Session exercises

Before we start, I want to confirm my setup. Please tell me:

1. 1.Do I have any connectors active — and if so, which ones?
2. 2.Do I have any Global Instructions set — and if so, what are they?

If you can't see either, tell me where to check.

You are helping me build my about-me.md — the knowledge context file that tells Claude who I am, how I work, and what I'm focused on. This file gets read at the start of every Cowork session and lives in my ABOUT ME/ folder.

Before we start, understand what about-me.md must be:

• •KNOWLEDGE only — who I am, my work, my team, my priorities, my tools. Not rules or guardrails (those live in Global Instructions)
• •Rich and detailed — unlike Global Instructions, this file can be as long as it needs to be. Depth is good here.
• •Written for Claude — imagine briefing a brilliant new team member on everything they need to know to be useful to me from day one
• •Updated when priorities shift — this is a living document, not a one-time exercise

What belongs here

• •My name, role, company, team structure
• •My current priorities, goals, and active projects
• •My manager's priorities and how my work connects upward
• •How I like Claude to communicate with me — tone, length, format
• •Which tools and connectors I use and how I use them
• •My most common Claude use cases
• •Anything a sharp new team member would need to know on day one

What does NOT belong here (goes in Global Instructions instead)

• •Rules and guardrails ("never send emails without approval")
• •Always/never behavioural instructions

Now interview me to gather everything you need. Be curious — if an answer is vague, ask a follow-up before moving on. Cover these areas in order:

• •My name, role, company, and what I actually do day-to-day
• •My team — my manager and people across my team (so we can fetch v2mom, slack, email information about them)
• •My active projects
• •Any specific tool, ritual or how I work
• •Anything else a new team member would need to know to be genuinely useful to me from day one

After I've answered everything, produce my about-me.md as a clean, structured markdown file using this format:

About Me — [NAME]

Last updated: [DATE]

WHO I AM

Name, role, company, what I do

MY TEAM

Manager + their priorities / Direct reports / Key collaborators

MY PRIORITIES & GOALS

Current vision, methods, measures, what I'm accountable for

ACTIVE PROJECTS

What's live, what's hot, what needs attention

HOW TO WORK WITH ME

Communication style, tone, length, format, what to avoid

ALWAYS KNOW

Anything else a sharp new team member needs on day one

Be comprehensive. Use bullet points within sections. If an answer was vague, note it with [TO REFINE] so I know to come back to it.

Start with your first question now.

You are helping me build my voice.md — the writing style file that tells Claude how to write on my behalf so it sounds like me, not like generic AI.

Before we start, understand what voice.md must be:

• •Style only — how I write, my tone, my structure, my patterns, what I never say
• •The reference Claude uses for any writing task — emails, Slack messages, documents, comms, updates
• •Specific and concrete — vague descriptions like "professional" are useless. Exact words to ban, real examples of my writing, and precise patterns are what make this file work
• •Distinct from about-me.md — that file says who I am. This file says how I sound.

What belongs here

• •Words and phrases I never want to see in my writing
• •How I naturally structure messages and documents
• •My tone across different audiences
• •My sentence style — length, rhythm, how direct I am
• •Signature phrases or patterns I actually use
• •Real examples of my writing for Claude to study
• •The ANTI-AI writing I am pasting below

What does NOT belong here

• •Who I am, my role, my priorities (those are in about-me.md)
• •Rules and guardrails (those are in Global Instructions)

Now interview me to build this file. Cover these areas in order:

• •Ask me to describe my natural communication style in 3 words (add suggestions)
• •Ask how I typically open and close messages — do I get straight to the point, give context first, use a signature sign-off? (add suggestions)
• •Ask how direct I am when delivering bad news or difficult feedback — do I soften it or say it plainly? (add suggestions)

After I've answered everything, produce my voice.md as a clean structured markdown file using this format:

Voice Profile — [NAME]

Last updated: [DATE]

MY VOICE IN 3 WORDS

[the essence of how I communicate]

WRITING PRINCIPLES

How I open, how I structure, how I close

Sentence length and rhythm

How direct I am

NEVER USE — BANNED WORDS & PHRASES

[concrete list — specific words and phrases to always avoid]

TONE BY AUDIENCE

To my manager: [...]

To my team: [...]

To clients / external: [...]

MY NATURAL PATTERNS

Phrases I actually use / Structures I reach for

ANTI-AI WRITING RULES

Add the rules to prevent Claude from sounding like AI

EXAMPLE OF MY WRITING

[paste the example they gave + 3-5 patterns extracted from it]

Be specific. Generic voice files are useless. Push for concrete examples and exact language throughout.

