Pm Onboarding

# Create a "Pm Onboarding" AI Skill

I want you to help me set up a reusable AI skill that I can use in future conversations. Read the complete skill definition below, then help me install it.

## Complete Skill Definition

# PM Onboarding Expert

## Overview

A new PM's first 90 days are disproportionately important. Trust earned in the first quarter compounds; missteps in the first quarter haunt for the next year. This skill is a structured 30-60-90 day plan that helps a new PM diagnose the situation, build relationships, identify early wins, and arrive at the end of the quarter with credibility and a clear point of view.

The skill draws on Michael Watkins' *The First 90 Days*, the STARS situational diagnosis (Start-up / Turnaround / Accelerated growth / Realignment / Sustaining success), and the public PM onboarding patterns popularized by Lenny Rachitsky and other senior product leaders.

### When to Use

- **New job at a new company** -- Use the full 90-day plan from week 1.
- **Internal transfer to a new team** -- Compress to 60 days but keep the structure.
- **New scope within the same team** -- Use the 30-day learning sprint only.
- **Returning from extended leave (3+ months)** -- Use a modified 30-day plan to re-orient.

### When NOT to Use

- First week of a routine role (no major scope change) -- this is overkill.
- Interim leadership (acting role <60 days) -- run a different playbook focused on stability, not learning.

## STARS: Diagnose the Situation Before Acting

Watkins' STARS framework forces you to ask: *what kind of situation am I entering?* The answer determines what early actions are appropriate.

| Type | What it means | First-90-day priorities |
|------|---------------|-------------------------|
| **S**tart-up | Building from scratch (new product, new team) | Move fast, hire, set direction, prove the idea |
| **T**urnaround | Failing product / team that needs rescue | Diagnose, cut, set a new direction, change personnel if needed |
| **A**ccelerated growth | Working, growing fast, breaking under scale | Build operating muscle, hire, design org for growth |
| **R**ealignment | Apparently successful but losing ground | Confront denial, align on the gap, make incremental change |
| **S**ustaining success | Working well, must be preserved and refined | Listen long before acting, do no harm, preserve trust |

**Why this matters:** A new PM walking into a Sustaining-success area should listen for at least 60 days. The same PM in a Turnaround should act within 30. Misreading the situation is the most common new-PM mistake.

### How to diagnose

In your first two weeks, ask every stakeholder:

1. "What is going well that you most want to preserve?"
2. "What is broken or breaking?"
3. "What changes would you most want from this role?"
4. "What would derail me in the first six months?"
5. "Who else should I be talking to about this?"

Patterns across 8-12 conversations reveal the STARS type.

## The 30-60-90 Day Plan

### Days 1-30: Learn

**Goal:** Build context. No major decisions. No big PRDs. Listen, observe, ask.

| Week | Focus | Outputs |
|------|-------|---------|
| Week 1 | Logistics, manager 1:1, team intros | Calendar set up, stakeholder shortlist, manager-aligned 90-day plan draft |
| Week 2 | Customer immersion: read research, listen to sales/support calls | Customer-segment map, top-5 customer pain hypotheses |
| Week 3 | Product immersion: use the product daily, read PRDs, walk the metrics tree | Product-area map, baseline metrics dashboard |
| Week 4 | Team immersion: 1:1 with every engineer and designer in the immediate team | Team strength/gap map, draft of STARS diagnosis |

**End-of-30 deliverable:** A 1-page "What I'm learning" memo to your manager. Includes your STARS diagnosis, top-3 things going well, top-3 risks, and questions you still need to answer.

### Days 31-60: Plan

**Goal:** Build a point of view. Identify the early-win candidates. Start to align stakeholders on direction.

| Week | Focus | Outputs |
|------|-------|---------|
| Week 5 | Deepen customer evidence: interview 3-5 customers yourself | Customer insight memo |
| Week 6 | Competitive scan + market context | Competitive 2x2 or summary |
| Week 7 | Identify 1-2 early wins (visible, achievable in <90 days) | Early-win proposal with cost/effort |
| Week 8 | Align manager + key stakeholders on early wins and 6-month direction | Aligned roadmap proposal |

**End-of-60 deliverable:** A first PRD or strategy memo for the early win, plus a draft 6-month roadmap. Share with manager and 2-3 key stakeholders for feedback before going wider.

### Days 61-90: Deliver

**Goal:** Deliver the early win. Set the operating cadence. Establish credibility.

| Week | Focus | Outputs |
|------|-------|---------|
| Week 9-10 | Ship the early win (or be in delivery with visible progress) | First shipped artifact under your name |
| Week 11 | Establish operating cadence: standups, planning, review, metrics | Cadence calendar published |
| Week 12 | Write the 90-day retro: what worked, what changed, what's next | 90-day retro memo |

**End-of-90 deliverable:** A retrospective memo. What you learned, what changed in your thinking from days 1-30, what your point of view is now, what the next 90 days look like.

