I (finally!) got access to Claude Code officially at work. I’ve been feeling a bit behind the curve since it seems like most product teams have had licenses for months. So I’ve been trying to lock in and play catch up by exhaustively learning and applying ways I can automate my routine execution tasks so I can focus more on the judgment, taste, and influence aspects of the job.
Here is a day-by-day breakdown of exactly how I set that up over my first week:
day 1 - setup + installing mcps
We didn’t have access to Enterprise yet, so I only installed Claude on my terminal and used their API usage billing to get credentials. I personally prefer running Claude directly within an IDE like Cursor. By keeping Claude open in a terminal side-panel, I maintain context on the active directory and open files as visual cues while I chat with Claude.
Below is my personal setup that with Cursor as an IDE + Claude opened in the terminal as a side panel:
When it comes to setting up MCPs, I first set up Figma and Jira since those were the two applications I’d been interfacing with the most in my day to day. Below is the exact process I used (including some trial-and-error learnings) to connect an MCP, using Notion as the example:
Fetch the command: Copy the specific installation command from Claude Code’s MCP documentation for your target server.
Execute: Paste and run the command in your terminal.
Re-initialize: You will likely need to restart the session for the MCP to register. You can either start a new session entirely or kill the current one using
Ctrl + Con Mac.Verify: Type
/mcpin the terminal to view your active list of connected servers.Authenticate: Hit authenticate. This opens a new browser window (or tab) where you’ll authorize the connection.
Confirm: You’ll know the handshake was successful when you see an “Authentication Successful” message in the browser, mirrored by an “Authentication successful. Connected to [MCP name].” prompt in your terminal.
day 2 - project folder setup
I knew from a recent PM webinar that building reusable “skills” was the key to maximizing use out of Claude Code for PMs, but the optimal directory structure to enable that wasn’t immediately obvious.
When I prompted Claude to create my first skill to write weekly program review updates, it defaulted to a global setup, storing the skill at the root level of my laptop. I had to explicitly course-correct the LLM to adopt a project-local architecture, ensuring that my AI skills and knowledge were isolated within the specific project folder.
After a few steering prompts, I landed on this directory structure:
.
├── .env # Environment variables (e.g., API keys for tools like Jira)
└── .claude/ # AI configuration and workspace directives
├── claude.md # Master instructions: Defines the PM persona, standard tone, and overarching goals
├── skills/ # Active capabilities: The "How-To" instructions for the AI
│ ├── create-jira-tickets/
│ │ └── skill.md # Rules for writing user stories, defining acceptance criteria, and sizing
│ └── create-prd/
│ └── skill.md # Your standard PRD template, required sections, and formatting rules
└── knowledge/ # Passive context: The "What" and "Why" behind the product
├── strategy/ # OKRs, quarterly roadmaps, and high-level product vision
├── competitive-research/ # Competitor teardowns, feature matrices, and market positioning
├── customer-research/ # User interview transcripts, survey data, and synthesized pain points
├── meetings/ # Raw meeting notes, transcripts, and weekly sync action items
└── decisions/ # Decision logs (e.g., DACI frameworks), trade-offs, and pivot rationalesIn retrospect, I should have treated the folder structure itself as a product feature. If I were starting over, I would spend more time upfront using Claude’s /plan mode to architect an optimal, scalable folder hierarchy before writing any markdown files.
day 3 - populating the knowledge base
I came into Day 3 pretty ambitious. My initial instinct was to create dozens of skills right out of the gate, but I realized that skills are less useful without the right context. So I started migrating a few of my core work artifacts into the .claude/knowledge/ directory to test against my skills.
Here’s the data ingestion workflow I used to convert my knowledge into a machine-readable format:
Dump the unstructured data: I created raw Markdown files and pasted in messy, unformatted text. Some examples of the context I brought over included raw Zoom audio transcripts, existing product strategy documents, and deep research outputs generated via Gemini.
Build formatting skills: Rather than manually cleaning this data, I built a few foundational skills specifically designed to parse and normalize raw text into structured frameworks.
Execute the cleanup: Using Claude Code, I invoked the formatting skill in the terminal and used the
@reference to point the AI directly at the.mdfile to rewrite it.
With my context properly ingested, the directory started to look like this:
.
