Agent Skills Hub

perf-analyzer

Synthesize performance profiling data into actionable recommendations and evidence-backed technical decisions.

claude-code-mechanism-selector

A decision-support tool for Claude Code users to select the optimal extension mechanism—slash commands, skills, subagents, or hooks—based on project requirements.

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.

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.

deepwiki-rs

AI-powered documentation engine that automatically generates C4 architecture diagrams, technical specs, and codebase analysis from any source code directory.

mcp-rails

Implement a full Model Context Protocol (MCP) stack in Rails. Connect to external servers, expose your Rails app as an MCP server, or manage subprocess MCP containers via Docker with OAuth 2.1 PKCE support.

video-watcher

Fetch and parse transcripts from YouTube and Bilibili videos for summarization, QA, and content extraction using yt-dlp.

go-i18n

Manage Go CLI i18n rules, locale file structures, env-based language detection, and string key naming conventions for the Skills-X ecosystem.

file-todos

A structured file-based system for tracking todos, managing technical debt, and coordinating code review workflows directly within your repository.

risk-based-testing

Focus testing effort on highest-risk areas using risk assessment and prioritization. Use when planning test strategy, allocating resources, or making coverage decisions.

write-e2e-cases

Automate the creation and maintenance of Rsbuild E2E tests, ensuring feature coverage and regression prevention through Playwright.

prompt-estruturado

A structured prompting framework to transform casual inputs into professional, modular LLM prompts with persona, context, task, format, and guardrails.