Vapi's vapi-prompt-builder skill helps write, improve or review the system prompts behind Vapi voice agents and multi-assistant Squads that answer phone or web calls. It gathers what the agent has to do, then builds the prompt in sections that cover its role, tasks, tool use, guardrails, handoffs and escalation. It tunes the wording for speech, keeping replies short and handling turn-taking, errors and collecting caller details. It needs a Vapi API key.
Design a multi-assistant Vapi Squad with handoffsVapi's create-squad skill helps an agent decide whether a voice use case needs several assistants at all and, if so, build a Vapi Squad with documented handoff tools between them. It defines each member's job, tools and boundaries, puts the entry member first, resolves real assistant IDs before wiring handoffs, and sets context and variable passing only where needed. By default it returns a plan or JSON payload and only makes live changes when you ask and a VAPI_API_KEY is set. It warns against inventing IDs, tools or credentials and against splitting each step of a conversation into its own assistant.Voice agentsVoice agentsVapi
Design and run Vapi Simulations test suitesVapi's simulations skill sets up automated tests for Vapi voice assistants and Squads using Vapi Simulations. It starts from requirements written in everyday words and plans what to cover, then builds the test personalities, scenarios, success criteria and suites, with tool mocks and variables where needed. It can run tests over chat or voice, read the results, and wire suites into regression checks, launch reviews or CI gates. Live runs need a Vapi API key.Voice agentsVapiVoice agents
Create a Vapi voice assistantThis skill designs and builds a voice assistant on Vapi for phone or web calls. It covers the system prompt and first message, choosing a model, voice, and transcriber, multilingual setup, call-control tools, and hooks. It also explains errors from the create call. A Vapi API key is needed to save the assistant.Voice agentsVapiVoice AI
Build a Deepgram voice agent over one WebSocketThis skill from Deepgram shows an agent how to build a spoken assistant on Deepgram's agent API, where one WebSocket handles listening, the language model and speech output. It first helps decide between building on that API directly or using a framework such as Pipecat, LiveKit Agents, Retell or Vapi with Deepgram speech underneath. It then walks through the connection order, the Settings message, streaming audio, interruptions, changing settings during a call and function calls that your own code answers, including Twilio phone calls. It points to Deepgram's other skills for the full API reference and language SDKs.Voice agentsVoice agentsSpeech APIs
Place outbound, web, scheduled and batch calls with VapiVapi's create-call skill shows an agent how to start a single phone call to a customer, a browser-based web call, a call scheduled for later or a small batch of calls through the Vapi API. It includes examples in cURL, TypeScript and Python, how to define an assistant inline for a quick test, how to attach metadata and how to list or fetch calls with their transcripts and recordings. It points to a separate skill for larger campaigns with reporting and cancellation. It needs a Vapi API key. Automated calls made without consent can break US FCC and TCPA rules. License: the SKILL.md frontmatter says MIT, but the repository has no license file.Voice agentsVapiPhone calls
Give an OpenClaw agent a phone line with AmberAmber is a skill and runtime that gives an OpenClaw agent its own phone number through a bridge between Twilio, or a compatible voice provider, and OpenAI Realtime. It can answer and screen callers, place outbound calls only after confirmation, look up contacts, book on your calendar, take messages and log transcripts, and it exposes these as MCP tools plus a local call dashboard. The author describes it as a sensitive communications system and asks operators to decide how callers are told, how consent is gathered and how long data is kept before production use. The local CRM and transcript enrichment are off unless you enable them.Voice agentsVoice agentsOpenClaw