├── .env
└── .claude/
├── claude.md
├── skills/
│ ├── create-jira-tickets/
│ │ └── skill.md
│ └── format-zoom-transcript/
│ └── skill.md
└── knowledge/
├── strategy/
│ └── q3-product-growth-strategy.md
├── competitive-research/
│ └── competitor-teardown-tax-filing-alternatives.md
├── customer-research/
│ └── user-interviews-self-employed-tax-pain-points.md
├── meetings/
│ └── 2026-03-10-product-strategy-sync-transcript.md
└── decisions/day 4 & 5 - creating more skills
With my .claude/knowledge/ directory populated, I was ready to start executing workflows. I wanted to break down the types of cognitive tasks Claude Code could handle. Instead of just looking at what the AI can “type,” I started framing my skills around the level of cognitive load they remove from my plate.
These fall into three distinct tiers, scaling from basic data processing to advanced critical evaluation:
tier 1: information processing
Example skill: /format-zoom-transcript
Reasoning effort: Low
Task scope: High volume
AI just needs to parse a massive amount of messy, unstructured data (like the raw transcripts) and format it into a clean, legible structure. I personally benefit from these types of skills by reclaiming energy it takes to parse through meeting minutes and manually pick out important information like action items.
Raw input
Bagels [ Owner Kaci Nguyen ]-Shared screen with speaker view
Mar 10, 2026 10:30 AM
Who can see your viewing activity?
00:00:02/00:26/12
Speed
Audio Transcript
Chat Messages
Search transcript
Kaci Nguyen
Kaci Nguyen
Hi everyone so this morning... I made bagels.
Casey Wynn
Casey Wynn
00:27
That sounds delicious. What kind?
Kaci Nguyen
Kaci Nguyen
00:41
Everything.Output
# Bagel Meeting - March 10, 2026
[00:00] Kaci Nguyen: Hi everyone so this morning... I made bagels.
[00:27] Casey Wynn: That sounds delicious. What kind?
[00:41] Kaci Nguyen: Everything.tier 2: structured facilitation
Example skill: /write-decision-doc
Reasoning effort: Medium
Task scope: High organization
AI is taking on the cognitive load that I’d typically bear when organizing an argument from the logical structuring to the trade-off articulation. Instead, I’m able to focus strictly on the content and information gathering from stakeholders.
Here is an example skill file I use:
---
name: write-decision-doc
description: Drafts a structured decision document using the DACI framework (Options, Pros/Cons, Recommendation).
triggers: ["write a decision doc", "help me document this decision", "create a decision doc for", "I need to make a decision on", "/write-decision-doc", "options analysis"]
version: 1.0.0
---
# Skill: Write Decision Doc
Draft a structured decision document using standard frameworks: Decision Trigger, DACI, Options, Pros/Cons, Recommendation, and Helpful Details. Gather context from the user first, then produce a filled-in draft ready to share with stakeholders.
## Step 1: Gather Context
Use your standard questioning capability to collect essential inputs. Ask up to 4 questions at once. Tailor the questions to any context already provided in the conversation. Skip questions if the answers are already clear from provided Slack threads, meeting notes, or requirements.
Always ensure you know:
- **The Decision:** What needs to be decided and what triggered it.
- **The Driver (D):** Who owns this decision.
- **The Approver (A):** Who has final authority.
- **The Goal Framing:** What outcome the decision serves (e.g., revenue, user experience, learning).
## Step 2: Identify the Decision Type
Based on the context, determine how comprehensive the document needs to be. When in doubt, use the full template below. The user can always trim it later.
## Step 3: Draft the Document
Fill in the template below using the gathered context. Apply these writing rules:
- Lead every section with the key point.
- Use active voice.
- Be specific: use names, dates, and numbers where known.
- One idea per sentence.
- Use explicit `[TBD]` placeholders where information is missing. Never guess or hallucinate facts.
---
## Output Template
```markdown
# DECISION: [Name of Decision]
**Driver:** [Name] | **Last Update:** [YYYY-MM-DD]
---
## Decision Trigger
[1-3 sentences. What happened that requires a decision? Lead with the situation, end with the specific question that needs answering.]
