vapi
Build, manage, and deploy AI-powered voice assistants, phone bots, and IVR systems with Vapi using the Model Context Protocol (MCP).
Discover reusable agent skills, browse implementation details, and find the right skill for your workflow.
410 skills found
Build, manage, and deploy AI-powered voice assistants, phone bots, and IVR systems with Vapi using the Model Context Protocol (MCP).
Method-driven planning workflow that intelligently decomposes tasks into structured plan.md files using zen-mcp tools, adapting to user clarity and automation needs.
Anthropic Claude integration patterns: streaming, RAG with pgvector, tool use, model selection (Haiku/Sonnet/Opus), prompt caching, and cost management for AI-powered engineering.
Execute implementation plans using isolated subagents for each task, featuring a rigorous two-stage review process for spec compliance and code quality.
Comprehensive Google Docs and Drive management tool. Supports document creation via Markdown, text formatting, structure analysis, and full file operations including upload, download, and sharing.
A testing utility designed to simulate prompt injection attacks and validate security scanners for AI agent skills.
Convert various documents, media, and web content into Markdown using markitdown, ideal for LLM processing and text analysis.
Transforms content to match specific voice profiles, tones, or styles using configurable YAML templates for consistent brand and narrative output.
Automated GitHub PR review agent for code quality, security analysis, and standard compliance using gh CLI.
Create and update comprehensive GitHub issues with full technical context to prevent requirement loss and reduce implementation friction.
Expert assistant for designing and optimizing production-grade Trigger.dev background jobs, AI workflows, and resilient asynchronous task architectures in TypeScript.
An advanced research intelligence skill for content creators and marketers that analyzes trends across 10+ platforms to generate data-driven content outlines based on user intent.