Onboarding Orchestrator logo

Onboarding Orchestrator

Organization
Amazon-Quick
onboarding-orchestrator

Designs and manages end-to-end employee onboarding programs with structured 30/60/90 day plans, buddy assignments, meeting schedules, tool access checklists, and milestone tracking. Adapts plans by role type and seniority. Use when asked to 'set up onboarding', 'create onboarding plan', 'new hire checklist', '30-60-90 plan', 'onboard new team member', or 'prepare for new joiner'.

Overview

PublisherAmazon-Quick
RepositoryAmazon-Quick-official-catalog
Skill nameonboarding-orchestrator
Stars
50
Forks
4
Bundled files
1
LicenseMIT-0
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 Amazon-Quick on GitHub. Read the source before you install it.

Installation

Install the Onboarding Orchestrator 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/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/hr/onboarding-orchestrator
  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/Amazon-Quick/Amazon-Quick-official-catalog.git /tmp/Amazon-Quick-official-catalog
mkdir -p .claude/skills
cp -r /tmp/Amazon-Quick-official-catalog/skills/hr/onboarding-orchestrator .claude/skills/onboarding-orchestrator
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Onboarding Orchestrator 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 Onboarding Orchestrator 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 Onboarding Orchestrator 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.

Overview

Builds structured onboarding programs for new hires, covering the first 90 days with clear milestones, recurring check-ins, tool access tracking, and buddy coordination. Adapts the plan based on role type (engineering, product, design, operations) and seniority level, then schedules calendar events and produces trackable artifacts.

Workflow

<Definition - 30/60/90 Day Framework> A phased onboarding structure that breaks the first three months into distinct periods with escalating expectations:

  • Days 1-30 (Learn): Orientation, tool setup, team introductions, shadowing, and absorbing context. Success means the new hire can describe the team's mission, navigate internal tools, and identify key stakeholders.
  • Days 31-60 (Contribute): First independent tasks, pairing on projects, attending design reviews or standups actively. Success means the new hire has shipped at least one small deliverable and can operate with minimal hand-holding.
  • Days 61-90 (Own): Taking ownership of a workstream, proposing improvements, driving meetings. Success means the new hire is operating at the level expected for their role and seniority. </Definition - 30/60/90 Day Framework>

<Definition - Onboarding Buddy> A peer-level team member (not the manager) assigned to help the new hire navigate informal norms, answer "silly questions," and provide social connection. The buddy commits to:

  • Daily 15-minute check-ins during week 1
  • Twice-weekly check-ins during weeks 2-4
  • Weekly check-ins during months 2-3
  • Being responsive on chat for ad-hoc questions throughout

The buddy should have at least 6 months of tenure on the team and not be on a performance plan or active leave during the onboarding window. </Definition - Onboarding Buddy>

<Workflow - Onboarding Plan description="End-to-end onboarding program creation for a new hire." tools=[file_write, run_python, open_in_session_tab] triggers=["set up onboarding", "create onboarding plan", "new hire checklist", "30-60-90 plan", "onboard new team member", "prepare for new joiner"]

  1. [Agent] Determine today's date. Calculate the number of days until start_date. If start_date is in the past, alert the user and ask whether to proceed with a compressed plan starting today. If fails: If the date calculation fails, ask the user to confirm today's date and the start_date in an explicit format (YYYY-MM-DD) before continuing.

  2. [Ask user] Confirm all inputs: new_hire_name, role, start_date, team, manager_name, and buddy. If buddy is not provided, ask the user to suggest one or confirm you should leave it as TBD. Clarify seniority level (entry, mid, senior, staff+, director+) and whether the hire is remote or in-office. If fails: Re-ask for any inputs still missing; if seniority or work location cannot be confirmed, note the assumption used and ask the user to correct it.

  3. [Decide] Per Rule 10, if start_date is more than 30 days away, flag the plan as preliminary and recommend revisiting. Otherwise proceed to full plan generation.

