drewsepeczi/drewsepeczi-first-assistant icon
public
Published on 4/7/2025
My First Assistant

This is an example custom assistant that will help you complete the Python onboarding in VS Code. After trying it out, feel free to experiment with other blocks or create your own custom assistant.

Rules
Prompts
Models
Context
Data
anthropic Claude 3.7 Sonnet model icon

Claude 3.7 Sonnet

anthropic

200kinput·8.192koutput
gemini Gemini 2.0 Flash model icon

Gemini 2.0 Flash

gemini

1048kinput·8.192koutput
openai Morph Fast Apply model icon

Morph Fast Apply

OpenAI

ollama deepseek-r1 8b model icon

deepseek-r1 8b

ollama

together Llama 4 Maverick Instruct (17Bx128E) model icon

Llama 4 Maverick Instruct (17Bx128E)

together

gemini Gemini 2.5 Pro model icon

Gemini 2.5 Pro

gemini

1048kinput·65.536koutput
together Llama 4 Scout Instruct (17Bx16E) model icon

Llama 4 Scout Instruct (17Bx16E)

together

relace Relace Instant Apply model icon

Relace Instant Apply

relace

ollama qwen2.5-coder 1.5b model icon

qwen2.5-coder 1.5b

ollama

You are a Python coding assistant. You should always try to - Use type hints consistently - Write concise docstrings on functions and classes - Follow the PEP8 style guide
- Follow Next.js patterns, use app router and correctly use server and client components.
- Use Tailwind CSS for styling.
- Use Shadcn UI for components.
- Use TanStack Query (react-query) for frontend data fetching.
- Use React Hook Form for form handling.
- Use Zod for validation.
- Use React Context for state management.
- Use Prisma for database access.
- Follow AirBnB style guide for code formatting.
- Use PascalCase when creating new React files. UserCard, not user-card.
- Use named exports when creating new react components.
- DO NOT TEACH ME HOW TO SET UP THE PROJECT, JUMP STRAIGHT TO WRITING COMPONENTS AND CODE.
You are an experienced data scientist who specializes in Python-based
data science and machine learning. You use the following tools:
- Python 3 as the primary programming language
- PyTorch for deep learning and neural networks
- NumPy for numerical computing and array operations
- Pandas for data manipulation and analysis
- Jupyter for interactive development and visualization
- Conda for environment and package management
- Matplotlib for data visualization and plotting
- Optimize indexes to improve query execution speed.
- Avoid N+1 queries and suggest more efficient alternatives.
- Recommend normalization or denormalization strategies based on use cases.
- Implement transaction management where necessary to ensure data consistency.
- Suggest methods for monitoring database performance.
- You are a Svelte developer
- Use SvelteKit for the framework
- Use TailwindCSS for styling
- Use TypeScript
- Use the canonical SvelteKit file structure:
  ```
  src/
    actions/
    components/
    data/
    routes/
    runes/
    styles/
    utils/
Pythonhttps://docs.python.org/3/
Reacthttps://react.dev/reference/
Vue docshttps://vuejs.org/v2/guide/
Next.jshttps://nextjs.org/docs/app
Zodhttps://zod.dev/
Vercel AI SDK Docshttps://sdk.vercel.ai/docs/
Uvicorn Docshttps://www.uvicorn.org/
React Testing Library Docshttps://testing-library.com/docs/react-testing-library/intro/
Obsidian Developer Docshttps://raw.githubusercontent.com/obsidianmd/obsidian-api/refs/heads/master/obsidian.d.ts
SvelteKithttps://svelte.dev/docs/kit
My dochttps://ui.aceternity.com/components

Prompts

Learn more
Client component
Create a client component.
Create a client component with the following functionality. If writing this as a server component is not possible, explain why.
Page
Creates a new Next.js page based on the description provided.
Create a new Next.js page based on the following description.
New Component
Create a new Svelte component
Please create a new Svelte component following these guidelines:
- Include JSDoc comments for component and props
- Include basic error handling and loading states
- ALWAYS add a TypeScript prop interface
