Collaboration Platform Administration logo

Collaboration Platform Administration

CommunityPopular
cbrock84
collaboration-platform-administration

Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal hold. Use this to configure a tenant, tighten sharing, investigate a mail delivery or phishing problem, or work out who can see a file and why.

Overview

Publishercbrock84
Repositoryheadcount
Skill namecollaboration-platform-administration
Stars
1.6K
Forks
237
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 Collaboration Platform Administration 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.
  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/collaboration-platform-administration .claude/skills/collaboration-platform-administration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Collaboration Platform Administration 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 Collaboration Platform Administration 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 Collaboration Platform Administration 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.

Collaboration platform administration

This platform holds most of the organization's unstructured information and nearly all of its external communication. It is usually configured once during migration, by whoever ran the migration, and then never revisited.

Get mail authentication right, and keep it right

SPF, DKIM and DMARC together determine whether your mail is delivered and whether someone else can send as you. All three need to exist and agree.

  • SPF breaks quietly as third-party senders accumulate — marketing platforms, ticketing systems, invoicing tools — and has a hard limit on lookups that a growing list eventually crosses.
  • DKIM has to be enabled per sending domain and per service, not once for the tenant.
  • DMARC starts in monitoring and only protects once it moves to enforcement. A policy left at none for two years is a report nobody reads.

Every new tool that sends mail on your behalf is a change to this configuration. Route that through the same process as any other change, or the first sign will be a customer saying your invoices go to spam.

Phishing controls are configuration, not awareness training

External sender warnings, impersonation and lookalike-domain protection, attachment and link inspection, and blocking auto-forwarding to external addresses are settings. Auto-forward rules in particular are the classic account-compromise persistence mechanism, and the account owner will not notice.

Alert on inbox rule creation that forwards or deletes. It is one of the highest-signal detections available and it comes free with the platform.

Shared mailboxes, groups and the identities nobody owns

Shared mailboxes, distribution lists and team channels accumulate faster than anything else in the tenant and are never cleaned up. Each needs a named owner and a review date, because a distribution list nobody owns eventually mails the whole company by accident, and a shared mailbox with stale access is a standing data exposure.

Never leave a shared mailbox with a sign-in-capable account. It is an unmonitored identity with a password.

External sharing is where file storage leaks

The defaults are usually more permissive than the organization would choose, and the settings sit at several levels — tenant, site, folder, individual link — with the most permissive winning.

  • Anyone-with-the-link sharing is the setting worth deciding on deliberately. If it is allowed, it needs an expiry.
  • Guest access should expire and be reviewed. Guests from a project three years ago are still guests.
  • Permission inheritance is where sprawl comes from. Someone grants access to a top-level folder to solve one request, and it propagates everywhere below.

Run a sharing report on a schedule. Nobody discovers over-sharing by browsing.

Retention and legal hold are configured in advance or not at all

Retention policies decide what survives deletion and for how long, and they have to be set before the data you will need is deleted. Legal hold suspends deletion for named custodians and must be capable of being applied quickly.

The platform's own recycle bins are not a retention policy and not a backup — the retention windows are short and administrator deletion can bypass 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

  • Add a service that sends mail as your domain without updating authentication records.
  • Leave DMARC in monitoring indefinitely and describe the domain as protected.
  • Allow anyone-with-the-link sharing with no expiry.
  • Treat the platform's recycle bin as either retention or backup.

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 Collaboration Platform Administration AI skill do?

Administers the email, chat, meeting and file-sharing platform the organization runs on — tenant and domain configuration, mail authentication and routing, phishing and spam controls, shared mailboxes and distribution groups, external sharing and guest access, permission sprawl in file storage, and retention and legal hold. Use this to configure a tenant, tighten sharing, investigate a mail delivery or phishing problem, or work out who can see a file and why.

Why use Collaboration Platform Administration on TypingMind?

Because you install it once and use it with any model. Collaboration Platform Administration 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 Collaboration Platform Administration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/cbrock84/headcount/tree/main/plugins/it-operations/skills/collaboration-platform-administration. 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 Collaboration Platform Administration?

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 Collaboration Platform Administration?

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

Is the Collaboration Platform Administration 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 👇