Training deck built for an internal practice rollout. De-identified for public viewing. All deal scenarios are fictional.
Claude Desktop · practice enablement

Two ways to
work with Claude.

One desktop app. A spectrum of help — from thinking alongside you, to handing off whole projects.

Claude Chat Claude Cowork
Opener 0:24
Contents

What we'll cover.

Tip — click any part to jump straight to it.

Setting the stage · where today fits

Building on the work you’ve already done.

Through earlier AI training, you’ve already been working hands-on with AI tools — so a lot of today will feel familiar. Here’s how the pieces fit together.

So far · prior AI training

You’ve already built work plans, decks, and dashboards in AI tools. Those instincts carry straight over.

Today · this session

Get comfortable with Chat and Cowork and the key features within them — and how they compound into a way of working.

Next · practice-specific offerings

Practice-specific offerings — built for Integration, Diligence, and Divestiture — are in development. More to come.

The big picture

Same Claude. Two modes of working.

The difference isn't intelligence — it's how much you hand off. As you move from one to the other, you give Claude more room to act on its own, with your approval at the gates.

Chat

You drive. Claude thinks, drafts, and builds with you, turn by turn.

Cowork

You delegate. Claude plans and executes multi-step knowledge work, you approve.

← More conversationalMore autonomous →

You can get a long way just by chatting — but it goes further when you treat this as a way of working, where context, skills, and automation compound. We’ll build to that.

01
PART ONE
The thinking partner

Claude Chat

The conversational surface at claude.ai and in the desktop app — where you and Claude break problems down together.

Chat 0:31
Claude Chat
01

A conversation that builds on your ideas.

Chat is the everyday surface for writing, learning, research, and analysis. You work turn by turn: Claude expands on your logic, simplifies complexity, and turns a back-and-forth into finished work.

Writing & editing Research Analysis Learning Brainstorming
Claude Chat · What's inside

More than a chat box.

Artifacts

Generate interactive visualizations, tools, and reports in a side panel you can iterate on live.

Projects

Persistent workspaces that keep context, files, and instructions together across many sessions.

Files & images

Upload documents and images for Claude to read, analyze, and reason over directly.

Voice mode

Hands-free, spoken conversation for working on the go or thinking out loud.

Web search

Pull in current information and cite sources without leaving the conversation.

Connectors

Connect OneDrive, SharePoint, and other tools to ground answers in your own context.

↪ More on connectors in the Cowork section.

Claude Chat · Projects

A home for work that comes back.

A Project is a persistent workspace in Claude Chat — it holds your files, your instructions, and the thread of past conversations, so every chat inside it starts already knowing the context. The same instinct as a primed Cowork folder, on the Chat side.

Projects 0:22

Shared files

Upload the documents the work draws on once — every conversation in the Project can read them.

Project instructions

Standing guidance Claude follows across the whole Project — tone, format, and what to avoid.

Continuity

Past chats stay with the Project, so you pick up where you left off instead of re-explaining.

Share with your team

Share the Project with teammates so everyone works from the same files, instructions, and history.

Explore Open the Projects tab in Claude Chat and click into one — poke around its files, instructions, and memory, and see how the whole Project shares with your team.

↪ Why a Project, not Cowork? In a Project, Claude reads your files to think with you — it doesn’t change them. When the files themselves need to change, that’s Cowork (more in the Cowork section).

Reach for a Project whenever you’ll return to the same body of work more than once.

When to reach for Chat

“Help me think it through — and make it with me.”

  • Draft & refineA memo, a strategy doc, a tricky email — iterate line by line.
  • Make sense of materialDrop in a report or dataset and ask questions until it's clear.
  • Prototype an ideaSpin up a quick interactive artifact to see a concept come alive.
  • Learn something newWork through a topic step by step, at your pace.

Best when you want to stay in the loop on every step.

02
PART TWO
The delegate

Claude Cowork

Hand off whole tasks. Claude makes a plan, gets your approval, and does the tedious knowledge work for you.

Claude Cowork
02

Delegate the work, keep the control.