For the Anti-AI writing, add this to the voice.md file:

When you write for me, it must sound like a human wrote it — not a consultant, not a chatbot, not a LinkedIn post.

THE RULE

If I would cringe reading it back, rewrite it.

NEVER USE THESE WORDS OR PHRASES

delve · leverage (as a verb) · utilize · synergy · robust · seamlessly · streamlined · holistic · paradigm · groundbreaking · game-changing · transformative · foster · elevate · harness · underscore · tapestry · pivotal · overarching · nuanced (as filler) · navigate / landscape / ecosystem / journey (used as metaphors)

"it's not just X, it's Y" · "in today's fast-paced world" · "it's worth noting that" · "let's dive in" · "moving forward" · "first and foremost" · "at the end of the day" · "that being said" · "moving the needle" · "touch base" · "circle back" · "value add" · "actionable insights" · "thought leadership" · "furthermore" · "moreover" · "nevertheless" · "in order to" (just say "to")

Never open with: "Certainly!" · "Absolutely!" · "Great question!" · "I hope this email finds you well" · "Please don't hesitate to reach out"

WRITE LIKE THIS INSTEAD

• •Lead with the point — say the thing first, reasoning after
• •Short sentences — one idea, then the next
• •Be specific — "three customers escalated" not "some concerns were raised"
• •Active voice — "we decided" not "a decision was made"
• •Say bad news plainly — don't soften it into nothing
• •Cut the summary at the end — if it needs a recap, it was too long

Start with your first question now.

Generate my memory.md file — the long-term memory file that YOU (Claude) write to and maintain automatically during our Cowork sessions.

This file is different from my other context files. I don't fill it in — you do. It starts mostly empty but contains the rules that govern how you maintain it. Every time you read this file at the start of a session, you also know how to update it by the end.

Generate the file with this exact structure:

Section 1 — Header

A header explaining what this file is and that Claude maintains it automatically.

Section 2 — Rules for writing

(Claude reads these and follows them every session)

• •Add entries after any session where something significant was decided, completed, or learned
• •Always date-stamp new entries
• •Keep entries to 1–2 lines max — summaries only, never verbatim transcripts
• •Never duplicate what's already stable in about-me.md
• •Never record sensitive personal, financial, or confidential information
• •If a project or decision is already in this file, update the existing entry rather than adding a duplicate

Section 3 — Rules for pruning

(Claude applies these periodically)

• •Mark items [STALE?] if they haven't been referenced in 30 days
• •Remove completed projects once resolved
• •Remove decisions older than 90 days unless still actively relevant
• •Keep the file lean — if it grows beyond 2 pages, compress the oldest entries

Section 4 — Active Projects

(empty, ready for Claude to populate)

Entry format: [DATE] | [PROJECT] | [STATUS] | [NEXT ACTION]

Section 5 — Decisions Log

(empty, ready for Claude to populate)

Entry format: [DATE] | [DECISION] | [CONTEXT]

Section 6 — Context Learned

(empty, ready for Claude to populate)

Things learned about how I work, prefer things, or think — that aren't already in about-me.md

Entry format: [DATE] | [WHAT WAS LEARNED]

Section 7 — Open Loops

(empty, ready for Claude to populate)

Outstanding items, things to follow up, waiting-on items

Entry format: [DATE] | [ITEM] | [OWNER] | [STATUS]

Create a MEMORY folder in the folder of this conversation and save this file as MEMORY.md inside it.

You are helping me build my Global Instructions for Claude Cowork — the short behavioural rules file that applies to every single Cowork session I run.

Before we start, understand what Global Instructions must be:

• •BEST PRACTICE LENGTH — Write as many rules as are genuinely needed. Every line must earn its place. No padding, no redundancy. Claude decides the right length — not a fixed line count.
• •RULES only — behavioural guardrails and always/never rules. Never biographical facts, context, or knowledge (those go in about-me.md)
• •Always enforced — these apply to every task, every session, no exceptions
• •Must include one block that loads all three context files at session start, using folder-first fallback:
• ◦Read about-me.md from the current session folder first; fall back to ~/about-me.md
• ◦Read voice.md from the current session folder first; fall back to ~/voice.md
• ◦Read memory.md from the current session folder first; fall back to ~/memory.md

**REQUIRED — Execute at session start, before any user interaction automatically load about-me.md, voice.md and memory.md from the current workspace we're working on.

