing NLP labs/assignments, (2) understanding NLP concepts (tokenization, embeddings, transformers), (3) implementing NLP algorithms, (4) debugging NLP code, (5) preparing for NLP exams. |
When user mentions lab/实验:
data/nlp/Week X/Lab Y/For NLP concepts, provide:
Key topics: tokenization, word embeddings, RNN/LSTM, attention, transformers, BERT, GPT, text classification, NER, sentiment analysis, machine translation.
When analyzing NLP code:
Write clean, professional NLP code:
Comments:
Structure:
# ============ Section Name ============Good Example:
def tokenize(text):
"""Tokenize and clean text: lowercase, alphabetic only."""
tokens = word_tokenize(text)
return [t.lower() for t in tokens if t.isalpha()]
Bad Example (over-commented):
def tokenize(text):
# Step 1: Tokenize the text
# 步骤 1：对文本进行分词
tokens = word_tokenize(text) # Split into words / 分割成单词
# Step 2: Clean tokens / 步骤 2：清理词元
return [t.lower() for t in tokens if t.isalpha()] # Lowercase and alphabetic / 小写和字母
Principles:
For homework/作业:
Generate practice materials:
Materials location: aisd/courses/nlp/
Structure:
slides/*.pdf - Lecture slides (original)notes/lecture*_notes.md - Extracted markdown notesnotes/lecture*_notes_images/ - Extracted imageslabs/*.pdf - Lab instructionscode/lab*/*.py - Lab codeWhen user asks to take notes or expand slides content:
Notes are in aisd/courses/nlp/notes/lecture*_notes.md
For each page section:
Add Chinese Translation:
**Term (术语)**: Explanation / 解释Expand Bullet Points:
Add Code Examples:
Create Practice Questions:
**Q:** Question / **A:** Answer## Page X
### [Original Title]
**中文标题**: [Chinese translation]
**Key Concepts / 关键概念:**
- Concept 1 (概念1): Explanation / 解释
- Concept 2 (概念2): Explanation / 解释
**Detailed Notes / 详细笔记:**
[Expanded explanation with examples]
**Code Example / 代码示例:**
\`\`\`python
# Demonstration code
\`\`\`
**Practice / 练习:**
**Q:** Question
**A:** Answer
**📝 My Notes / 我的笔记:**
> [Personal understanding and connections]
Generate from notes:
Flashcards:
Summary Sheet:
Quiz Questions:
Course data location: data/nlp/
Structure:
Week X/Lab Y/*.pdf - Lab instructionsWeek X/*.pdf - Lecture slidesWeek X/Hybrid Work/ - Hybrid materialsWhen user says "week X lab Y", read from corresponding Week X/Lab Y/ folder.