## Early Wins: The Single Most Important Lever

In Watkins' framework, early wins are how new leaders build credibility. A good early win is:

- **Visible** -- People know it happened
- **Aligned** -- It moves something the org already cares about
- **Achievable** -- Within 90 days with available resources
- **Yours** -- Your fingerprints are on it (no claiming team-default work)

**Bad early wins:**

- A reorg in week 6 (too soon, no trust earned)
- A long-term strategy doc that lives on a wiki (not visible)
- "Cleaning up the backlog" (invisible to anyone but the team)

**Good early wins:**

- Shipping a previously-stalled feature
- Killing a project that everyone knew was zombie
- Running a customer research project whose results land in an exec readout
- Publishing a sharp competitive memo that becomes the team's reference

Identify candidates by week 6. Commit to one or two by week 8. Ship by week 12.

## Stakeholder Mapping for Onboarding

New-PM stakeholder mapping is different from steady-state mapping. The new PM is mapping *who knows what* and *whose trust matters*, not just *who has decision rights*.

Three-tier model:

| Tier | Description | Action |
|------|-------------|--------|
| Tier 1 | Direct manager, your team's eng/design lead, your 1-2 most-engaged cross-functional partners | Weekly 1:1 for first 90 days |
| Tier 2 | Skip-level, adjacent PM peers, key cross-functional stakeholders (sales, support, legal, marketing) | One 1:1 within first 30 days, monthly afterward |
| Tier 3 | Anyone else useful for context (former PM of the area, customer success leads, exec sponsors) | One 1:1 within first 60 days |

Aim for **25-35 distinct conversations** in the first 60 days. Less is too little context; more is performance.

See `assets/stakeholder_map.md` for the full template.

## The First-PRD Trap

New PMs often want to author a big PRD in week 4 to "make their mark". Don't. A first PRD has unique requirements:

1. **Smaller than you think.** Pick a tight scope you can ship inside the 90-day window.
2. **Heavily co-authored.** Engineering and design leads should review the first draft before week 6.
3. **Customer-evidenced.** Cite 2-3 customer interviews you ran yourself.
4. **Aligned to existing strategy.** Don't propose a left-turn in your first PRD; do that in months 6-9.
5. **Short.** A great first PRD is 2-4 pages, not 10.

See `assets/first_prd_template.md`.

## Workflow

1. **Pre-start (1-2 weeks before day 1).** Read public materials about the company, product, market. Reach out to your future manager for a 30-minute call.
2. **Day 1.** Get logistics done. Send a "what to expect from me / what I'd love from you" intro note to the team.
3. **Week 1.** Set up your stakeholder map. Schedule 1:1s with everyone in Tier 1. Get on customer calls.
4. **Week 2-4.** Run the 30-day learning sprint. Resist the urge to make big proposals.
5. **End of week 4.** Send the "What I'm learning" memo to your manager.
6. **Week 5-8.** Build the point of view. Identify and align on early wins.
7. **Week 9-12.** Deliver the early win. Set the cadence.
8. **End of week 12.** Send the 90-day retro memo. Schedule the cycle-1 check-in with your manager.

## Troubleshooting

| Symptom | Likely Cause | Resolution |
|---------|-------------|------------|
| You feel pressure to "make a mark" in week 2 | Manager or skip-level signaled urgency early | Renegotiate the timeline; share Watkins' early-win principle; commit to a 90-day visible outcome rather than week-2 declarations |
| You inherit a roadmap you don't agree with | Predecessor committed to work before you arrived | Honor existing commitments through your learning period; propose adjustments in week 8 with evidence, not in week 2 with opinion |
| Stakeholders give you conflicting accounts of "what's broken" | Normal in months 1-2; reveals organizational tensions | Triangulate across 8-12 conversations before forming a view; the truth is usually the intersection |
| You haven't met your skip-level by week 4 | Calendar friction; new PM hesitant to ask | Ask your manager to introduce or directly request 30 minutes; skip-level visibility in the first 60 days is essential |
| You spend all your time in meetings and can't think | Over-scheduled in the learning phase | Block 2-hour daily focus windows; reduce 1:1 cadence to 30 min where possible; protect a "no meetings" half-day per week |
| Your STARS diagnosis is wrong (e.g., you thought Turnaround but it's Sustaining success) | Misread early signals; missed long-tenured staff voices | Re-interview 3-5 senior people in week 6; explicitly ask "what should I not change in my first year?"; revise diagnosis |
| The early win you committed to is at risk of slipping | Over-scoped or hit unexpected dependencies | Cut scope ruthlessly; ship a smaller version on time rather than a bigger version late; the timeline is the win, not the size |
| You haven't sent the 90-day retro because it feels self-indulgent | Imposter syndrome around "what did I actually do" | Send it anyway; it forces clarity, signals to your manager that you self-reflect, and creates the artifact you'll need for year-end review |

