Buzz Media Attachments logo

Buzz Media Attachments

Community
tonbistudio
buzz-media-attachments

Use when attaching a local media file to the active Buzz conversation. Do not use for general media editing or non-Buzz delivery.

Overview

Publishertonbistudio
Repositorybuzz-skills
Skill namebuzz-media-attachments
Stars
277
Forks
18
Bundled files
1
LicenseMIT
Links
  • 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.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by tonbistudio on GitHub. Read the source before you install it.

Installation

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

1

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.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/tonbistudio/buzz-skills/tree/main/buzz-media-attachments
  4. 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.
2

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/tonbistudio/buzz-skills.git /tmp/buzz-skills
mkdir -p .claude/skills
cp -r /tmp/buzz-skills/buzz-media-attachments .claude/skills/buzz-media-attachments
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Buzz Media Attachments 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 Buzz Media Attachments 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 Buzz Media Attachments 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.

Buzz Media Attachments

Use this workflow when a user asks to post a local media file into the current Buzz conversation and normal MEDIA:/path delivery fails.

Workflow

  1. Verify the source file exists and is readable. Use ffprobe for video metadata when relevant.

  2. Find the current Buzz channel UUID from the live gateway log rather than guessing:

    bash
    # Search ~/.hermes/logs/gateway.log for the user's latest inbound Buzz message.
    # The line contains: platform=buzz ... chat=<CHANNEL_UUID>
  3. Use Buzz's native attachment mechanism:

    bash
    buzz messages send \
      --channel <CHANNEL_UUID> \
      --content - \
      --file /absolute/path/to/file

    --file may be repeated to attach several files to one message.

  4. Load Buzz credentials without shell-sourcing .env. BUZZ_AUTH_TAG can contain JSON that shell source mangles. Parse the file with python-dotenv and pass values through a subprocess environment:

    python
    import os, subprocess
    from dotenv import dotenv_values
    
    env = os.environ.copy()
    env.update({
        k: v for k, v in dotenv_values(os.path.expanduser("~/.hermes/.env")).items()
        if v is not None
    })
    result = subprocess.run(
        ["buzz", "messages", "send",
         "--channel", channel_id,
         "--content", "-",
         "--file", file_path],
        input=caption,
        text=True,
        env=env,
        capture_output=True,
        timeout=180,
    )
  5. If Buzz rejects an MP4, diagnose the returned relay error:

    • moov atom not at front of file (not fast-start): first try remuxing:

      bash
      ffmpeg -y -v error -i input.mp4 -c copy -movflags +faststart output.mp4
    • media contains metadata or a non-canonical metadata channel: use Buzz Desktop's canonical sanitizer settings. A simple stream-copy remux is insufficient because FFmpeg may retain or add forbidden MP4 metadata structures. Fully re-encode exactly as follows:

      bash
      ffmpeg -y -nostdin -loglevel error -protocol_whitelist file,pipe \
        -i input.mp4 \
        -map 0:v:0 -map '0:a:0?' \
        -map_metadata -1 -map_chapters -1 -sn -dn \
        -fflags +bitexact -flags:v +bitexact -flags:a +bitexact \
        -c:v libx264 -preset fast -crf 23 -pix_fmt yuv420p \
        -vf 'pad=ceil(iw/2)*2:ceil(ih/2)*2' \
        -c:a aac -b:a 128k \
        -movflags +faststart -metadata encoder= \
        output.mp4

      This matches block/buzz Desktop's transcode_to_mp4() implementation and produces the canonical H.264/AAC, metadata-free, fast-start MP4 expected by the relay.

    • If canonical MP4 encoding is undesirable, fails, or the user specifically asks for Attach Image, convert a short clip to an animated GIF:

      bash
      ffmpeg -y -v error -i input.mp4 \
        -vf "fps=12,scale=512:-1:flags=lanczos,split[s0][s1];[s0]palettegen=max_colors=128[p];[s1][p]paletteuse=dither=bayer" \
        -loop 0 -map_metadata -1 output.gif

    Upload the resulting MP4 or GIF through buzz messages send --file.

  6. Verify success from real output. Only report success when Buzz returns JSON containing:

    json
    {"accepted": true, "event_id": "..."}

Pitfalls

  • Plain MEDIA:/absolute/path.mp4 can route through Hermes' generic send_video fallback; Buzz may not implement native video delivery there.
  • Do not claim an attachment worked merely because the gateway accepted the assistant response. Check the Buzz CLI's accepted value and retain the event_id as verification.
  • Never print BUZZ_PRIVATE_KEY or other .env values.
  • Keep converted GIFs in /tmp unless the user requests durable copies; do not modify the source MP4.
  • GIF conversion can increase file size. For long or high-resolution clips, lower fps, scale width, or color count before uploading.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Buzz Media Attachments AI skill do?

Use when attaching a local media file to the active Buzz conversation. Do not use for general media editing or non-Buzz delivery.

Why use Buzz Media Attachments on TypingMind?

Because you install it once and use it with any model. Buzz Media Attachments 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 Buzz Media Attachments in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/tonbistudio/buzz-skills/tree/main/buzz-media-attachments. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Buzz Media Attachments?

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 Buzz Media Attachments?

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

Is the Buzz Media Attachments AI skill free?

Yes. It is published on GitHub by tonbistudio under the MIT license. 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

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