Agent skills for Claude Code

Validate, commit, and push.

AI-assisted safety layer for git push operations with quality gates and collaboration guardrails.

Push to remote and monitor CI. Validates branch safety, executes git push WITH explicit user approval, then monitors CI run status via gh…

Commit and push agent-skill changes to the user's private skills GitHub repo (private-skills-repo, rooted at ~/.agents).

DDOS production handoff layer. Converts a validated single-file HTML preview (typically from /dashboard-preview) into a deployable PWA…

Progressive Web App patterns with Workbox 7.x, service worker lifecycle, offline-first strategies, and installability.

Drive PWN::WWW::Twitter from pwn_eval.

Build production-ready AI agents with PydanticAI — type-safe tool use, structured outputs, dependency injection, and multi-model support.

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

Configure PyInstaller for Python binary builds with spec files and bundling options.

Pairwise test generation

Pyodide WASM apps in Web Workers. Use for Python-in-browser.

Complete guide for Pyth Network - decentralized oracle providing real-time price feeds for DeFi.

Creates FastAPI endpoints with layered architecture (Router → Service → Repository).

Use when planning, implementing, or reviewing code for any Python project — designing architecture, writing classes or functions…

Guidance for writing correct, non-blocking async Python — using async/await for I/O-bound work, never calling blocking functions from…

Python background job patterns including task queues, workers, and event-driven architecture.

Comprehensive Python programming reference covering syntax, concurrency, networking, databases, ML/LLM development, and HPC.

When to activate: Typer, Click, argparse, CLI applications, rich output, progress bars, configuration files

Python code quality standards. Use when working with types, linting, type checking, exceptions, logging, or configuring…

Analyze Python code quality using MCP tools - complexity, clones, dead code, coupling.