Cowork is the autonomous mode in the desktop app for knowledge work. You point it at a folder — your engagement workspace — then describe an outcome; Claude works with the files in that folder and your connected apps to complete the whole job — checking in on the steps that matter.

Local file access Cloud connectors Step approvals Desktop & mobile pairing
Claude Cowork · Your files

It reads and writes your real files.

Point Cowork at a folder on your computer and it works inside it — reading every file for context, then creating and editing files right there. Chat keeps its work inside the conversation; Cowork works on the real files in your folder, on your machine.

Reads the whole folder

It pulls context from every file in the workspace — no copy-paste, no re-explaining the deal each time.

Creates & edits

It drafts new files, edits existing ones, and organizes them — saved straight into your folder, not pasted back as text.

The big shift from Chat

Chat works inside the conversation — even the artifacts it builds live there, apart from your files. Cowork edits and creates the actual files in your workspace.

Claude Cowork · How it works

Describe it. Approve it. Done.

Cowork 0:38
1

You describe the outcome

Tell Claude what you want in plain language — “sweep these contracts for change-of-control clauses,” “build the weekly status report.”

2

Claude proposes a plan

It shows you the steps and the access it needs before it starts. You decide what it can touch, and whether it checks in along the way.

3

Claude executes

It carries out the work autonomously, keeping you informed of significant actions along the way.

Set the posture per task — “act before asking” to approve each step, or “act without asking” once you trust it. Either way, you decide which folders and connectors Claude can touch.

Claude Cowork · What it handles

The tedious work, handed off.

Montage 0:25

Scheduled tasks

Recurring daily, weekly, or monthly workflows that run on their own — like a morning email digest.

File organization

Sorts, renames, and categorizes files using sensible, consistent conventions.

Data extraction

Pulls details from screenshots, receipts, and invoices into clean, formatted spreadsheets.

Report generation

Produces branded documents, decks, and reports from your source materials.

Email & monitoring

Watches inboxes and metrics, then summarizes what changed into a digest.

Template content

Compiles and analyzes data into repeatable, template-based outputs.

Claude Cowork · Connectors

Connect the tools you already work in.

Connectors let Claude reach into your real systems — SharePoint, OneDrive, Outlook, Teams — using your existing permissions. It's how Cowork works with your actual files and mail, not just what you upload.

Connectors 0:20

SharePoint & OneDrive

Search sites and libraries; read the documents you already have access to.

Outlook

Search mail and calendar — pull threads and find availability.

Teams

Search chat messages and conversations for context.

Try it now Connect Microsoft 365 and ask: “what’s on my calendar tomorrow?”

Read-only and permission-respecting — Claude only sees what your organization already lets you see. It's also what lets you point Cowork at your team's shared folder.

Claude Cowork · Scheduled tasks

Say it once. It runs on its own.

Any job you can describe, Cowork can put on a schedule — recurring or one-time. The tell: if doing it once right now wouldn’t satisfy the request, schedule it.

Scheduled 0:30

Daily brief

“Every weekday at 7am, brief me — what’s on my calendar, the unread mail that matters, and what needs my attention across the deal.”

Weekly status pack

“Each Friday at 3pm, compile the workstream trackers into a draft of the steering-committee update.”

Standing monitor

“Each morning, check the data room for new uploads and log anything that touches the TSA scope.”

One-time reminder

“Tomorrow at 9am, remind me to chase the Tax lead on the German entity setup.” Not everything recurs.

Try it now Just say it in Cowork: “Each weekday at 7am, give me a morning brief — my calendar, the unread mail that matters, and anything that needs my attention.”

Each run is a normal Cowork session — same plan, same approvals, just on a clock.

Claude Cowork · Live artifacts

Outputs that refresh when you open them.

A live artifact is a dashboard, tracker, or brief Claude builds that you open and keep — it pulls the latest each time you open it, instead of going stale the moment you export it.

Live view 0:23

Status dashboard

A deal or workstream view that pulls the latest each time you open it.

Live tracker

An entity or issue list that re-queries the workspace each time you open it.

