Frameworks

Best Python Agent Skills

1522 Python skills for AI coding assistants — ranked by popularity.

This repository provides a curated collection of skill files for AI agents like Claude Code, Codex, and Cursor. Designed specifically for Python developers, these files act as functional blueprints that direct your AI to perform complex tasks with precision. You can automate academic literature reviews using databases like PubMed, scaffold production-ready FastAPI projects with built-in async patterns, or deploy LLMs locally via llama-cpp. We also include specialized modules for building Textual TUI applications, executing autonomous trading strategies, and constructing Model Context Protocol servers. Whether you are conducting financial risk analytics or archiving multimedia content, these skills reduce the boilerplate code your agent needs to write from scratch. By importing these structured definitions, you enable your AI assistant to handle domain-specific architecture and complex workflows without constant manual instruction. It is a toolkit for developers who want to scale their productivity by giving their agents expert-level Python context.

Top Python skills

literature-review

K-Dense-AI

Conduct comprehensive, systematic literature reviews using multiple academic databases (PubMed, arXiv, bioRxiv, Semantic Scholar, etc.). This skill should be used when conducting systematic literature reviews, meta-analyses, research synthesis, or comprehensive literature searches across biomedical, scientific, and technical domains. Creates professionally formatted markdown documents and PDFs with verified citations in multiple citation styles (APA, Nature, Vancouver, etc.).

5591,298

fastapi-templates

wshobson

Create production-ready FastAPI projects with async patterns, dependency injection, and comprehensive error handling. Use when building new FastAPI applications or setting up backend API projects.

5201,086

llama-cpp

zechenzhangAGI

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

21471

textual

KyleKing

Expert guidance for building TUI (Text User Interface) applications with the Textual framework. Invoke when user asks about Textual development, TUI apps, widgets, screens, CSS styling, reactive programming, or testing Textual applications.

143346

quant-analyst

zenobi-us

Expert quantitative analyst specializing in financial modeling, algorithmic trading, and risk analytics. Masters statistical methods, derivatives pricing, and high-frequency trading with focus on mathematical rigor, performance optimization, and profitable strategy development.

103355

video-downloader

ComposioHQ

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

101255

mcp-builder

anthropics

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

136215

streamlit

sverzijl

When working with Streamlit web apps, data dashboards, ML/AI app UIs, interactive Python visualizations, or building data science applications with Python

86239

stock-analyzer

FrancyJGLisboa

Provides comprehensive technical analysis for stocks and ETFs using RSI, MACD, Bollinger Bands, and other indicators. Activates when user requests stock analysis, technical indicators, trading signals, or market data for specific ticker symbols.

71214

python-testing-patterns

wshobson

Implement comprehensive testing strategies with pytest, fixtures, mocking, and test-driven development. Use when writing Python tests, setting up test suites, or implementing testing best practices.

77204

architecture-patterns

wshobson

Implement proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design. Use when architecting complex backend systems or refactoring existing applications for better maintainability.

55214

fastapi-pro

sickn33

Build high-performance async APIs with FastAPI, SQLAlchemy 2.0, and Pydantic V2. Master microservices, WebSockets, and modern Python async patterns. Use PROACTIVELY for FastAPI development, async optimization, or API architecture.

79181

openalex-database

davila7

Query and analyze scholarly literature using the OpenAlex database. This skill should be used when searching for academic papers, analyzing research trends, finding works by authors or institutions, tracking citations, discovering open access publications, or conducting bibliometric analysis across 240M+ scholarly works. Use for literature searches, research output analysis, citation analysis, and academic database queries.

48202

pdf

anthropics

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

64178

google-analytics

davila7

Analyze Google Analytics data, review website performance metrics, identify traffic patterns, and suggest data-driven improvements. Use when the user asks about analytics, website metrics, traffic analysis, conversion rates, user behavior, or performance optimization.

