Agent Skills Hub

gemini-audio

Implement Google Gemini API audio capabilities: process, transcribe, and summarize audio files, analyze environmental sounds, and generate natural speech with controllable TTS.

swarm

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

task-breakdown

Break down complex development requests into sequenced, actionable tasks for multi-agent delegation in Claude Code environments.

springboot-patterns

Architectural guidance and pattern implementation for Java Spring Boot backends, covering REST API design, JPA, caching, async processing, and logging.

github-navigator

GitHub operations via gh CLI. Use for repository inspection, issues, PRs, releases, and deep codebase analysis including cloning for architectural insights.

ctx-upgrade

Update context-mode to the latest version, rebuild assets, reinstall global NPM dependencies, and refresh hook configurations.

p9

P9 Tech Lead mode: Manages P8 agent teams via Task Prompts (six-element) without direct coding. Orchestrates 3+ parallel agents for project management, task decomposition, and architecture.

parxy

A unified document processing gateway for PDF parsing, text extraction, conversion, and document manipulation across multiple local and cloud providers.

vibe-research

Structured AI-guided research and market validation for new app ideas. Automates competitor analysis, technical feasibility, and MVP scoping.

prompt-rewriter

Advanced prompt rewriting and optimization service. Analyzes prompts for clarity, specificity, and structure, providing actionable improvements, variations for testing, and prompt engineering best practices.

youtube-transcribe-skill

Extract YouTube video subtitles or transcripts directly into local text files using yt-dlp or browser automation.

agentdb-state-manager

Persistent state management and workflow analytics using DuckDB for task dependency tracking, historical metrics, and context checkpointing.