Agent Skills Hub

github-code-review

Deploy specialized AI swarms to perform comprehensive, multi-domain GitHub pull request reviews covering security, performance, architecture, and style.

artifact-tracking

AI-optimized artifact tracking system for token-efficient project orchestration, phase management, and automated task delegation using YAML-Markdown hybrid formats.

libragent-quality

Comprehensive code quality validation for LibrAgent, covering TypeScript frontend and Rust/Tauri backend via automated linting, formatting, type checking, and build verification.

zarr-python

Python skill for high-performance storage of chunked N-dimensional arrays using Zarr, supporting cloud storage (S3/GCS), parallel I/O, and integration with NumPy, Dask, and Xarray.

k8s-troubleshooting

AI-powered Kubernetes and OpenShift troubleshooting. Proactively assess cluster health, debug pod failures, analyze logs, and validate security using Popeye-inspired patterns.

brainwriting

Structured parallel brainstorming agent for ideation and conceptual expansion. Uses multi-agent perspectives to evolve vague ideas into practical, actionable visions. Ideation only, not for task planning.

iam

Manage AWS Identity and Access Management: configure users, roles, policies, and permissions for secure cloud environments.

dev-checker

Automated code quality validation tool for pre-commit and pre-deploy checks, covering TypeScript, builds, and linting.

moai-essentials-debug

Advanced multi-language debugging support with stack trace analysis, runtime error triage, and automated diagnostic tools for containerized and distributed systems.

wiki-llms-txt

Generates llms.txt and llms-full.txt files to provide LLM-friendly documentation and project context.

changelog

Automated runtime observability changelog for Claude Code development sessions, tracking file changes, test results, and git commits.

vibe-orchestrator

Master workflow controller for Lovable-style, AI-driven development. Instantly generates premium, multi-page, animated applications by routing to specialized sub-agents. No prompts needed—just build.