What belongs here

• •"Never send emails without my explicit approval"
• •"Always ask before deleting or modifying any file"
• •"Load about-me.md, voice.md, and memory.md at session start (folder-first, root fallback)"
• •"Use any connectors I have active, if that connector is relevant to my request"
• •High-level tone summary (1 line max — detail lives in voice.md)

What does NOT belong here (goes in other files instead)

• •My name, role, company, projects, priorities, V2MOM → about-me.md
• •Detailed tone, writing style, language preferences → voice.md
• •How I use my tools or what my connectors contain → about-me.md
• •Session history, decisions, open loops → memory.md

Produce my Global Instructions as a clean, paste-ready block — no labels, no headers, no explanation. Just the lines. Prioritise the file-loading block and connector safety rules. Everything else goes in the appropriate context file.

You are a strategic advisor helping me prepare for an upcoming 1:1 with my manager.

Step 1 — Load context

First, read the about-me.md file in the current project folder to understand who I am and my role. If that file doesn't exist, fall back to ~/about-me.md.

Then, using any active connectors (Notion, Slack, Calendar, or others), gather the following — in parallel where possible:

• •My V2MOM
• •My manager's V2MOM
• •Notes from my most recent 1:1 with my manager (look for a Notion page titled "1:1" with my manager's name)
• •Recent Slack messages between me and my manager (check Notion for simulated Slack pages, or use the Slack connector if active)
• •Any upcoming calendar events involving my manager in the next 7 days
• •Any in-flight project pages, status updates, or shared workstreams that are currently active and relevant

If a connector isn't available for a source, note it and skip it — don't block the analysis.

Step 2 — Analyse across three dimensions, from my manager's perspective

For each dimension, give: a rating (Strong / Needs Attention / Gap), a short analysis grounded in what you actually found (not just V2MOM theory — reference recent signals, open items, and anything unresolved from the last 1:1), and one specific thing I should say or raise in the meeting.

• •Upward alignment — Where do my current work and priorities directly serve my manager's goals? Where are the gaps — things they care about that I'm not visibly addressing or that have shifted since the V2MOMs were written?
• •Visibility — What progress or work am I doing that my manager might not fully see? What's happened recently — shipped, decided, at risk — that I should proactively surface rather than wait to be asked?
• •Risk & gaps — What open items, commitments, or concerns from the last 1:1 might my manager be tracking? What am I not addressing that could worry them if left unsaid?

Step 3 — Produce

• •A 5-bullet agenda for the 1:1, ordered by priority to my manager, not to me — anchored in what's live and current, not just strategic theory
• •Two questions I should ask my manager
• •One thing I should ask for — a decision, resource, support, or clarity I need from them

Generate a dedicated memory file for my recurring 1:1 meetings with my manager.

Save it as: 1on1-manager-memory.md in my MEMORY/ sub folder (not in the Claude memory system) in the current folder of this conversation.

This file is maintained by Claude automatically — not filled in manually. It accumulates context from 1-1.

Create a reusable skill called /prepare-manager-1-1.

When this skill is triggered it runs the following steps:

Step 1 — Gather context

• •Look for about-me.md in the current project folder. If not found, fall back to ~/about-me.md. Extract my name, role, and my manager's name and role.
• •Look for MEMORY/1on1-manager-memory.md — load past decisions, recurring themes, and context. If it doesn't exist, note it and continue.
• •Retrieve my V2MOM and my manager's V2MOM using the Notion connector. If unavailable, look for V2MOM files in the project folder.
• •Fetch the most recent 1:1 notes from Notion — look for a page titled "1:1 [Month] [Year] — [My name] & [Manager name]". This is the recency anchor: it shows what was discussed, committed, and left open.
• •Pull recent Slack messages: first check Notion for a page titled "Slack Messages with [Manager name]"; then use the Slack connector if active. Look for the last 7 days.
• •Check the Calendar connector for the upcoming 1:1 — date, time, any existing agenda — and any shared events from the past 7 days.
• •Pull last 7 days of email involving my manager if an email connector is active.

If a connector is unavailable, note it at the top of the prep doc and continue — never block the analysis on a missing source.

Step 2 — Analyse my V2MOM from my manager's perspective across three dimensions

Ground each dimension in what you actually found — use recent signals from the 1:1 notes, Slack, and calendar, not just V2MOM theory. The V2MOM is the strategy layer; the recent sources are the operational layer.

• •Upward alignment — Where do my current work and priorities serve my manager's goals? Where are the gaps, including things that may have shifted since the V2MOMs were written?
• •Visibility — What progress might my manager not fully see? What should I proactively surface rather than wait to be asked?
• •Risk & gaps — What open items or commitments from the last 1:1 might my manager still be tracking? What am I not addressing that could worry them if left unsaid?

For each dimension: a rating (Strong / Needs Attention / Gap), a short analysis citing specific sources, one concrete thing to say in the meeting.

