SkillFoxx

Agora Skills plugin

Agora teaches an AI assistant to build voice agents and video calls on Agora SDKs, from login to a first working demo

  • 91 ★ on the repository
  • Last commit
  • MIT
PluginOfficial

Extended access

Why this level

  • The agent logs in to your Agora account through the CLI, creates projects and obtains the App ID, App Certificate and tokens
  • The skill clones samples and runs a local demo with your keys
All reasons and checks

agoraio/skillsAuthor:Agora

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add plugins/agora-skills

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • The agent logs in to your Agora account through the CLI, creates projects and obtains the App ID, App Certificate and tokens
  • The skill clones samples and runs a local demo with your keys

This is third-party code. Review the repository files before installing.

What it does

The official Agora knowledge pack for AI coding assistants. The `agora` skill helps pick a product, wire up credentials and run a first demo. It is strongest in conversational AI: voice agents, AI tutors and companions, customer support replacing IVR, voice toys and physical AI such as robots and wearables. Classic scenarios are covered too: 1:1 and group calls, streaming, chat and signaling, session recording and production token generation. The agent logs in to Agora through the Agora CLI: a browser opens free sign-up if there is no account, and keys need no manual copying. It then creates a project, extracts the App ID, App Certificate and tokens, clones the official sample for your stack (Web, Next.js, iOS, Android, Python, Go), runs the demo and lets you swap the LLM: OpenAI, Anthropic, Gemini, DeepSeek, Qwen or your own model. Install with `npx skills add github:AgoraIO/skills` or the Claude Code plugin.

Who it is for. Developers of apps with voice AI, video calls and chat building on Agora SDKs and working in Claude Code, Cursor, Copilot or Windsurf.

Good fit when

  • You want a voice AI agent in the browser in one evening with your own model attached
  • You need an AI tutor or companion with a live voice and its own personality
  • A support line on IVR must be replaced by a voice agent
  • Production needs Agora token generation in Node.js, Python or Go

Not a fit when

  • You need another vendor's video or voice solution: the skill knows Agora products only
  • You need only a general WebRTC reference with no SDK tie
  • You are not ready to create an Agora account and install the Agora CLI

Example request

Install the Agora skill and build a voice AI agent demo on Next.js with my Anthropic model

Limitations

  • An Agora account is required, and login and project creation go through the Agora CLI, installed with a separate script from the Agora CDN.
  • The skill creates a project and extracts the App ID, App Certificate and tokens, which are your account credentials, so keep them out of the repository.
  • The knowledge covers Agora products, and third-party LLM providers for a voice agent connect with their own keys.
  • A Git clone install works for Cursor, Windsurf, Copilot and Kiro: point them to the `skills/agora/SKILL.md` file.

How to disable. In Claude Code run `/plugin uninstall agora@agora-skills`. If you installed through `npx skills`, delete the skill folder from the agent skills directory and remove the Agora CLI per Agora instructions.

FAQ

How do I install Agora Skills?

With `npx skills add github:AgoraIO/skills`, the Claude Code plugin (`/plugin marketplace add AgoraIO/skills`, then `/plugin install agora@agora-skills`) or by cloning the repository and pointing at `skills/agora/SKILL.md`.

What does the Agora CLI do?

It logs in, creates and binds a project, writes variables for samples and checks readiness. Install: `curl -fsSL https://dl.agora.io/cli/install.sh | sh`, and on Windows `irm https://dl.agora.io/cli/install.ps1 | iex`.

Which models can I connect to a voice agent?

OpenAI, Anthropic, Gemini, DeepSeek, Qwen or your own backend. After the demo runs you swap the model without rewriting the whole sample.

Which platforms have samples?

Web, React, Next.js, iOS, Android, Python and Go for conversational AI, and React Native and Flutter for classic RTC. The server gateway for media streaming is C++ on Linux.

Do I copy keys by hand?

No, after login through the Agora CLI the agent creates the project and extracts the App ID, App Certificate and tokens, writing them into the sample environment.

Discussion

No questions or reviews yet.

