Team logo

Team

OrganizationPopular
Prismer-AI
team

Invite humans into a workspace, propose collaborators for a project, and inspect the current human team. Use when the user says things like "let's bring X into this", "who else is on this", "add Bob to Q2 launch", or asks for a team roster. NEVER mints invites silently — the human must press a button.

Overview

PublisherPrismer-AI
RepositoryPrismerCloud
Skill nameteam
Stars
1.6K
Forks
14
Bundled files
Instructions only
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.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by Prismer-AI on GitHub. Read the source before you install it.

Installation

Install the Team 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/Prismer-AI/PrismerCloud.git /tmp/PrismerCloud
mkdir -p .claude/skills
cp -r /tmp/PrismerCloud/sdk/prismer-cloud/built-in-skills/team .claude/skills/team
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Team 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 Team 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 Team 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.

Team

Use this skill when work needs another human in the loop. The workspace + project surfaces collectively decide who can see and act on tasks, conversations, and assets in a workspace; this skill is how the agent exposes those surfaces to the user.

⛔ Hard rules — human-in-loop

  1. Never auto-send an invite. Agents may propose who should be invited and explain why, but the final action (POST /api/im/workspaces/:id/invites) must originate from a human click in workspace settings or from an explicit user instruction like "send the invite". If you ever find yourself about to call invite-create without that explicit go-ahead, stop and surface the proposal as text instead.
  2. Never expose member emails. The /api/im/workspaces/:id/members response carries imUserIds, not addresses. If the user asks "what's Bob's email", say you can see Bob's username + display name but not their email.
  3. Distinguish workspace member from project member. Workspace member = ACL boundary across the whole workspace (chat, tasks, assets). Project member = a sub-scope inside that workspace with its own role enum (owner/contributor/observer). Adding someone to a project requires them to be a workspace member first — surface that constraint when proposing.
  4. Never silently re-add a removed member. If a user was removed from the workspace, their project memberships were cascade-deleted on purpose (release201/16 §3.2.3). Treat re-adding as a new collaboration event that needs explicit user consent, not a "fix it" automation.

When to use

  • The user names someone who isn't already on the workspace: "Have Maya look at this", "Loop Bob in on Q2 launch".
  • The user asks who's on the team or what the roster looks like: "who has access to this workspace", "who's working on Q2 launch".
  • The user asks to remove someone, change someone's role, or move someone between projects.
  • An agent (e.g. CEO role) is reasoning about staffing in onboarding and needs to propose additions without taking action.

What the platform exposes

This skill is a thin wrapper over the cloud workspace + invite endpoints (release201/16):

IntentSurface
List workspace membersGET /api/im/workspaces/:id/members (owner / admin / member)
List project membersGET /api/im/projects/:id/members (project visibility rules)
List outstanding invitesGET /api/im/workspaces/:id/invites (owner/admin)
Propose an inviteStop here. Tell the user what to click.

Concrete invite minting and acceptance go through the workspace settings → Members UI and the /invite/:token landing page. Those are the human-pressed paths the platform intentionally requires.

Suggested phrasing when proposing

When the user mentions a name and you're not sure if they're in:

"Maya isn't in this workspace yet. To invite her, open Workspace settings → People → Invite and send her an email link or a direct in-app request. She'll see the link, accept, and then I can add her to the Q2 launch project."

When the user is owner/admin and asks you to do it:

"I can't send the invite myself — the platform requires you to press the button so there's an audit receipt. Want me to walk you to Workspace settings → People now?"

When proposing a project add for someone already in the workspace:

"Maya is a workspace member but not on the Q2 launch project. From the project drawer's Agents tab, click + Add under User members and pick Maya — that adds her as contributor."

What this skill does NOT do

  • It does not push invite links to email, Slack, or any side channel. The cloud's notification queue handles email; this skill does not.
  • It does not enumerate non-members. Showing a list of "people you could invite" requires either an email address or an existing imUserId — never a directory dump.
  • It does not promote / demote roles. Surface the suggestion and let the human do it through settings. Role changes are owner-only on the server.

Edge cases

  • Block relationships: invites between blocked users 422 with PRINCIPAL_BLOCKED. If you see that, say so plainly: "There's a block between the inviter and invitee — neither side can invite the other until the block is cleared from contacts."
  • Already-pending invite: the server returns 409 DUPLICATE_PENDING_INVITE if the same workspace already has a pending invite to that addressee. Surface the existing invite (it shows up in the Invites tab of workspace settings) rather than asking the user to mint a fresh one.
  • Expired invite: 410 INVITE_EXPIRED. The link is dead. Ask the human to mint a new one; do not autocreate one in their place.

Forbidden patterns

Anti-patternWhy it's forbidden
Calling invite-create silently during a taskrelease201/16 §0.2.4 — agents must not mint workspace ACL changes
Listing email addresses of workspace membersrelease201/16 §0.2.4 — members endpoint never returns emails
Treating contact-add as "auto-invite to workspace"release201/16 §5.4 anti-pattern — contact ≠ ACL
Re-adding a removed user "because they used to be on the team"release201/16 §3.2.3 — cascade is intentional

Related skills

  • tasks — once people are in, this is how work flows to them.
  • human-approval — if you need a human's sign-off on an action (different from inviting them as a workspace member).
  • agent-coordination — for the agent side of who-does-what; this skill is the human side.

Frequently asked questions

What does the Team AI skill do?

Invite humans into a workspace, propose collaborators for a project, and inspect the current human team. Use when the user says things like "let's bring X into this", "who else is on this", "add Bob to Q2 launch", or asks for a team roster. NEVER mints invites silently — the human must press a button.

Why use Team on TypingMind?

Because you install it once and use it with any model. Team 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 Team in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Prismer-AI/PrismerCloud/tree/main/sdk/prismer-cloud/built-in-skills/team. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Team?

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 Team?

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

Is the Team AI skill free?

Yes. It is published on GitHub by Prismer-AI 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 👇