Agent skills for Claude Code

This skill should be used when the user wants to create a pull request, or submit code for review.

Automate Pushover tasks via Rube MCP (Composio).

Guides the structured engineering workflow for binary vulnerability analysis, debugging, and proof-of-concept stabilization.

Generate synthetic evaluation datasets for the PXI eval harness (evals/pxi/).

When to activate: Pydantic v2, data validation, serialization, settings management, pydantic-settings, field validators

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files.

Fast high-dimensional fixed effects: OLS, Poisson, IV with multi-way FE; DiD (TWFE, did2s, Sun-Abraham); clustered SEs…

Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data.

Guides the agent on how to run clean python styling, Black/Ruff compliance checks, and pytest execution on changed python scripts.

Pythia event generation skill for proton-proton and lepton collisions at high energies

When to activate: httpx, API clients, retry logic, auth headers, rate limiting client-side, OpenAPI client generation

Best practices, common mistakes, decision guidance, and checklists for async Python, asyncio, and FastAPI — covering single-instance code…

Curated bundle of essential Python backend development skills.

When to activate: ARQ, RQ, background workers, Redis-based queues, async task workers

When to activate: Redis, caching strategies, cache-aside, TTL, cache invalidation, aiocache, cache decorators

Guidance for writing, reviewing, and refactoring Python code with clear style, naming, design principles, and testing discipline.

Reviews Python code for type safety, async patterns, error handling, and common mistakes.

When to activate: multiprocessing, threading, concurrent.futures, ProcessPoolExecutor, GIL, CPU-bound tasks

When to activate: configuration management, pydantic-settings, env files, feature flags, environment-specific settings

Python data processing pipelines with modular architecture.

When to activate: ETL, data pipeline, Prefect, Airflow, DLT, Polars, batch processing, data quality