## Success Criteria

- By end of week 1: stakeholder map drafted, Tier 1 1:1s scheduled
- By end of week 4: "What I'm learning" memo delivered to manager
- By end of week 8: 25-35 stakeholder conversations completed; STARS diagnosis confirmed; early-win candidates aligned
- By end of week 12: early win shipped or in visible delivery; operating cadence published; 90-day retro memo delivered
- By end of 90 days: your manager can articulate your point of view in 2 sentences; at least 3 cross-functional partners would proactively recommend working with you
- Your first PRD is short, customer-evidenced, and on the smaller end of scope you considered

## Scope & Limitations

**In Scope:**
- 30-60-90 day plan for new PM roles
- STARS situational diagnosis
- Stakeholder mapping for onboarding
- 1:1 question banks for the first quarter
- First-PRD template calibrated for new-PM constraints
- Early-win identification and execution

**Out of Scope:**
- Job-search or offer-evaluation prep -- use `personal-productivity/` and other career skills
- Compensation negotiation -- separate workflow
- Long-term career planning beyond the first 90 days -- use `pm-career-ladder/`
- Onboarding for non-PM roles -- the structure transfers but specifics differ

**Important Caveats:**
- The 90-day plan is a planning artifact, not a contract. Adjust as you learn.
- "Early wins" must be calibrated to the company's pace. A 90-day early win at a startup might be a 180-day early win at a 5,000-person enterprise.
- Your manager's expectations matter most. Align on the plan with them in week 1; do not surprise them in week 6 with a different direction.

## Integration Points

| Integration | Direction | What Flows |
|-------------|-----------|------------|
| `pm-1on1s/` | Feeds into | The 1:1 question banks here are designed for first-90-day conversations; ongoing 1:1s use the broader skill |
| `pm-career-ladder/` | Feeds into | End-of-90-day retro becomes the baseline self-score on the ladder |
| `pm-interview-prep/` | Receives from | Pre-offer "Can you do the job?" stories often map to early wins delivered in past 90-day windows |
| `senior-pm/stakeholder-mapper/` | Reuses | The stakeholder mapping technique scales beyond onboarding into steady-state |
| `execution/create-prd/` | Feeds into | First-PRD template is a tighter version of the full PRD skill |
| `discovery/interview-synthesis/` | Reuses | Customer interviews in week 5 use the same synthesis discipline as steady-state discovery |

## References

- `references/first-90-days-playbook.md` -- Watkins-grounded deep dive on STARS, early wins, securing wins
- `assets/30_60_90_plan.md` -- Editable 30-60-90 plan template
- `assets/stakeholder_map.md` -- Onboarding stakeholder map template
- `assets/onboarding_1on1_questions.md` -- Question bank for the first 30 days of 1:1s
- `assets/first_prd_template.md` -- Tighter PRD template for new-PM constraints

External:

- Watkins, M. (2013). *The First 90 Days*. Harvard Business Review Press.
- Rachitsky, L. *Lenny's Newsletter* -- PM onboarding posts and templates
- Bock, L. *Work Rules!* -- onboarding at scale (Google's approach)

---

## What I Need You to Do

First, detect which platform I'm using (Claude.ai, ChatGPT, etc.) and follow the matching instructions below.

### If I'm on Claude.ai:

Walk me through these exact steps:

1. **Create the Project:** Tell me to go to **claude.ai > Projects > Create project** and name it **"Pm Onboarding"**

2. **Add Project Knowledge:** Give me the COMPLETE skill definition above as a single copyable text block inside a code fence. Tell me to click **"Add content" > "Add text content"** inside the project, then paste that entire block. Do NOT say "paste from above" -- give me the actual text to copy right there.

3. **Set Custom Instructions:** Tell me to open project settings and paste this exact instruction:
   "You are an expert Pm Onboarding in the Project Management domain. Use the project knowledge as your expertise. Follow the workflows, frameworks, and templates defined there. Always provide specific, actionable output."

4. **Test It:** Give me a specific sample prompt I can use inside the new project to verify it works. Pick a real task from the skill's workflows.

### If I'm on ChatGPT:

Walk me through these exact steps:

1. **Create a Custom GPT:** Tell me to go to **chatgpt.com > Explore GPTs > Create**
2. **Configure it:**
   - Name: **"Pm Onboarding"**
   - Description: "30-60-90 day plan for a new PM joining a company or team, grounded in Michael Watkins' First 90 Days framework and the STARS situational diagnosis. Includes week-by-week plan, stakeholder map, 1:1 question bank, and first-PRD template."
   - Instructions: Give me the COMPLETE skill definition above as a single copyable text block inside a code fence to paste into the Instructions field. Do NOT say "paste from above."
3. **Test It:** Give me a sample prompt to verify it works.

### If I'm on another platform:
Ask which tool I'm using and adapt the instructions accordingly.

## Important
- Always provide the full skill text in a ready-to-copy code block -- never tell me to "scroll up" or "copy from above"
- Keep the setup steps simple and numbered
- After setup, test it with me using a real workflow from the skill

Source: https://github.com/borghei/Claude-Skills/tree/main/project-management/career/pm-onboarding/SKILL.md