  4. [Think] Based on role type and seniority, determine the appropriate plan shape:

    • Engineering roles: emphasize codebase orientation, dev environment setup, first PR milestones, on-call shadowing.
    • Product roles: emphasize stakeholder mapping, roadmap context, first spec or decision document.
    • Design roles: emphasize design system review, critique participation, first design deliverable.
    • Operations/other roles: emphasize process documentation, cross-team dependencies, first process improvement. Adjust milestone difficulty and autonomy expectations by seniority.
  5. [Agent] Build the tool access checklist based on role type. Include standard items (email, calendar, chat, HR system, wiki) plus role-specific items (code repositories and CI/CD for engineering, analytics dashboards for product, design tools for design). Present as a checklist with owner (IT, manager, or self-service) and target completion date (all within first 3 days). If fails: If role-specific tools cannot be determined, present the standard checklist and ask the user which additional systems apply.

  6. [Agent] Draft the full 30/60/90 day plan using the Plan Template. Structure into three phases with weekly breakdowns for month 1 and bi-weekly breakdowns for months 2-3. Include milestones, success criteria, and responsible parties for each item. If fails: If the plan cannot be drafted from the template, report the error and retry once before asking the user to simplify scope.

  7. [Agent] Draft the recurring meeting schedule:

    • Manager 1:1: weekly, 30 minutes, starting day 2
    • Buddy check-in: daily 15 minutes in week 1, twice-weekly in weeks 2-4, weekly in months 2-3
    • Team standup or sync: per existing team cadence
    • 30-day checkpoint: manager + new hire, 45 minutes
    • 60-day checkpoint: manager + new hire, 45 minutes
    • 90-day review: manager + new hire + skip-level optional, 60 minutes If fails: If the schedule cannot be generated, present the meeting list in plain text so the user can adjust it manually.
  8. [Ask user] Present the complete draft plan and meeting schedule. Invite edits. Highlight any assumptions made about tool access or team norms. Do not proceed until the user approves. Validate: Explicit approval received, or edits incorporated and re-presented. If fails: If the user does not approve, capture their requested edits, revise the draft, and re-present before proceeding.

  9. [Agent] Save the finalized onboarding plan as a Markdown document using file_write. Open it in the session tab for the user. If fails: If the file cannot be saved or opened, report the error and provide the full plan content inline so it is not lost.

  10. [Ask user] Ask whether to schedule the recurring calendar events now. Per Rule 1, show the full list of events with dates, times, attendees, and frequency. Wait for explicit approval. Validate: User approves the calendar event list. If fails: If the user does not approve the event list, skip calendar creation and note the events as manual follow-up items.

  11. [Agent] Create calendar events via the connected calendar provider for each approved item. Use the manager as the organizer for events that include the new hire (per Gotchas). Set appropriate reminders (15 minutes for check-ins, 1 day for milestone reviews). If fails: List which events could not be created and provide manual instructions.

  12. [Decide] If buddy was confirmed, generate the buddy briefing using the Check-in Agenda Template and save as a separate document. If buddy is TBD, note this as an open action item.

  13. [Agent] Present a summary of completed actions: plan document saved, calendar events created (with count), and any open items requiring follow-up. If fails: If the summary cannot be generated, list the completed and outstanding actions in plain text.

</Workflow - Onboarding Plan>

<Template - 30/60/90 Day Plan>

Onboarding Plan: {{new_hire_name}}

Role: {{role}} Team: {{team}} Start Date: {{start_date}} Manager: {{manager_name}} Buddy: {{buddy}}


Phase 1: Learn (Days 1-30)

Week 1: Foundations

  • Complete tool access setup (see checklist below)
  • Meet manager for expectations alignment
  • Meet buddy for informal orientation
  • Review team wiki and onboarding reading list
  • Attend first team standup/sync
  • Complete mandatory compliance training (if applicable)

Week 2: Context Building

  • 1:1 introductions with immediate team members
  • Shadow a key workflow or process end-to-end
  • Review recent project artifacts for context
  • Identify first small task or contribution

Weeks 3-4: First Steps

  • Complete first small deliverable
  • Attend cross-team meetings as observer
  • Document questions and gaps for 30-day checkpoint

30-Day Milestone: Can describe team mission, navigate tools independently, and has completed one small deliverable.


