Structured intent, not an open-ended settling-in period.
The tool that turns "spend the first 90 days listening" into a specific plan: what to diagnose, which relationships matter most, one credible early win, and what to deliberately leave alone.
"Listen for the first 90 days" is true and useless on its own. It's an attitude, not a plan, and it often avoids the harder work of deciding what to learn, from whom, and what decision that learning informs.
This tool turns the first 90 days into three distinct phases with specific goals: diagnosis, one deliberately chosen early win, and a documented plan for what comes next, without pretending everything should change on day one.
The first 90 days, structured on purpose.
Same new role, same pressure, run two ways.
A newly hired VP of Marketing joins a company where the previous lead left on bad terms after a string of underperforming campaigns.
You ask Claude for first-90-days advice. You get a solid general framework: build relationships, listen first, don't change too much too fast.
True, and generic enough to apply to any new hire anywhere, which leaves you with an attitude to hold rather than a specific plan for this team, this CEO, and this specific credibility problem.
It builds the plan for this specific situation:
- →Diagnostic conversations named specifically: sales leadership on what actually converts, the CEO on what really prompted the last departure
- →One credible early win chosen deliberately: a single fixable campaign, relaunched by day 45 with a measurable lift
- →An explicit do-not-touch: the existing tech stack, until the undocumented integration reason behind it is understood
The finished plan phases days 1-30 as diagnosis only, days 30-60 around the early win in motion, and days 60-90 around a validated first-quarter plan, so nothing gets proposed before it's actually understood.
The cold version told you to listen first. This told you specifically to whom, about what, and what to do with it.
- ✦New executives and managers starting a role that matters
- ✦Founders taking on a function they haven't run before
- ✦Managers planning onboarding for a senior hire
- →first-90-days.zip: a native Claude Skill. Upload to Settings → Skills in Claude, or unzip to
~/.claude/skills/ - →first-90-days-skill.md: plain markdown. Works in ChatGPT Custom GPTs, Gemini, Claude Projects, agent system prompts, anywhere
- →A README inside the zip with install steps for Claude, ChatGPT, Gemini, and the API
What it does with a real question.
I start on Monday as the new Operations Director at a 120-person manufacturing company. I report to the CEO, inherit a team of eight, and know the sector but not this business. There is a known problem with late deliveries, and the previous director left on poor terms after two years.
Diagnose before you decide. Your temptation will be to attack the late deliveries immediately, because everyone knows it's the problem. Resist treating it as a month-one fix. You know the sector, which is exactly the risk: you'll pattern-match to causes you've seen elsewhere and propose them before you understand this plant. Spend the first thirty days finding out why deliveries are late here, and whether the cause is production, scheduling, purchasing, or promises sales makes that operations can't keep.
The poor-terms exit tells you something too. Ask the CEO directly, in week one, what specifically went wrong between them and the previous director. You need to know whether the friction was about results, style, or a disagreement over what the problem even is, so you don't repeat it unknowingly.
Define day-90 success with the CEO now, in their terms: probably a credible root-cause read on late deliveries plus one measurable improvement, not a transformed operation. Pick that single early win deliberately, something fixable without new budget or authority you haven't earned, such as a recurring bottleneck on one product line.
Equally important, name what you won't touch yet: inherited processes, supplier arrangements, anything that looks wrong but may exist for a reason nobody has told you.
Your next move: on Monday, before meeting the team as a group, book a one-on-one with each of your eight direct reports and ask each what actually causes late deliveries, in their words.
The full Tool runs the whole procedure and writes the complete deliverable, not this excerpt.
Written by claude-sonnet-5-5 with this Tool loaded, 2026-10-11. Checked automatically for length and for copied framework text.
No subscription · free updates within v1.x
Works as a Claude Skill (.zip) and as a plain .md for ChatGPT, Gemini & every LLM
Delivered to your email within 60 seconds · Secured by Stripe
Price includes UK VAT where applicable
Before you buy.
How is this different from just asking Claude directly?
Asked cold, Claude gives general first-90-days advice, listen first, build relationships, don't move too fast, that applies to any new role anywhere. This builds a specific plan for your situation: named diagnostic conversations, a deliberately chosen early win, an explicit do-not-touch list, and phased milestones tied to what you're actually walking into.
Will this work with ChatGPT, Gemini, and other LLMs?
Yes. You get a native Claude Skill (.zip) that auto-invokes in Claude, plus a plain .md you can paste into a ChatGPT Custom GPT, a Gemini system prompt, or any LLM. The procedure travels with the file.
Can I share this with my team?
It's licensed for your own personal and professional use. The output it produces is yours to circulate. To put the Tool itself in the hands of a whole team, email hello@authority.md about team licensing.
What if it doesn't work for me?
If the file hasn't been delivered, or arrives defective or empty, we refund in full: see our refund policy.
First 90 Days Plan is a structured planning tool. Not a substitute for direct conversations with your manager or team about what they actually expect from your first quarter.