Refreshing brief

A summary you re-run on demand instead of rewriting from scratch.

Try it now Ask Cowork for an attention board: “Create a live status page of what needs my attention today across my connected tools, and keep it updated.”
When to reach for Cowork

“Just take care of it — and show me before anything risky.”

  • Repetitive, multi-step jobsFormatting, organizing, compiling — work that's clear but time-consuming.
  • Work across your files & appsWhen the task spans a folder, a spreadsheet, and a few connectors.
  • Things that should just happenRecurring reports and digests you'd rather not remember to run.
  • Outcome over processYou care about the result, not babysitting each step.

Best when you'd rather delegate than do.

Side by side

The two at a glance.

Claude Chat Claude Cowork
Core ideaThink & make with youDelegate knowledge work
You provideA conversationAn outcome to hand off
AutonomyTurn by turnPlan → approve → execute
Works withFiles, web, connectors, artifactsLocal files & cloud apps
Lives inWeb & desktop appDesktop app (+ mobile pairing)
Reach for it whenYou want a thinking partnerThe task is clear but tedious
Side by side · going deeper

Both keep a workspace. One difference.

Both a Chat Project and a Cowork folder are persistent workspaces that hold your files and context — so what's actually different? It comes down to what the work is: the conversation, or the files.

Claude Chat · Project
“The conversation is the unit of work.”

Files are loaded in as reference; Claude reasons over them and hands finished work back as artifacts in the thread. State lives in the conversation — read-mostly, and relatively static.

Like a briefed analyst in the meeting room — they've read the data room and hand you drafts, but the room doesn't change.

Claude Cowork · Folder
“The folder is the unit of work.”

Claude reads, writes, and edits files in place on disk. The folder is the durable state, not the chat — read-write, and it scales to far more files, since they're pulled selectively rather than all held in context.

Like an analyst at the deal folder on the shared drive — actually rebuilding the workbook; the folder itself is what's different when they're done.

The tell — at the end of the session, what should have changed: the answer, or the files?

A mental model

How to pick, in one sentence each.

  • Reach for Chatfor a quick, self-contained question — a one-off, an email to react to, something to draft or pressure-test — when there's no folder of context behind it.
  • Reach for Coworkwhen the work lives in a folder you keep coming back to — real files to read and change, context you'd rather not re-explain — and you want Claude working in it alongside you, like a coworker.
Which would you reach for?
“Reply to this email so it sounds right.”
→ Chat
“Pull key terms from the contracts in the data room into a tracker.”
→ Cowork
“Explain the difference between an asset deal and a stock deal.”
→ Chat
“Standardize the file names in our deal folder and build an index.”
→ Cowork
“Summarize this article I just pasted in.”
→ Chat
“Each Friday, compile a status digest from the trackers in our folder.”
→ Cowork

Both share the same models — Opus 4.8, Sonnet 4.6, Haiku 4.5 — and the same permission-first safety posture.

03
PART THREE
The customization layer

Making Claude yours

Beneath both modes is a layer you can shape — teaching Claude your context, your procedures, and the tools your team shares. The same idea runs across Chat and Cowork alike.

Making Claude yours · The building blocks

Two ways to shape how Claude works.

Instructions and skills — the two layers you can shape, both plain files Claude reads.

Concept 0:15

CLAUDE.md

A standing-instructions file Claude reads every session — your conventions, environment, and preferences, kept right next to the work. In the desktop app, project instructions play the same role.

For example# Project Tide — working rules
Never name the buyer in client-facing docs.
Drafts go to working/ · finals to deliverables/.
Just ask ▸“Review this workspace and draft a CLAUDE.md that captures how we work.”

Skills

Packaged know-how — instructions plus optional scripts — Claude loads only when a task calls for it, so a specialized procedure (a steerco pack, your house TSA format) runs the same way every time. The built-in skill-creator builds one from a procedure you describe.

For examplesteerco-update/SKILL.md
“House template · RAG table · max two pages.”
Loads whenever you ask for a steering update.
Just ask ▸“Turn what we just did into a skill, so it runs the same way next time.”