Step 3 — Produce the prep doc

• •5-bullet agenda ordered by priority to my manager, not to me
• •Two questions I should ask
• •One thing I should ask for — a specific decision, resource, support, or clarity (vague asks don't count — it must name a person, a decision, and ideally a deadline)

Save to: OUTPUTS/manager-1on1-prep-[DATE].md

Skill rules

• •If a connector is unavailable, skip it, note it at the top of the prep doc, and keep going
• •Prep doc is a 3-minute read — tight and actionable, not a report

Create this skill now, ready to trigger with /prepare-manager-1-1.

Turn the 1:1 prep into a scheduled task, based on whether I have a 1:1 today.

Create a scheduled task that runs every morning at 7:00 AM. Use /schedule with the following configuration:

• •Frequency: Daily at 07:00
• •Model: Sonnet for prep work, Haiku for calendar check only
• •Name: morning-1on1-prep

WORKFLOW

Step 1 — Read today's calendar

Check today's calendar for any scheduled meetings. Look specifically for:

• •1:1 meetings with my manager
• •1:1 meetings with any of my direct reports
• •Any meeting explicitly labelled "1:1" or "one on one"

Step 2 — Branch A: 1:1 detected

If one or more 1:1s are found, for each 1:1 detected:

• •Identify who the meeting is with and at what time
• •If the meeting is with my manager → run /prepare-manager-1-1
• •If the meeting is with a direct report → run the direct report prep workflow:
• ◦Read my about-me.md and 1on1-manager-memory.md for context
• ◦Pull last 7 days of email and Slack relevant to that person
• ◦Retrieve their V2MOM if available via connector
• ◦Produce: 3 talking points, one coaching question, one thing to acknowledge, any open actions from previous interactions

For each prep produced:

• •Save to OUTPUTS/1on1-prep/1on1-prep-[PERSON]-[DATE].md
• •Send me an email with subject: 1:1 Prep — [PERSON NAME] — [TIME] and the full prep doc as the body
• •Post a summary (3 bullets max) to my #leadership-prep Slack channel with the meeting time and person's name

Step 2 — Branch B: No 1:1 detected

Do nothing. End the task silently.

Task rules

• •If a connector is unavailable, skip that source silently and continue — do not stop the task
• •If /prepare-manager-1-1 skill is not found, fall back to the direct report prep workflow and note the skill is missing
• •Never send emails or post to Slack without completing the full prep first
• •All outputs must be saved before any delivery happens
• •If the calendar shows more than 3 x 1:1s in one day, flag this at the top of the first email: "Heavy 1:1 day — [N] preps generated"

Set this task now using /schedule. Confirm the schedule, the name, and the first run time before saving.

Every weekday at 8am I want you to prepare my day for me. Think of yourself as a chief of staff briefing me with an executive brief before I start my day helping me focus.

First read my about-me file in the project folder so you know who I am and what I'm working on — if it's not there fall back to the one in my home folder.

Then pull up my calendar for the day. For every meeting I have, prep it — use Notion, Gmail, and Slack to find relevant context and summarise what I need to know going in, any open questions, and what a good outcome looks like. One section per meeting in chronological order.

Also go through the last 24 hours across Gmail, Slack, and Notion and surface all the topics I've been involved in. Don't filter — just show me what's been active and let me decide what matters. Group by theme if there's a lot.

Create a "DAILY BRIEFINGS" sub folder in the current workspace folder we're working, in case it doesn't exist yet. If it exists, always save the Daily Briefing files in that sub-folder. Save the briefing as a markdown file named "Daily Briefing — [DATE].md" where [DATE] is today's date in the format "Month Day, Year" (e.g., "Daily Briefing — June 15, 2026.md"). Keep the full file path to the created markdown file.

Then add a 15-minute "Read Daily Briefing" block to my Google Calendar starting 15 minutes before my first meeting (or at 8am if I have no meetings). In the event description, mention to go to DAILY BRIEFINGS > file title, so I can open it directly from the calendar event on any device, and add a TLDR of bullets with the main topics of this briefing, well formatted.

I want my chief of staff to monitor the external signals that matter to me — industry news, regulatory changes, and competitor moves — and deliver a curated briefing, so I stay informed without actively searching.

Set this up as a scheduled task:

• •Frequency: Weekly, every Monday morning
• •Sources: the 5 most relevant external sources for OutSystems — covering low-code / enterprise application development, our key competitors, and the regulatory landscape we operate in
• •Signals to watch: industry news, regulatory changes, competitor moves

Each run:

• •Scan those 5 sources for anything new and relevant since last week
• •Curate it into a single pre-read briefing so I'm up to date at a glance — what changed, why it matters to us, and anything I should act on
• •Email it to me

Before you schedule this, propose the 5 sources you'd monitor and confirm them with me — and ask me anything that isn't clear. Then set up the scheduled task.