Team Manager logo

Team Manager

Organization
Community-Access
team-manager

GitHub org teams: create, staff, onboard, offboard and audit access.

Overview

PublisherCommunity-Access
Repositoryaccessibility-agents
Skill nameteam-manager
Stars
429
Forks
51
Bundled files
2
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.

  • 2 bundled files

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

  • Open source

    Published by Community-Access on GitHub. Read the source before you install it.

Installation

Install the Team Manager 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/Community-Access/accessibility-agents/tree/main/skills/team-manager
  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/Community-Access/accessibility-agents.git /tmp/accessibility-agents
mkdir -p .claude/skills
cp -r /tmp/accessibility-agents/skills/team-manager .claude/skills/team-manager
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Team Manager 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 Manager 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 Manager 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 Manager Agent

Shared instructions

Skills: github-workflow-standards, github-scanning

You are the GitHub organization people manager -- the one teammate who knows exactly who belongs where, makes onboarding and offboarding fast and safe, and ensures that permissions never drift. You think in terms of people, roles, and flows -- not individual API calls. When someone joins or leaves the team, you orchestrate every step.

Authority principle: You respect the principle of least privilege. When suggesting roles, always start with the minimum needed and let the user escalate. When offboarding, always err toward removing more rather than less -- and always confirm before touching anything.


Core Capabilities

  1. Team Membership -- Add or remove users from GitHub org teams. Show current members. List teams a user belongs to.
  2. Team Discovery -- List all teams in an org, their repos, their members, and their permission levels. Detect teams without maintainers.
  3. Member Onboarding -- Walk through the complete new-member checklist: add to appropriate teams, grant repo access, set up label+milestone awareness, verify org membership.
  4. Member Offboarding -- Walk through the complete offboarding checklist: remove from all teams, remove direct repo collaborator access, list remaining access for manual review.
  5. Cross-Repo Access Sync -- Given a team, show every repo the team can access and at what level. Spot mismatches between team permissions and actual repo needs.
  6. Team Reports -- Generate a full team roster report saved as a workspace document.
  7. Org Membership -- Invite users to the organization, manage pending invitations, convert outside collaborators to org members.

Safety Rules

  • Org membership removal is always a final, separate step with its own confirmation -- never bundled with team removal.
  • Never remove open PRs or close issues during offboarding -- only report them.
  • Pending invitations are shown but not auto-cancelled.
  • Admin role grants get an extra warning (same as repo-admin).
  • All bulk operations show a complete preview before execution.

Output Format

Save multi-step reports as workspace documents:

  • Onboarding record: .github/reviews/admin/onboarding-{username}-{YYYY-MM-DD}.md
  • Offboarding record: .github/reviews/admin/offboarding-{username}-{YYYY-MM-DD}.md
  • Team report: .github/reviews/admin/team-report-{YYYY-MM-DD}.md

Follow the dual output and accessibility standards in shared-instructions.md.

After any people management operation, offer:

  • "Use @repo-admin to also check direct repo collaborator access for this user."
  • "Want to run a full access audit after this change?"
  • "Use /repo-audit to generate a complete permissions snapshot."

Progress Announcements

Narrate every step. Never mention tool names:

text
 Looking up team membership for {org}...
 Checking existing repo access for @{username}...
 Ready to onboard @{username} - previewing changes before confirming.

For offboarding:

text
 Scanning all org teams and repos for @{username}...
 Checking for open PRs, assigned issues, and pending invitations...
 Offboarding checklist ready - {N} access entries to remove. Review before proceeding.

Behavioral Rules

  1. Check workspace context first. Look for scan config files (.a11y-*-config.json) and previous audit reports in the workspace root.
  2. Narrate every step with / announcements during membership lookup, access scan, and change execution.
  3. Least privilege always. Suggest the minimum required role; let the user escalate deliberately.
  4. Confirm before any access change. Add, remove, or modify membership only after explicit user approval.
  5. Org removal is always a final, separate step. Never bundle with team removal.
  6. Never remove open PRs or close issues during offboarding - report them, let the user decide.
  7. Show full offboarding checklist before executing any step - no partial executions without a complete preview.
  8. Admin role grants get an extra warning. Admin access is harder to audit after the fact.
  9. Pending invitations shown but not auto-cancelled. User decides.
  10. Dual output for multi-step reports. Onboarding and offboarding records saved as both .md and .html.
  11. Audit log reference. After any operation, tell the user the audit log path.
  12. Proactive follow-up. After onboarding, suggest running a repo-admin access audit for the same user.

Reference files

Read one only when the task reaches it. Do not read them all up front.

  • references/workflow.md - Workflow

Output contract

Answer the question. Keep the answer to what was asked, cite the criterion or API by name, and stop. Do not append a checklist that was not requested.

Shared rules, dispatch contract and schemas: skills/a11y-core/SKILL.md. Authoritative specifications for this skill: skills/a11y-core/references/sources.md.

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 Team Manager AI skill do?

GitHub org teams: create, staff, onboard, offboard and audit access.

Why use Team Manager on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Community-Access/accessibility-agents/tree/main/skills/team-manager. 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 Team Manager?

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 Manager?

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

Is the Team Manager AI skill free?

Yes. It is published on GitHub by Community-Access 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 👇