my-plugins

Pulls in up-to-date official skills shipped by a project's installed libraries (FastAPI, Streamlit, etc.) via tiangolo/library-skills.

Pause execution and inspect runtime state via DAP. Set breakpoints, evaluate expressions, test fixes in-place. Attach to running processes by PID — no restart, no code changes, no manual setup.

Evaluate Claude Code skills against best practices from Anthropic's article. Tracks skill usage globally via hooks.

Spawn a peer back-and-forth between Claude (max thinking) and Codex (high reasoning) to deeply analyze hard tradeoffs and architecture decisions, with user-input proxying when the agents need clarification.

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

Agent skills for Qdrant vector search: scaling, performance optimization, search quality, monitoring, deployment, edge, model migration, multitenancy, version upgrades, and SDK usage

Basecamp integration for Claude Code. Create todos, track work, link code to projects.

Agent skills for building agents with LangChain, LangGraph, and Deep Agents

CLI tool for managing Git worktrees, optimized for parallel AI agent workflows and multi-branch development scenarios.