Telephony And Conferencing logo

Telephony And Conferencing

CommunityPopular
cbrock84
telephony-and-conferencing

Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet emergency-calling requirements, port numbers without losing service, or work out why voice quality degrades only sometimes.

Overview

Publishercbrock84
Repositoryheadcount
Skill nametelephony-and-conferencing
Stars
2K
Forks
316
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 cbrock84 on GitHub. Read the source before you install it.

Installation

Install the Telephony And Conferencing 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/cbrock84/headcount/tree/main/plugins/it-operations/skills/telephony-and-conferencing
  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/cbrock84/headcount.git /tmp/headcount
mkdir -p .claude/skills
cp -r /tmp/headcount/plugins/it-operations/skills/telephony-and-conferencing .claude/skills/telephony-and-conferencing
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Telephony And Conferencing 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 Telephony And Conferencing 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 Telephony And Conferencing 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.

Telephony and conferencing

Voice is the service where failure is most visible and least tolerated. Nobody files a ticket when email is slow; everyone notices a dead phone, and customers notice first. It is also the service most likely to be nobody's stated job — inherited from a facilities vendor, half-migrated to a collaboration suite, with the parts that still work unowned.

Voice is an application on the network now, and behaves like one

A phone system is real-time traffic sharing a network built for everything else. That makes voice the first service to expose problems the network was hiding: jitter, packet loss, and asymmetric routing that a file transfer absorbs and a conversation does not.

Quality complaints are almost never about the phone system. Diagnose them as network problems on the path, and prioritize voice traffic explicitly rather than assuming capacity is enough — a link with headroom on average still queues at the moment someone is talking. See it-operations:network-administration for the diagnosis order.

The corollary is that a network change can break voice without touching it, which is an argument for including voice in the change review rather than discovering it afterward.

Emergency calling is a legal obligation, not a feature

Emergency calls must reach the right dispatch center with a location accurate enough to send help to, and in most jurisdictions this is regulated rather than optional. Two requirements that routinely get missed: a caller must be able to dial emergency services directly without a prefix, and someone on site should be notified when such a call is placed.

Remote and hybrid work is what makes this hard. A softphone carries its number, not its location, so a home worker dialing for help may route to the office's dispatch center hundreds of miles away. Provider features exist to handle this and they require configuration and user prompting to work.

Treat location records as data that goes stale. Desk moves, new floors, and new home addresses all invalidate them, and nobody discovers the error at a good moment.

Numbers are assets, and porting is the risky part

Phone numbers are contractually held by the losing provider until a port completes, which gives that provider both the ability and the incentive to make leaving slow. Ports fail on trivial mismatches — a service address that does not match the billing record exactly, an account PIN nobody has, a number that was never actually on the account.

Get a current bill and a copy of the losing provider's records before scheduling anything, port a small test group first, and never cancel the old service until the new one carries live traffic. Canceling early does not accelerate the port; it strands the numbers.

Keep the number inventory somewhere permanent, with what each number is for. Main lines, fax lines that still receive real documents, and numbers printed on physical material are all things that cost more than they appear to when lost.

Rooms fail on the last two feet

Conference rooms are where the technology is judged, and they fail in the mundane ways: the wrong cable, a display on the wrong input, a control panel asleep, a camera pointed at a wall. A room that takes five minutes to start a meeting is a room people stop booking.

Standardize aggressively — the same room build repeated is supportable, and eight bespoke rooms are not. One-touch join is worth real money because it eliminates the entire class of failure. Monitor rooms as infrastructure rather than waiting for complaints; most platforms report device health, and a dead room found on Monday morning beats one found by an executive at nine o'clock.

Recording creates records

Call and meeting recording is trivial to enable and produces material that is discoverable in litigation, subject to privacy law, and subject to consent requirements that vary by jurisdiction — some places require every party to consent, not just one.

Decide retention before switching it on, and default to short. Transcripts and AI-generated summaries are records too, and they are increasingly produced automatically by the meeting platform whether or not anyone chose it. legal-risk:privacy-and-data-protection owns the obligations; this skill owns knowing the feature creates them.

Sources

references/sources.md in this skill lists the outside authorities that settle the questions here — what each one is authoritative for, and what you may do with it. Check them before answering on anything they cover, and cite what you used. Most are free to read and not free to reproduce; the use note on each is binding.

Never

  • Deploy softphones without solving location for emergency calls.
  • Cancel the losing provider before numbers have ported and carry traffic.
  • Enable recording before deciding retention.
  • Diagnose voice quality inside the phone system when the network is untested.

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 Telephony And Conferencing AI skill do?

Runs voice and meeting infrastructure — phone systems and numbers, emergency calling obligations, conference rooms and their AV, call recording and its retention consequences, and the porting that makes provider changes go badly. Use this to replace a phone system, fix rooms nobody can start a meeting in, meet emergency-calling requirements, port numbers without losing service, or work out why voice quality degrades only sometimes.

Why use Telephony And Conferencing on TypingMind?

Because you install it once and use it with any model. Telephony And Conferencing 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 Telephony And Conferencing in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/telephony-and-conferencing. 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 Telephony And Conferencing?

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 Telephony And Conferencing?

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

Is the Telephony And Conferencing AI skill free?

Yes. It is published on GitHub by cbrock84 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 👇