Already have skills built in another tool? Add them with Add skill — see “Where do I find skills?” below.

Both live right in Cowork — and neither is hand-crafted: describe what you want, and Claude writes them for you.

Making Claude yours · Where it all lives

It all lives in one folder.

CLAUDE.md, your context, your skills — these aren’t settings buried in an app. They’re plain files in your engagement folder. Point Cowork at it and every layer above is in play at once.

engagement/
  • ├─CLAUDE.md standing instructions
  • ├─handoff.md where we left off
  • ├─background/ your context
  • │  ├─context.md
  • │  ├─stakeholders.md
  • │  └─workplan.md
  • ├─data-room/ raw inputs
  • ├─working/ drafts
  • └─deliverables/ finished work

One way to lay it out — not a required structure. Keep what’s useful and skip the rest; you don’t need a background, data-room, working, and deliverables folder for every workspace. Let the work decide the shape.

  • CLAUDE.md → standing instructionsRead every session, so your conventions never need re-explaining.
  • background/ → the contextThe deal, the people, the plan — what Claude orients on the moment the folder opens.
  • Write it down once → reuse itAnything worth keeping — a document review, a decision, where things stand — goes in a .md. Claude reads it next session, so you never re-explain or lose context.
  • Skills load on topPackaged how-tos Claude reaches for when a task calls for them.

Get in the habit — when something’s worth remembering, ask Claude to write it to a .md and keep it in the folder.

Making Claude yours · Managing context

One workspace per deal. One chat per task.

Two boundaries keep the work clean — and keep Claude sharp. Scope a Cowork workspace to a deal, and each chat to a task. It’s the same instinct you already use for any folder on your computer: one engagement’s files belong together, and unrelated work doesn’t get buried in with them.

New deal · new workspaceEach engagement gets its own folder — its own files, its own CLAUDE.md and context — and you point Cowork at that one. A second, unrelated deal is a second folder, not more files piled into this one.
↻  New chat when the task changes
  • A different task or deliverableGive it a clean slate, free of earlier clutter.
  • The thread’s gotten longAnswers start to drift, repeat, or forget what you said.
  • You’ve corrected twiceClear it and re-ask with a sharper prompt.
→  Same chat when it builds on the last
  • The next step builds on itBuild the one-pager, then make it a skill.
  • You’re deep in one problemThe accumulated context is the point — keep it.
  • You’re iterating on one draftRefining the same document, turn by turn.

↪ Before you start fresh, capture what matters to a .md in the folder — the folder is the memory that carries across chats; the chat is just the working space.

General principles

“Teach Claude once — reuse it everywhere.”

  • Give Claude standing contextCapture your conventions once instead of re-explaining them each session — Claude carries them forward.
  • Turn repeatable how-tos into SkillsClaude reaches for the right skill automatically, so results stay consistent without re-prompting.
  • Load only what's relevantSkills stay out of the way until a task needs them, keeping each conversation focused.
  • Package once, share widelyBundle your conventions and skills so a whole team can standardize on one setup.
  • You stay in controlCustomization adds capability — never removes the approval gates. The same permission-first posture throughout.
Getting started

One app. Pick the mode
that fits the moment.

You already have the desktop app — Chat and Cowork live in one place. Switch between them as the moment calls for it.

Open Claude · Chat and Cowork are in the sidebar
Closer 0:10
04
PART FOUR
Hands-on with Cowork

Try it yourself

Pick the deal closest to your world, pair up, and run a short hands-on tour of Cowork together — out of a workspace that already knows the deal.

Choose your scenario

Pick the deal closest to your work.

Three workspaces, the same seven-step tour. Pick one with your group — you’ll all work out of that one folder. Click a tile to load that scenario’s guided steps.

Divestiture

Sell-side separation — Meridian is carving out its Flow Control division; the advisor runs the SMO. You build a TSA workstream status one-pager.

Folder ▸project-tide

Integration

Buy-side integration — Northwind is folding in Lattice Analytics; the advisor runs the IMO. You build a Day-1 readiness one-pager.

