Agent Skills Hub

subagent-driven-development

Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.

vvm

VVM (Vibe Virtual Machine) is a language for agentic programs where the LLM acts as the runtime. Orchestrate multi-agent workflows, manage state, and build resilient AI pipelines.

commit

Enforces Sentry-style conventional commits, branch safety checks, and structured issue referencing for AI coding agents.

nano-banana

Automate Python scripting and Gemini-powered image generation using uv. Ideal for creating art, editing images, and running ad-hoc scripts.

customer-research

Multi-source research tool for customer inquiries, bug investigations, and account history synthesis with source attribution and confidence scoring.

ReasoningBank with AgentDB

Implement ReasoningBank adaptive learning with AgentDB's ultra-fast vector backend. Features trajectory tracking, verdict judgment, memory distillation, and pattern recognition for self-learning autonomous agents.

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.

wacli

Send WhatsApp messages to third parties, sync history, and search conversations via command line.

k0ntext

RPI Plan Phase: Create chunk-based, dependency-aware implementation plans from research documents for structured, atomic development.

claude-oracle

Automated tool and MCP server discovery for Claude Code. Searches 17+ registries to find relevant skills, plugins, and tools before planning or when errors occur.

gh-fix-ci

Debug failing GitHub Actions CI checks by fetching logs, summarizing failures, and planning fixes.

template-nextjs-moderne

A comprehensive Next.js 15 development and project management skill for Claude Code, featuring Supabase integration, RBAC, and automated quality validation.