Apple Media

Organization

sundial-org

apple-media

Control Apple TV, HomePod, and AirPlay devices via pyatv (scan, stream, playback, volume, navigation).

Overview

Publisher	sundial-org
Repository	`awesome-openclaw-skills`
Skill name	`apple-media`
Stars	664
Forks	97
Bundled files	Instructions only
Links	Skill source Repository

Markdown instructions
A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.
Works with any LLM
AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.
Self-contained
Everything the model needs lives in the instructions — no extra files to sync.
Open source
Published by sundial-org on GitHub. Read the source before you install it.

Installation

Install the Apple Media AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/apple-media
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/sundial-org/awesome-openclaw-skills.git /tmp/awesome-openclaw-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-openclaw-skills/skills/apple-media .claude/skills/apple-media

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Apple Media in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Apple Media on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Apple Media is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed
The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.
Switch models mid-chat
Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Apple Media Remote

Control Apple TV, HomePod, and AirPlay devices from the command line using atvremote.

Setup Notes

pyatv has a compatibility issue with Python 3.14+. Use --python python3.13 (or any version ≤3.13) when installing.
If ~/.local/bin isn't on your PATH after install, run: pipx ensurepath
If your default Python is 3.14+, you can also call directly: python3.13 -m pyatv.scripts.atvremote <command>

Scan for Devices

bash
atvremote scan
atvremote --scan-hosts 10.0.0.50 scan          # Scan specific IP (faster)
atvremote --scan-hosts 10.0.0.50,10.0.0.51 scan  # Multiple IPs

Returns all discoverable Apple TV, HomePod, and AirPlay devices on the local network with their names, addresses, protocols, and pairing status.

Target a Device

Use -n <name> (device name), -s <ip> (address), or -i <id> (identifier) to target:

bash
atvremote -n "Kitchen" <command>
atvremote -s 10.0.0.50 <command>
atvremote -i AA:BB:CC:DD:EE:FF <command>

Playback Control

bash
atvremote -n "Kitchen" playing           # Now playing info (title, artist, album, position, etc.)
atvremote -n "Kitchen" play              # Resume playback
atvremote -n "Kitchen" pause             # Pause playback (resumable with play)
atvremote -n "Kitchen" play_pause        # Toggle play/pause
atvremote -n "Kitchen" stop              # Stop playback (ends session, cannot resume)
atvremote -n "Kitchen" next              # Next track
atvremote -n "Kitchen" previous          # Previous track
atvremote -n "Kitchen" skip_forward      # Skip forward (~10-30s, app-dependent)
atvremote -n "Kitchen" skip_backward     # Skip backward (~10-30s, app-dependent)
atvremote -n "Kitchen" skip_forward=30   # Skip forward specific seconds
atvremote -n "Kitchen" set_position=120  # Seek to position (seconds)
atvremote -n "Kitchen" set_shuffle=Songs # Shuffle: Off, Songs, Albums
atvremote -n "Kitchen" set_repeat=All    # Repeat: Off, Track, All

Volume

bash
atvremote -n "Kitchen" volume            # Get current volume (0-100)
atvremote -n "Kitchen" set_volume=50     # Set volume (0-100)
atvremote -n "Kitchen" volume_up         # Step up (~2.5%)
atvremote -n "Kitchen" volume_down       # Step down (~2.5%)

Streaming

Stream local files or URLs to a device:

bash
atvremote -n "Kitchen" stream_file=/path/to/audio.mp3   # Local file
atvremote -n "Kitchen" play_url=http://example.com/stream.mp3  # Remote URL

Supports common audio formats (MP3, WAV, AAC, FLAC, etc.).