Diligence · Human Capital

Buy-side HC diligence — Stonehaven is acquiring Northstar Advisors. You build an HC findings one-pager.

Setup · share & sync once

Get the folder into Cowork — together.

One person per team sets up the shared folder; everyone else syncs into that same copy. Follow it in order.

DriverOne person per team — do this once
  1. 1Download a local copy

    Open your scenario’s folder, then click Download in the toolbar to save it to your computer.

    Open project-tide
  2. 2Unzip the download

    It arrives as a .zip — unzip it first so you have a normal folder.

    Windows: right-click → Extract All · Mac: double-click to unzip.
  3. 3Upload it to your OneDrive

    Move that unzipped folder into your own OneDrive — now you control it.

    Keep it in OneDrive — not Downloads, Documents, or Desktop.
  4. 4Share with your teammates

    In OneDrive, right-click the folder → Share and invite each teammate by name.

TeammatesEveryone else — once you get the invite
  1. 5Open the share invite

    Accept the invite, then open the shared folder in OneDrive.

  2. 6Click Sync

    Hit Sync to pull the folder onto your machine.

    Don’t see Sync? Click the ⋯ More menu, then choose Sync.

Now everyone opens that one synced folder in Claude Cowork — same files, same instance. Take turns driving.

Your workspace · what’s in the folder

A folder that already knows the deal.

Whichever scenario you picked, the folder is the same shape — pre-built, so Cowork is current the moment you open it.

your-scenario/
  • ├─CLAUDE.md
  • ├─EXERCISES.html your lab sheet
  • ├─background/ the deal context
  • │  ├─context.md
  • │  ├─stakeholders.md
  • │  └─workplan.md
  • ├─data-room/ raw inputs
  • ├─templates/ the house format
  • ├─working/ scratch space
  • └─deliverables/ empty — yours lands here

CLAUDE.md

Engagement identity and working style — who Claude is on this deal, and the quality floor it holds to.

background/

The primed context: the deal, the stakeholders, and the workplan.

data-room/

Raw inputs — term sheets, excerpts, exports, and meeting transcripts.

templates/

The house format your one-pager follows — so you match a standard, not invent one.

deliverables/

Empty — the client-ready work you produce lands here.

working/

Scratch space for drafts in progress.

The tour · as a team

Seven steps. Take turns driving.

1

Orient

Ask Cowork to brief you on the deal, the players, and what’s open.

2

Build

Draft your one-pager to the house format. Watch it plan, then approve.

3

Skillify

Turn what you just did into a reusable skill. (swap drivers here)

4

Reuse

Run the skill on a second workstream — same format, new inputs.

5

Schedule

Set a daily digest of what’s open and at risk.

6

Live artifact

Turn your one-pager into a live, updating dashboard.

7

Handoff

Capture where it stands so a teammate — or a fresh session — can pick it up cold.

How the seven steps break into chats
Chat 1① Orient
Chat 2 · keep together② Build → ③ Skillify
Chat 3 · new driver④ Reuse
a fresh chat each⑤ Schedule · ⑥ Live artifact · ⑦ Handoff

A new task is a new chat — that keeps Claude’s context clean (don’t run all seven in one). The one pair to keep in a single chat is Build → Skillify — the skill is made from the one-pager you just built.

Your prompts ▸ Open EXERCISES.html in your folder — the exact prompt for each step is there. Start with: “Read this workspace and brief me — the deal, the key players, and what’s open.”
Divestiture · Step 1 of 7 · Orient
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Get the lay of the land.

The ask ▸ Read this workspace and brief me — the deal, the key players, and what’s open right now.
Then ▸ Explain the CLAUDE.md that came with this folder — what each rule does and why. Then add one rule of your own.
Stuck? Add a rule like “Show me a one-line plan before writing into deliverables/.” “Keep client one-pagers to a single page.” “Spell out every acronym on first use.”

What good looks like

A crisp brief — the deal, the players, the open items and risks — pulled straight from the folder, not from you.

Watch for ▸

Notice it never asked you to explain the deal. That's the workspace doing the work.

