agent-radio

Control internet radio: play streams, search stations, manage favorites, volume, stop/pause/next, and inspect current playback. Uses mpv with audio device auto-detection and ffplay fallback. Settings persist between runs.

3,891 stars

Best use case

agent-radio is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Control internet radio: play streams, search stations, manage favorites, volume, stop/pause/next, and inspect current playback. Uses mpv with audio device auto-detection and ffplay fallback. Settings persist between runs.

Teams using agent-radio should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

  • You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

  • You only need a quick one-off answer and do not need a reusable workflow.
  • You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/agent-radio/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/art-ps/agent-radio/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/agent-radio/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How agent-radio Compares

Feature / Agentagent-radioStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Control internet radio: play streams, search stations, manage favorites, volume, stop/pause/next, and inspect current playback. Uses mpv with audio device auto-detection and ffplay fallback. Settings persist between runs.

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

SKILL.md Source

# Agent Radio Skill

Internet radio player for OpenClaw with station search, favorites, volume control, and playback management.

## When to Use

Use when user wants to:
- Play an internet radio stream by URL
- Search for stations by name from the live Radio Browser directory
- Play a random built-in station when no target is provided
- Manage favorite stations (add, remove, list)
- Control volume, pause/resume, stop, skip to next
- Check what is currently playing
- Have a persistent radio experience across sessions

## Tools

This skill provides the following CLI commands in `scripts/`:

### `play <url|station_name> [volume]`
Play a stream by URL or by name from favorites or the built-in list.

If no target is provided, the skill chooses a random station from `stations.json`.
Optional `volume` is `0-100` and defaults to the saved setting.

Examples:
- `play https://stream.zeno.fm/0r0xa792kwzuv`
- `play BBC Radio 1`
- `play "Jazz 24 (KNKX)" 60`

### `stop`
Stop playback immediately.

### `pause`
Pause or resume the current playback process.

### `next`
Skip to the next favorite station in a cycle.

### `volume [level]`
Show the current volume or set a new default volume from `0-100`.

Examples:
- `volume`
- `volume 75`

### `now`
Show the current station URL, volume, PID, and playback status.

### `favorite add <name> <url>`
Add a station to favorites.

### `favorite remove <name>`
Remove a station from favorites.

### `list`
List all favorite and built-in stations.

### `find <query> [number]`
Search the Radio Browser directory. When `number` is provided, play that result immediately.

Examples:
- `find jazz`
- `find "lofi hip hop" 1`

## Configuration

Preferences are stored in: `{baseDir}/preferences.json`

```json
{
  "last_station": "",
  "volume": 80,
  "favorites": [
    {"name": "BBC Radio 1", "url": "http://..."},
    {"name": "Jazz 24 (KNKX)", "url": "https://..."}
  ],
  "audio_device": "auto",
  "current_pid": null,
  "paused": false
}
```

Audio device auto-detection:
- macOS: `coreaudio/BuiltInSpeakerDevice`
- Linux: `alsa/default`
- Windows: `directsound/default`

Override locations when needed:
- `AGENT_RADIO_BASE_DIR`
- `AGENT_RADIO_PREF_FILE`
- `AGENT_RADIO_STATIONS_FILE`

## Implementation Notes

- Primary player: `mpv --no-video --audio-device=<device> --volume=<vol> --cache=yes <url>`
- Fallback player: `ffplay -nodisp -autoexit <url>`
- Playback runs in the background and stores PID plus paused state in preferences.
- On `play`, any existing playback is stopped before starting the next stream.
- Station lookup is case-insensitive across favorites and built-in stations.
- `next` cycles favorite URLs instead of depending on station-name matching.

## Error Handling

- If both `mpv` and `ffplay` are missing, return install guidance.
- If dependencies like `jq` or `curl` are missing, fail early with a clear message.
- If a stored PID is stale, clear it automatically.
- If station search returns no matches, explain how to retry with another query or a direct URL.

## Examples for Users

```text
/radio play https://stream.zeno.fm/0r0xa792kwzuv
/radio play "BBC Radio 1"
/radio volume 70
/radio now
/radio find jazz
/radio find "lofi hip hop" 1
/radio favorite add "Lounge Jazz" https://jazz.stream
/radio list
/radio next
/radio stop
```

## Future Enhancements

- Built-in station directory with genres and countries
- Recording streams to file
- Equalizer presets
- Web interface control

---

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891
from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891
from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation