aiagents.org

AI skills for Voice agents

Skills for voice agents.

11 skills

Build voice agents with LiveKit

This skill helps you write spoken and text agents on the LiveKit Agents SDK and LiveKit Cloud. It focuses on keeping replies fast, keeping context small, and splitting one large agent into handoffs and tasks. It also covers fixes for agents that talk too much, repeat questions, or claim a booking that never saved.

Create a Vapi voice assistant

This 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.

Dub audio or video with ElevenLabs

This skill uses the ElevenLabs Dubbing API to translate the speech in audio or video files while keeping each original speaker's voice. It covers creating a project, adding target languages, editing the transcript or translation, and downloading the result.

Remove background noise with ElevenLabs

This skill cleans up recordings using the ElevenLabs Voice Isolator API, stripping noise, music, and ambience so the voice stays. It shows Python, JavaScript, and CLI usage, takes files or URLs, and lists supported formats. It is handy before transcription.

Run outbound call campaigns with Vapi

This skill creates, schedules, and manages outbound calling campaigns in Vapi for a contact list. It handles CSV or API contact data, concurrency, webhooks, pre-dial checks, and per-contact outcomes. It is not meant for a single call.

Speech

Generates text-to-speech narration and voiceover audio from prompts or scripts.

Test a LiveKit voice agent

This skill adds turn-by-turn tests for LiveKit voice agents, using pytest or Vitest. Tests check tool calls, handoffs, and replies, with mocked tools and seeded history for multi-turn cases. It also warns against tests that fail correct behavior.

Transcribe

Transcribes audio to text with optional speaker diarization and known-speaker hints.

Transcribe audio with ElevenLabs Scribe

This skill turns audio or video into text with ElevenLabs Scribe v2. Options include timestamps, labels for who is speaking, multichannel audio, key terms you want recognized, and language detection. Real-time streaming is supported for live use. An ElevenLabs API key is required.

Turn text into speech with ElevenLabs

This skill generates spoken audio from text with the ElevenLabs API. It covers choosing a model and voice, voice settings, picking among 90+ languages, streaming, and output formats. An ElevenLabs API key is required.

FAQ

What is an ai agent skill?

An agent skill is a portable pack of instructions that gives an agent specialized know-how for a task. In the open Agent Skills format (from Anthropic, now widely adopted), that pack is a folder with a SKILL.md file and optional scripts or references the agent can load when needed.

What is a SKILL.md file?

SKILL.md is the required main file in a skill folder. It starts with simple metadata (name and description) plus the instructions. Agents use the metadata to decide when a skill applies, then read the full file — and any linked files — only when the task needs them.

How do I use a skill from this directory?

Open the listing and follow the source link — usually a GitHub SKILL.md. Install with your agent’s skill flow, or add the repo the way that product documents. When this site shows the skill text, Copy is on the page.

What’s the difference between a skill and a prompt?

A prompt is paste-in text for one chat turn (or a short thread). A skill is a reusable file pack an agent can discover and load across a task, sometimes with code attached. Prompts live in the prompt directory; skills usually live on GitHub and we link out.

How are skills categorized?

Each skill uses one sitewide category — the same set as the rest of the directory (Coding agent, Marketing, Document intelligence, and so on). Hops filter to categories that already have skills.

Can I submit a skill?

Yes. Submit with a public GitHub SKILL.md URL, or attach a skill as part of a method on a use case. An editor reviews it before it appears here.