Why it compounds ▸

Context you capture once pays off every session after. A primed folder means you — and your teammates — never start cold again.

Heads upA folder’s CLAUDE.md is read at the start of each chat. After you add or change a rule, open a new chat for it to take effect — edits won’t reach the conversation that’s already running.
Divestiture · Step 2 of 7 · Build
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Build the one-pager.

The ask ▸ Draft a TSA workstream status one-pager for the High-Level TSA Scoping workstream. Save it to deliverables/.

What good looks like

A one-page draft that matches the house format, every non-obvious claim tagged to a source.

Watch for ▸

It works the ask end to end and pauses for your okay along the way — you're steering the judgment, not proofreading.

Why it compounds ▸

Describe the outcome, not the keystrokes — and notice you never named a format. The workspace already points Claude at the house sample, so the first draft comes back in your style, consistent and sourced. Not this one layout — hand it any example and it adopts that one. Your time goes to judgment, not assembling it.

Stay in this chatStep 3 turns this one-pager into a skill — Claude needs the work it just did still in view. Don’t open a new chat until after you’ve skilled it up.
Divestiture · Step 3 of 7 · Skillify — swap drivers here
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Make it a reusable skill.

The ask ▸ Turn what we just did into a reusable skill, so the next status update comes out in the same format.
Then ▸ Click Save skill, then share it with your teammate — Customize → Skills → your skill → Share — so they can run it too.

What good looks like

A short, reusable skill — a name, what it captures (the format + sourcing rules), when to use it — saved to the workspace.

Watch for ▸

It should capture the format, not this one deal's facts — so it works on any workstream.

Why it compounds ▸

This is the leap past chatting: you're keeping the method itself, so the next one-pager starts from it — and sharing it puts your whole team on one setup. Teach Claude once; reuse it everywhere.

Same chat as Step 2You’re packaging the one-pager you just built, so this belongs in that same conversation. A fresh chat here would lose the context the skill is made from.
Divestiture · Step 4 of 7 · Reuse
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Run it again — a new workstream.

The ask ▸ Type / and pick the skill you just made, then point it at the Technology Separation workstream.

What good looks like

The same one-pager, same shape, for a new workstream — produced in a single step.

Watch for ▸

Same format, new inputs — the second time should feel instant. Don't see your skill in the / list? The teammate who built it has to Save and Share it first.

Why it compounds ▸

Every skill you build makes the next task faster. The returns stack across the whole engagement.

New driver, new chatThis is a fresh task on a teammate’s laptop — open a new chat and invoke the shared skill with /. From here on, each remaining step is fine to start in its own chat.
Divestiture · Step 5 of 7 · Schedule
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Set a standing digest.

The ask ▸ Every weekday morning, give me a short digest of what’s open and what’s at risk across the deal, pulling from background/workplan.md.

What good looks like

A standing task set to run on a cadence — a morning digest of what's open and at risk.

Watch for ▸

You're learning the setup — it won’t fire overnight here. Note how little you had to specify. Then open the task and hit Run now once to watch it work — approve each step as “always allow,” so the scheduled run won’t stall waiting on you.

Why it compounds ▸

Move from doing the recurring work to delegating it. Cowork keeps working when you're not — your time goes to judgment, not the weekly pull-together.

Divestiture · Step 6 of 7 · Live artifact
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Turn it into a living view.

The ask ▸ Turn the TSA status one-pager you just built into a single-page HTML dashboard you can open as a live artifact — and have it pull the latest from the workplan each time you open it.

What good looks like

A dashboard that opens as a living view and pulls current data each time you open it.

Watch for ▸

It's not a static export — each time you open it, it pulls current data from the workspace on its own, no re-prompting. The view reflects today, not the day you built it.

Why it compounds ▸

Outputs that refresh on open beat documents that go stale the moment you save them. Build once, current every time you open it.

Divestiture · Step 7 of 7 · Handoff
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Leave a trail for the next session.

The ask ▸ Take stock of this workspace — the deliverables, the workplan, what’s been decided — and write a short handoff so a teammate, future-me, or a fresh Claude session can pick it up cold: what’s done, what’s open, what’s decided, and what to watch.