Prisma schema
Create a Prisma schema.
Create or update a Prisma schema with the following models and relationships. Include necessary fields, relationships, and any relevant enums.
API route inspection
Analyzes API routes for security issues
Review this API route for security vulnerabilities. Ask questions about the context, data flow, and potential attack vectors. Be thorough in your investigation.
Exploratory Data Analysis
Initial data exploration and key insights
Create an exploratory data analysis workflow that includes:

Data Overview:
- Basic statistics (mean, median, std, quartiles)
- Missing values and data types
- Unique value distributions

Visualizations:
- Numerical: histograms, box plots
- Categorical: bar charts, frequency plots
- Relationships: correlation matrices
- Temporal patterns (if applicable)

Quality Assessment:
- Outlier detection
- Data inconsistencies
- Value range validation

Insights & Documentation:
- Key findings summary
- Data quality issues
- Variable relationships
- Next steps recommendations
- Reproducible Jupyter notebook

The user has provided the following information:
API route
Create an API route.
Create an API route with the following functionality.
RAG Pipeline Design
Comprehensive retrieval-augmented generation system design
Design a RAG (Retrieval-Augmented Generation) system with:

Document Processing:
- Text extraction strategy
- Chunking approach with size and overlap parameters
- Metadata extraction and enrichment
- Document hierarchy preservation

Vector Store Integration:
- Embedding model selection and rationale
- Vector database architecture
- Indexing strategy
- Query optimization

Retrieval Strategy:
- Hybrid search (vector + keyword)
- Re-ranking methodology
- Metadata filtering capabilities
- Multi-query reformulation

LLM Integration:
- Context window optimization
- Prompt engineering for retrieval
- Citation and source tracking
- Hallucination mitigation strategies

Evaluation Framework:
- Retrieval relevance metrics
- Answer accuracy measures
- Ground truth comparison
- End-to-end benchmarking

Deployment Architecture:
- Caching strategies
- Scaling considerations
- Latency optimization
- Monitoring approach

The user's knowledge base has the following characteristics:

Context

Learn more
@code
Reference specific functions or classes from throughout your project
@docs
Reference the contents from any documentation site
@diff
Reference all of the changes you've made to your current branch
@terminal
Reference the last command you ran in your IDE's terminal and its output
@problems
Get Problems from the current file
@folder
Uses the same retrieval mechanism as @Codebase, but only on a single folder
@codebase
Reference the most relevant snippets from your codebase
@currentFile
Reference the currently open file
@url
Reference the markdown converted contents of a given URL
@file
Reference any file in your current workspace
@repo-map
Reference the outline of your codebase
@open
Reference the contents of all of your open files
@clipboard
Reference recent clipboard items
@commit
@os
Reference the architecture and platform of your current operating system

S3

${{ secrets.drewsepeczi/drewsepeczi-first-assistant/continuedev/s3-dev-data/CONNECTION_STRING }}

Google Cloud Storage

${{ secrets.drewsepeczi/drewsepeczi-first-assistant/continuedev/google-cloud-storage-dev-data/CONNECTION_STRING }}

MCP Servers

Learn more

Exa

npx -y exa-mcp-server

Memory

npx -y @modelcontextprotocol/server-memory

Playwright

npx -y @executeautomation/playwright-mcp-server

Postgres

npx -y @modelcontextprotocol/server-postgres ${{ secrets.drewsepeczi/drewsepeczi-first-assistant/anthropic/postgres-mcp/CONNECTION_STRING }}

GitHub

npx -y @modelcontextprotocol/server-github

Brave Search

npx -y @modelcontextprotocol/server-brave-search

Filesystem

npx -y @modelcontextprotocol/server-filesystem ${{ secrets.drewsepeczi/drewsepeczi-first-assistant/anthropic/filesystem-mcp/PATH }}

Repomix

npx -y repomix --mcp