Phase 2: Contribute (Days 31-60)

Weeks 5-6: Building Momentum

  • Take on first independent task with defined scope
  • Participate actively in team discussions and reviews
  • Begin building relationships with adjacent teams

Weeks 7-8: Expanding Impact

  • Pair with a teammate on a medium-complexity project
  • Present work or findings to the team
  • Identify one area for process improvement

60-Day Milestone: Has shipped at least one meaningful deliverable independently and operates with minimal guidance on routine work.


Phase 3: Own (Days 61-90)

Weeks 9-10: Taking Ownership

  • Own a workstream or project area end-to-end
  • Drive at least one meeting or discussion
  • Propose an improvement to team process or tooling

Weeks 11-12: Full Integration

  • Operate at expected level for role and seniority
  • Mentor or assist newer team members if applicable
  • Prepare self-assessment for 90-day review

90-Day Milestone: Fully ramped, owning work independently, and contributing to team direction.


Tool Access Checklist

ToolOwnerTarget DateStatus
Email and CalendarITDay 1
Chat (Slack/Teams)ITDay 1
HR SystemSelf-serviceDay 1
Wiki/DocumentationManagerDay 1
[Role-specific tools][Owner]Day 1-3

Key Meetings

MeetingFrequencyDurationAttendeesStart
Manager 1:1Weekly30 min{{manager_name}}, {{new_hire_name}}Day 2
Buddy check-inSee schedule15 min{{buddy}}, {{new_hire_name}}Day 1
30-day checkpointOnce45 min{{manager_name}}, {{new_hire_name}}Day 30
60-day checkpointOnce45 min{{manager_name}}, {{new_hire_name}}Day 60
90-day reviewOnce60 min{{manager_name}}, {{new_hire_name}}Day 90
</Template - 30/60/90 Day Plan>

<Template - Check-in Agenda>

Onboarding Check-in Agenda

New Hire: {{new_hire_name}} Meeting With: [Manager or Buddy] Date: [Date] Phase: [Learn / Contribute / Own]


Standing Questions

  1. What went well since our last check-in?
  2. What felt confusing or frustrating?
  3. Is there anything blocking your progress?
  4. Do you have what you need in terms of tools, access, and information?
  5. Who else should you be meeting with that you have not yet?

Phase-Specific Questions

Days 1-30 (Learn)

  • Are you clear on the team's priorities and how your role fits?
  • Is the pace of introductions and reading manageable?
  • Do you feel comfortable asking questions?

Days 31-60 (Contribute)

  • Do you have enough context to work independently on your current task?
  • Are there decisions you are unsure you have authority to make?
  • How is your relationship with adjacent teams developing?

Days 61-90 (Own)

  • What would you change about how the team works?
  • Are there areas where you want more responsibility?
  • Do you feel you are operating at the level expected for your role?

Action Items

  • [Captured during meeting] </Template - Check-in Agenda>

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 Onboarding Orchestrator AI skill do?

Designs and manages end-to-end employee onboarding programs with structured 30/60/90 day plans, buddy assignments, meeting schedules, tool access checklists, and milestone tracking. Adapts plans by role type and seniority. Use when asked to 'set up onboarding', 'create onboarding plan', 'new hire checklist', '30-60-90 plan', 'onboard new team member', or 'prepare for new joiner'.

Why use Onboarding Orchestrator on TypingMind?

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

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/Amazon-Quick/Amazon-Quick-official-catalog/tree/main/skills/hr/onboarding-orchestrator. 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 Onboarding Orchestrator?

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 Onboarding Orchestrator?

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

Is the Onboarding Orchestrator AI skill free?

Yes. It is published on GitHub by Amazon-Quick under the MIT-0 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 👇