What good looks like

A tight handoff — status, open items, decisions made, and what to watch — enough that someone cold can carry on.

Watch for ▸

Prove it: open a fresh session, give it the handoff, and ask it to keep going — it shouldn’t need the deal re-explained.

Why it compounds ▸

Context is something you capture on purpose, not something that vanishes when the chat closes. A good handoff is how work survives people and sessions.

Integration · Step 1 of 7 · Orient
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Get the lay of the land.

The ask ▸ Read this workspace and brief me — the deal, the key players, and what’s open right now.
Then ▸ Explain the CLAUDE.md that came with this folder — what each rule does and why. Then add one rule of your own.
Stuck? Add a rule like “Show me a one-line plan before writing into deliverables/.” “Keep client one-pagers to a single page.” “Spell out every acronym on first use.”

What good looks like

A crisp brief — the deal, the players, the open items and risks — pulled straight from the folder, not from you.

Watch for ▸

Notice it never asked you to explain the deal. That's the workspace doing the work.

Why it compounds ▸

Context you capture once pays off every session after. A primed folder means you — and your teammates — never start cold again.

Heads upA folder’s CLAUDE.md is read at the start of each chat. After you add or change a rule, open a new chat for it to take effect — edits won’t reach the conversation that’s already running.
Integration · Step 2 of 7 · Build
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Build the one-pager.

The ask ▸ Draft a Day-1 readiness status one-pager for the Finance integration workstream. Save it to deliverables/.

What good looks like

A one-page draft that matches the house format, every non-obvious claim tagged to a source.

Watch for ▸

It works the ask end to end and pauses for your okay along the way — you're steering the judgment, not proofreading.

Why it compounds ▸

Describe the outcome, not the keystrokes — and notice you never named a format. The workspace already points Claude at the house sample, so the first draft comes back in your style, consistent and sourced. Not this one layout — hand it any example and it adopts that one. Your time goes to judgment, not assembling it.

Stay in this chatStep 3 turns this one-pager into a skill — Claude needs the work it just did still in view. Don’t open a new chat until after you’ve skilled it up.
Integration · Step 3 of 7 · Skillify — swap drivers here
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Make it a reusable skill.

The ask ▸ Turn what we just did into a reusable skill, so the next readiness update comes out in the same format.
Then ▸ Click Save skill, then share it with your teammate — Customize → Skills → your skill → Share — so they can run it too.

What good looks like

A short, reusable skill — a name, what it captures (the format + sourcing rules), when to use it — saved to the workspace.

Watch for ▸

It should capture the format, not this one deal's facts — so it works on any workstream.

Why it compounds ▸

This is the leap past chatting: you're keeping the method itself, so the next one-pager starts from it — and sharing it puts your whole team on one setup. Teach Claude once; reuse it everywhere.

Same chat as Step 2You’re packaging the one-pager you just built, so this belongs in that same conversation. A fresh chat here would lose the context the skill is made from.
Integration · Step 4 of 7 · Reuse
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Run it again — a new workstream.

The ask ▸ Type / and pick the skill you just made, then point it at the HR integration workstream.

What good looks like

The same one-pager, same shape, for a new workstream — produced in a single step.

Watch for ▸

Same format, new inputs — the second time should feel instant. Don't see your skill in the / list? The teammate who built it has to Save and Share it first.

Why it compounds ▸

Every skill you build makes the next task faster. The returns stack across the whole engagement.

New driver, new chatThis is a fresh task on a teammate’s laptop — open a new chat and invoke the shared skill with /. From here on, each remaining step is fine to start in its own chat.
Integration · Step 5 of 7 · Schedule
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Set a standing digest.

The ask ▸ Every weekday morning, give me a short digest of what’s open and what’s at risk across the deal, pulling from background/workplan.md.

What good looks like

A standing task set to run on a cadence — a morning digest of what's open and at risk.

