Agent Skills Hub

MLOps Industrialization

A framework to transform experimental ML prototypes into robust, production-ready Python packages using src layout, hybrid architecture, and strict configuration management.

pr-review-fix-loop

Orchestrate an automated PR review-fix loop. Dispatches subagents to analyze code, CI status, and comments, then applies iterative fixes until the PR reaches a passing state.

spawn-decision

A specialized decision-making agent for complex architectural choices, task planning, and error resolution within the orchestration system.

swarm

Orchestrate parallel Claude Code worker swarms with protocol-based behavioral governance for complex features, multi-step refactors, and long-running autonomous coding sessions.

performance-correlation

Correlate content attributes with GA4 and GSC metrics to identify performance drivers and optimization opportunities.

code-quality-review

Holistic, multi-dimensional code review skill providing prioritized, actionable feedback on correctness, security, performance, design, and accessibility.

open-source-maintainer

End-to-end GitHub repository maintenance agent. Automates triage, PR review, issue analysis, and maintenance reporting to ensure long-term repository health, stability, and growth.

regression-testing

Strategic regression testing with intelligent test selection, impact analysis, and continuous regression management for faster, more reliable software delivery.

code-search-selector

Intelligent tool selector for code search. Routes queries between semantic (claudemem) and native tools (Grep/Glob) to optimize efficiency, token usage, and search accuracy.

moai-workflow-worktree

Git worktree management for isolated parallel development, featuring automatic branch registration and seamless MoAI-ADK workflow integration.

taskery

Generate comprehensive instructions for AI agents to operate the Taskery local Kanban board, including CLI, API, and concurrency management.

skill-reinforcement

An automated meta-learning skill that improves agent workflows by capturing patterns, failures, and shortcuts after each task execution.