---
## DACI & Status
- **Status:** [Not Started / In Review / Approved]
- **Target Date:** [MM/DD/YYYY]
- **Driver:** [Name]
- **Approver:** [Name]
- **Consulted:** [Names or Teams]
- **Informed:** [Names or Teams]
---
## Options & Recommendation
**Recommended Option:** [State the winning option here in one clear sentence and briefly explain why.]
| Option | Description | Pros | Cons | Consulted POV |
| :--- | :--- | :--- | :--- | :--- |
| **1. [Name]** | [One-sentence summary] | - [Pro] | - [Con] | [Notes] |
| **2. [Name]** | [One-sentence summary] | - [Pro] | - [Con] | [Notes] |
| **3. [Name]** | [One-sentence summary] | - [Pro] | - [Con] | [Notes] |
---
## Helpful Details
- [Key constraint, context, or technical detail]
- [Key constraint, context, or technical detail]
### Related Docs
1. [[Doc Name]](Link or "TBD")
2. [[Doc Name]](Link or "TBD")
```
---
## Step 4: Save the File
Save the finalized draft to the workspace knowledge repository:
`knowledge/decisions/[decision-name].md`tier 3: cross-context analysis & critical evaluation
Example skill: /review-product-strategy
Reasoning effort: High
Task scope: High complexity
This is the most advanced cognitive tier where AI acts as a strategic thought partner. To do this, AI uses multiple contexts at once (such as leveraging competitive research files and customer transcripts) and evaluate a net-new artifact against them. This can be used to pressure-test work and avoid blind spots by checking the strategy against any real-world realities that may have been overlooked.
Example prompt:
Review @knowledge/strategy/q3-product-growth-strategy.md against @knowledge/competitor-teardown-tax-filing-alternatives.md and @knowledge/user-interviews-self-employed-tax-pain-points.md.
For each of these dimensions, give a brief assessment with a Strength and a Gap or Risk:
- Market alignment
- Competitive positioning
- Customer focus
- Business model coherence
- Execution risk
- Strategic continuity
Close with the top 3 gaps ranked by business risk.day 6 - ad-hoc tasks
This evening, I was moderating an alumni panel for the Intuit RPM/RDP 20th Anniversary. Because this panel was a one-time event, I figured the ROI of building a dedicated skill and saving it to my .claude directory wasn’t there.
Instead, I spun up a new terminal session as a new node purely for ad-hoc prep. The organizing team had curated a list of great questions for the panelists, but I felt some were phrased too formally for me to deliver them naturally.
So I fed the questions into Claude and used it for stylistic alignment, prompting it to rewrite the question to match my natural speaking voice and ensure the moderation felt conversational rather than scripted. It did pretty well for a few of them, but there were one of two where I needed to course-correct by providing it feedback.
Example:
Before:
In transitioning from a highly structured enterprise environment to founding an early-stage startup, which established product management methodologies did you find counterproductive and subsequently have to unlearn?
After:
Intuit teaches us incredible frameworks for building products at scale for hundreds of thousands of customers. But going to zero-to-one or even one-to-ten is a totally different beast. As a founder, what Intuit skills did you quickly realize you had to unlearn to scale your startup?
day 7 - skill prototyping framework
I came across Pawel Huryn’s well-known repository of pre-built PM skills and decided to port them directly into my workspace. It felt like a massive shortcut, but it quickly highlighted a few realities about how AI actually integrates into product work.
First, PM work is inherently cyclical. You aren’t writing vision docs, sizing features, or running sprint retros every single day. Because of this natural cadence, I haven’t been able to organically battle-test this massive library of new skills to gauge their actual quality.
Second, while community-built skills are a great baseline, they are fundamentally generic. They don’t naturally conform to the specific cultural DNA of your company, in my case, the “Intuit way” of communicating, structuring arguments, and driving alignment. The plug-and-play approach doesn’t always work for nuanced product workflows. It’ll need some fine-tuning.
Moving forward, my best practice for creating AI skills is a chat-first prototyping model:
Execute Manually: Run the task organically in a standard chat session first.
Iterate and Calibrate: Course-correct the AI’s tone, formatting, and logic until the output perfectly matches your company’s internal standards.
Codify: Once the output is perfect, prompt Claude with something like: “Extract the rules, formatting, and logic from this conversation and generate a
skill.mdfile in my.claudedirectory so I can replicate this exact workflow next time.”
By treating the chat window as a sandbox, you ensure that every skill you officially save to your directory is already proven, tailored, and highly relevant to your actual day-to-day work.
An example of a /edit-writing skill (had to ask Claude Code to simulate the conversation heh):
Next week, I’m hoping to continue expanding on the skills I’ve created, codifying knowledge, QA-ing the skills, and exploring more advanced features like agent teams 👾