Plugins
Official

Vapi plugin with 13 skills and an MCP connector: an agent builds voice assistants, calls, campaigns and tools on the platform

PluginExtended access69
Official

The Agnes AI Models skill helps an agent connect Agnes AI text, image and video models through an OpenAI-compatible gateway

SkillExtended access68

A CLI that sets a project up for an agent in one command: skills, MCP and plan-driven development via /aif.

CLIExtended access1.2K

The ag-ui-dotnet plugin and an A2UI skill teach a coding agent to build AG-UI apps: streaming chat, tools, shared state.

PluginMinimal access17.2K
Official

Apollo agent skills: Client, Server, iOS, Kotlin, MCP Server, Rover, GraphQL schemas and operations. Install via npx skills.

PluginMinimal access130

A library of 30-plus instruction skills for coding agents: planning, building, testing, hallucination guards and shipping

SkillMinimal access217

README in short

The README explains that the knowledge pack helps build conversational AI and classic real-time scenarios on Agora. It gives a quick start phrase for the agent, three install routes, a coverage table by capability and platform and setup for different tools. Details live in `ARCHITECTURE.md` and the plugin folder.

README badge

Original SKILL.md

---
name: agora
description: >-
  Activate when the user wants to build voice AI agents, video or voice calls,
  live streaming, screen sharing, in-app messaging and presence, recording,
  token or auth flows, or use the `agora` CLI for login, official recipes,
  quickstarts, env setup, diagnostics, introspection, skills, or MCP serving,
  especially when integrating Agora into an app.
license: MIT
metadata:
  author: agora
  version: '1.9.0'
---

<!-- applies-from: v0.2.1 -->

# Agora (agora.io)

Top-level workflow for selecting the right Agora path and loading only the references needed for the task.

## Workflow

1. Identify the user's primary goal from the problem they are solving.
2. Choose exactly one primary route first: RTC, RTM, ConvoAI, CLI, Cloud Recording, Server, Server Gateway, or Cross-product coordination.
3. Load only the primary product README first.
4. When the ConvoAI route is chosen and read-only workspace detection finds outdated server SDK package or module names — or the user asks to migrate — load **[references/conversational-ai/server-sdk-rename.md](references/conversational-ai/server-sdk-rename.md)** before editing manifests or imports. Do not load it for greenfield ConvoAI work.
5. If the task clearly spans multiple products, add the minimum supporting references after the primary route is chosen.
6. If the request matches ConvoAI and there is no proven working baseline yet, stop and follow the quickstart path before generating custom code from memory or scaffolding a replacement app.
7. For a new RTC Web one-to-one video-call demo without a working baseline, follow **[references/rtc/quickstarts.md](references/rtc/quickstarts.md)**. For other platforms or audio-only requests, use the routing rules in **[references/rtc/README.md](references/rtc/README.md)**.
8. Ask one short clarification only if the route is still ambiguous after checking the obvious cues below.
9. Use Level 2 documentation lookup only when the local references do not cover the needed detail.

## Route Selection

- **RTC**: video calls, voice chat, livestream, screen share, join/publish/subscribe tracks
  Route to **[references/rtc/README.md](references/rtc/README.md)**.
- **RTM**: chat, signaling, presence, metadata, notifications inside the client
  Route to **[references/rtm/README.md](references/rtm/README.md)**.
- **ConvoAI**: AI assistant, voice bot, agent demo, provider choice, MLLM, Studio Agent ID, agent backend
  Route to **[references/conversational-ai/README.md](references/conversational-ai/README.md)**.
- **ConvoAI + existing app**: user already has a codebase and wants ConvoAI added
  Route to **[references/conversational-ai/README.md](references/conversational-ai/README.md)** first, then **[references/conversational-ai/integration-from-quickstart.md](references/conversational-ai/integration-from-quickstart.md)** after the official quickstart has been cloned and inspected.
- **Agora CLI**: `agora` install, login, project selection, `init`, official recipe discovery, `quickstart`, env export, quickstart env binding, feature enablement, `doctor`, `project doctor`, env help, introspection, built-in skills, and MCP serving
  Route to **[references/cli/README.md](references/cli/README.md)**.
- **Cloud Recording**: acquire/start/query/stop recording lifecycle

Report a problem