43193

telegram-bot-builder

davila7

Expert in building Telegram bots that solve real problems - from simple automation to complex AI-powered bots. Covers bot architecture, the Telegram Bot API, user experience, monetization strategies, and scaling bots to thousands of users. Use when: telegram bot, bot api, telegram automation, chat bot telegram, tg bot.

106130

stripe-integration

wshobson

Implement Stripe payment processing for robust, PCI-compliant payment flows including checkout, subscriptions, and webhooks. Use when integrating Stripe payments, building subscription systems, or implementing secure checkout flows.

48165

pdf-processing

Ming-Kai-LC

Comprehensive PDF processing techniques for handling large files that exceed Claude Code's reading limits, including chunking strategies, text/table extraction, and OCR for scanned documents. Use when working with PDFs larger than 10-15MB or more than 30-50 pages.

37171

data-engineering

pluginagentmarketplace

ETL pipelines, Apache Spark, data warehousing, and big data processing. Use for building data pipelines, processing large datasets, or data infrastructure.

13192

annas-archive-ebooks

ratacat

Use when needing to look up book content, find a book by title/author, download an ebook, or reference material from a published book. Triggers on book lookups, ebook downloads, "find the book", "get the PDF/EPUB of". Downloads produce PDF/EPUB/MOBI files - use ebook-extractor skill to convert to text.

22177

deepwiki-rs

sopaco

AI-powered Rust documentation generation engine for comprehensive codebase analysis, C4 architecture diagrams, and automated technical documentation. Use when Claude needs to analyze source code, understand software architecture, generate technical specs, or create professional documentation from any programming language.

25170

prompt-optimizer

solatis

Optimize system prompts for Claude Code agents using proven prompt engineering patterns. Use when users request prompt improvement, optimization, or refinement for agent workflows, tool instructions, or system behaviors.

43147

codex-cli-bridge

alirezarezvani

Bridge between Claude Code and OpenAI Codex CLI - generates AGENTS.md from CLAUDE.md, provides Codex CLI execution helpers, and enables seamless interoperability between both tools

9180

jupyter-notebook

davila7

Use when the user asks to create, scaffold, or edit Jupyter notebooks (`.ipynb`) for experiments, explorations, or tutorials; prefer the bundled templates and run the helper script `new_notebook.py` to generate a clean starting notebook.

30158

How to choose a Python skill

Evaluate each skill by checking the maintainer and the specific scope of the provided logic. Review the code structure to ensure the dependency injection patterns or framework conventions align with your existing project requirements. Look for evidence of recent updates and clear usage guidelines within the skill file. If a skill offers multiple modes, such as the varied trading agents in moon-dev, ensure the agent's capabilities match your specific production environment rather than just general theory.