Power Management

bash
atvremote -n "Apple TV" power_state      # Check power state
atvremote -n "Apple TV" turn_on          # Wake device
atvremote -n "Apple TV" turn_off         # Sleep device

Navigation (Apple TV)

bash
atvremote -n "Apple TV" up               # D-pad up
atvremote -n "Apple TV" down             # D-pad down
atvremote -n "Apple TV" left             # D-pad left
atvremote -n "Apple TV" right            # D-pad right
atvremote -n "Apple TV" select           # Press select/enter
atvremote -n "Apple TV" menu             # Back/menu button
atvremote -n "Apple TV" home             # Home button
atvremote -n "Apple TV" home_hold        # Long press home (app switcher)
atvremote -n "Apple TV" top_menu         # Go to main menu
atvremote -n "Apple TV" control_center   # Open control center
atvremote -n "Apple TV" guide            # Show EPG/guide
atvremote -n "Apple TV" channel_up       # Next channel
atvremote -n "Apple TV" channel_down     # Previous channel
atvremote -n "Apple TV" screensaver      # Activate screensaver

Keyboard Input (Apple TV)

When a text field is focused:

bash
atvremote -n "Apple TV" text_get                 # Get current text
atvremote -n "Apple TV" text_set="search query"  # Replace text
atvremote -n "Apple TV" text_append=" more"      # Append text
atvremote -n "Apple TV" text_clear               # Clear text

App Control (Apple TV)

bash
atvremote -n "Apple TV" app_list                          # List installed apps
atvremote -n "Apple TV" launch_app=com.apple.TVMusic      # Launch by bundle ID or URL

Output Devices (Multi-room)

Manage connected audio outputs (e.g. grouping HomePods):

bash
atvremote -n "Apple TV" output_devices                    # List current output device IDs
atvremote -n "Apple TV" add_output_devices=<device_id>    # Add speaker to group
atvremote -n "Apple TV" remove_output_devices=<device_id> # Remove from group
atvremote -n "Apple TV" set_output_devices=<device_id>    # Set specific output(s)

Push Updates (Live Monitoring)

Watch for real-time playback changes:

bash
atvremote -n "Kitchen" push_updates   # Prints updates as they occur (ENTER to stop)

Pairing

Some devices (especially Apple TV) require pairing before control:

bash
atvremote -n "Living Room" pair                   # Pair (follow PIN prompt)
atvremote -n "Living Room" --protocol airplay pair  # Pair specific protocol
atvremote wizard                                  # Interactive guided setup

Credentials are stored automatically in ~/.pyatv.conf after pairing.

Device Info

bash
atvremote -n "Kitchen" device_info       # Model, OS version, MAC
atvremote -n "Kitchen" features          # List all supported features
atvremote -n "Kitchen" app               # Current app playing media

Tips

Pause vs Stop: Use pause/play to suspend and resume. stop ends the session entirely — playback must be restarted from the source (Siri, Home app, etc.)
HomePods with "Pairing: NotNeeded" can be streamed to immediately
Apple TVs typically require pairing first (all protocols the device supports)
The playing command shows media type, title, artist, position, shuffle/repeat state
For stereo HomePod pairs, target either unit by name
Use --scan-hosts for faster targeting when you know the device IP
Navigation and keyboard commands are primarily for Apple TV (not HomePod)

Frequently asked questions

What does the Apple Media AI skill do?

Control Apple TV, HomePod, and AirPlay devices via pyatv (scan, stream, playback, volume, navigation).

Why use Apple Media on TypingMind?

Because you install it once and use it with any model. Apple Media is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Apple Media in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/apple-media. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Apple Media?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Apple Media?

As many as you like. As long as a model supports skills, you can use Apple Media with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Apple Media AI skill free?

It is published on GitHub by sundial-org. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Feishu Doc

openclaw

OrganizationPopular

Feishu document read/write workflows. Activate when the user mentions Feishu docs, cloud docs, or docx links.

Feishu Drive

Feishu cloud-storage and comment workflows. Activate when the user mentions cloud space, folders, Drive files, or document comments.

Feishu Wiki

Feishu knowledge-base navigation workflows. Activate when the user mentions a knowledge base, wiki, or wiki link.

Wacli

Send third-party WhatsApp messages or sync/search WhatsApp history via wacli, not normal active chats.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

Apple Media Remote

Setup Notes

Scan for Devices

Target a Device

Playback Control

Volume

Streaming

Power Management

Navigation (Apple TV)

Keyboard Input (Apple TV)

App Control (Apple TV)

Output Devices (Multi-room)

Push Updates (Live Monitoring)

Pairing

Device Info

Tips

Frequently asked questions

Related AI Skills

Set up your own AI workspace now