Agent Skills Hub

user-story

Create structured user stories using the Mike Cohn format with Gherkin acceptance criteria to translate requirements into testable, development-ready tasks.

document

Interactive terminal canvas for rendering, editing, and selecting markdown text, emails, and project documentation in Claude Code.

research-pipeline

End-to-end autonomous research agent: from idea generation and literature review to experiment execution, adversarial review loops, and paper writing.

getting-started-guide

A structured guide for novelists to navigate the seven-step writing process, from constitution and specification to planning, tasking, drafting, and quality analysis.

react

React component development guide for LobeHub, including styling with antd-style, layout building with @lobehub/ui, and routing management.

frontend-accessibility-best-practices

Accessibility best practices and patterns for React applications to ensure WCAG compliance, semantic structure, and inclusive user experiences.

self-improve

Self-maintaining skill for OpenCode agents to update documentation, capture learnings, and extend tool/agent capabilities dynamically.

moonbit-refactoring

Refactor MoonBit code for idiomatic style: minimize public APIs, implement methods, leverage pattern matching with views, and enforce high test coverage for maintainable MoonBit projects.

tzurot-council-mcp

Multi-perspective AI consultation for technical architecture, complex refactoring, and structured debugging.

create-tasks

Creates well-formed, actionable engineering tasks from requirements using vertical slicing, INVEST principles, and Example Mapping.

doc-sync

Synchronizes and maintains CLAUDE.md and README.md documentation hierarchy across a repository to ensure consistent, just-in-time context for AI agents.

seo-fundamentals

Master SEO fundamentals with E-E-A-T, Core Web Vitals tracking, technical optimization, and AI content best practices for improved search visibility.