More Python skills

code-to-music
Cam10001110101 · 17 installs
openai-whisper
openclaw · 38 installs
langchain
zechenzhangAGI · 26 installs
cisco-network-diagram
neuro-synapse · 8 installs
math-tools
ananddtyagi · 26 installs
crawl4ai
basher83 · 21 installs
python-performance-optimization
wshobson · 27 installs
data-cleaning-pipeline
aj-geddes · 13 installs
jianying-editor
luoluoluo22 · 38 installs
backtesting-frameworks
wshobson · 17 installs
manim
davila7 · 29 installs
video-processor
basher83 · 17 installs
google-calendar-sync
astoreyai · 9 installs
excel-analysis
davila7 · 22 installs
unsloth
zechenzhangAGI · 15 installs
plotly
davila7 · 20 installs
exploratory-data-analysis
K-Dense-AI · 15 installs
llama-factory
zechenzhangAGI · 15 installs
pdf-processing-pro
davila7 · 17 installs
gemini-logo-remover
bear2u · 9 installs
llava
zechenzhangAGI · 7 installs
cocoindex
cocoindex-io · 6 installs
csv-data-summarizer
coffeefuelbump · 15 installs
senior-security
davila7 · 31 installs
paddle-ocr-validation
jgtolentino · 10 installs
ai-multimodal
mrgoonie · 9 installs
azure-functions
aj-geddes · 10 installs
async-python-patterns
wshobson · 12 installs
rag-implementation
wshobson · 10 installs
pair-trade-screener
tradermonty · 11 installs
billing-automation
wshobson · 10 installs
python-repl
gptme · 6 installs
langchain-architecture
wshobson · 8 installs
clojure-write
metabase · 16 installs
scientific-critical-thinking
davila7 · 18 installs
umap-learn
K-Dense-AI · 6 installs
ml-pipeline-workflow
wshobson · 9 installs
robotics-code-generator
HumaizaNaz · 14 installs
security-header-generator
Dexploarer · 5 installs
slack-gif-creator
anthropics · 6 installs
add-uint-support
pytorch · 18 installs
setup
barefootford · 12 installs
senior-data-engineer
davila7 · 21 installs
ai-cost-optimizer
ScientiaCapital · 9 installs
docstring
pytorch · 8 installs
validate-openapi-specs
epieczko · 5 installs
embedding-strategies
wshobson · 8 installs
ocr
trpc-group · 35 installs
building-automl-pipelines
jeremylongshore · 6 installs
modal
davila7 · 5 installs
model-compare
rawwerks · 7 installs
polars
davila7 · 22 installs
risk-metrics-calculation
wshobson · 8 installs
astropy
davila7 · 6 installs
python-design-patterns
wshobson · 19 installs
temporal-python-testing
wshobson · 8 installs
biorxiv-database
lifangda · 7 installs
langgraph
davila7 · 13 installs
scientific-visualization
davila7 · 26 installs
django-pro
sickn33 · 20 installs
data-visualization
anthropics · 25 installs
seaborn
davila7 · 8 installs
vectcut-api
sun-guannan · 11 installs
uv-package-manager
wshobson · 13 installs
distributed-tracing
wshobson · 5 installs
n8n-code-python
czlonkowski · 7 installs
backtesting-trading-strategies
jeremylongshore · 10 installs
python-pro
sickn33 · 23 installs
matchms
davila7 · 6 installs
python-code-style
wshobson · 9 installs
gpt-researcher
assafelovic · 14 installs
ollama-setup
jeremylongshore · 11 installs
llm-evaluation
wshobson · 6 installs
whisper
davila7 · 11 installs
lecture-transcript-slide-matcher
az9713 · 6 installs
cookbook-audit
anthropics · 5 installs
cirq
davila7 · 5 installs
i18n-localization
davila7 · 15 installs
home-assistant-integration-knowledge
home-assistant · 8 installs
backend-security-coder
sickn33 · 24 installs
copilot-sdk
github · 7 installs
physics-validator
omriwen · 6 installs
python-project-structure
wshobson · 8 installs
senior-computer-vision
davila7 · 12 installs
scikit-learn
davila7 · 9 installs
rdkit
K-Dense-AI · 8 installs
crewai
davila7 · 4 installs
geospatial-analysis
benchflow-ai · 16 installs
product-strategist
davila7 · 12 installs
senior-data-scientist
davila7 · 9 installs
discord-bot-architect
davila7 · 11 installs
llamaindex
davila7 · 3 installs
senior-backend
davila7 · 14 installs
transcribe
openai · 11 installs
voice-ai-development
davila7 · 5 installs
pydicom
davila7 · 6 installs

+1,402 more — browse all skills.

Frequently asked

How do I add these skills to my AI agent?
Most agentic tools allow you to import or reference specific skill definitions directly into your agent's configuration or system prompt. You should review the documentation for your specific interface—such as Cursor or Claude Code—to determine if they require placing the file in a dedicated local directory or embedding the text directly into the project's agent context.
Can I use these skills for production Python applications?
Yes, many of these skills are built for production use. For instance, the fastapi-templates skill produces code with standard async patterns and error handling, while the mcp-builder provides architectural guidance for service connectivity. However, you should always audit the generated output for security and performance constraints specific to your deployment environment before moving code to a live server.

Skills for other frameworks

Search skills

Search the agent skills registry