Watch for ▸

You're learning the setup — it won’t fire overnight here. Note how little you had to specify. Then open the task and hit Run now once to watch it work — approve each step as “always allow,” so the scheduled run won’t stall waiting on you.

Why it compounds ▸

Move from doing the recurring work to delegating it. Cowork keeps working when you're not — your time goes to judgment, not the weekly pull-together.

Integration · Step 6 of 7 · Live artifact
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Turn it into a living view.

The ask ▸ Turn the readiness one-pager you just built into a single-page HTML dashboard you can open as a live artifact — and have it pull the latest from the workplan each time you open it.

What good looks like

A dashboard that opens as a living view and pulls current data each time you open it.

Watch for ▸

It's not a static export — each time you open it, it pulls current data from the workspace on its own, no re-prompting. The view reflects today, not the day you built it.

Why it compounds ▸

Outputs that refresh on open beat documents that go stale the moment you save them. Build once, current every time you open it.

Integration · Step 7 of 7 · Handoff
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Leave a trail for the next session.

The ask ▸ Take stock of this workspace — the deliverables, the workplan, what’s been decided — and write a short handoff so a teammate, future-me, or a fresh Claude session can pick it up cold: what’s done, what’s open, what’s decided, and what to watch.

What good looks like

A tight handoff — status, open items, decisions made, and what to watch — enough that someone cold can carry on.

Watch for ▸

Prove it: open a fresh session, give it the handoff, and ask it to keep going — it shouldn’t need the deal re-explained.

Why it compounds ▸

Context is something you capture on purpose, not something that vanishes when the chat closes. A good handoff is how work survives people and sessions.

Diligence · Human Capital · Step 1 of 7 · Orient
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Get the lay of the land.

The ask ▸ Read this workspace and brief me — the deal, the key players, and what’s open right now.
Then ▸ Explain the CLAUDE.md that came with this folder — what each rule does and why. Then add one rule of your own.
Stuck? Add a rule like “Show me a one-line plan before writing into deliverables/.” “Keep client one-pagers to a single page.” “Spell out every acronym on first use.”

What good looks like

A crisp brief — the deal, the players, the open items and risks — pulled straight from the folder, not from you.

Watch for ▸

Notice it never asked you to explain the deal. That's the workspace doing the work.

Why it compounds ▸

Context you capture once pays off every session after. A primed folder means you — and your teammates — never start cold again.

Heads upA folder’s CLAUDE.md is read at the start of each chat. After you add or change a rule, open a new chat for it to take effect — edits won’t reach the conversation that’s already running.
Diligence · Human Capital · Step 2 of 7 · Build
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Build the one-pager.

The ask ▸ Draft an HC findings one-pager for the key-person & retention workstream. Save it to deliverables/.

What good looks like

A one-page draft that matches the house format, every non-obvious claim tagged to a source.

Watch for ▸

It works the ask end to end and pauses for your okay along the way — you're steering the judgment, not proofreading.

Why it compounds ▸

Describe the outcome, not the keystrokes — and notice you never named a format. The workspace already points Claude at the house sample, so the first draft comes back in your style, consistent and sourced. Not this one layout — hand it any example and it adopts that one. Your time goes to judgment, not assembling it.

Stay in this chatStep 3 turns this one-pager into a skill — Claude needs the work it just did still in view. Don’t open a new chat until after you’ve skilled it up.
Diligence · Human Capital · Step 3 of 7 · Skillify — swap drivers here
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Make it a reusable skill.

The ask ▸ Turn what we just did into a reusable skill, so the next findings page comes out in the same format.
Then ▸ Click Save skill, then share it with your teammate — Customize → Skills → your skill → Share — so they can run it too.

What good looks like

A short, reusable skill — a name, what it captures (the format + sourcing rules), when to use it — saved to the workspace.

Watch for ▸

It should capture the format, not this one deal's facts — so it works on any workstream.

Why it compounds ▸

This is the leap past chatting: you're keeping the method itself, so the next one-pager starts from it — and sharing it puts your whole team on one setup. Teach Claude once; reuse it everywhere.

Same chat as Step 2You’re packaging the one-pager you just built, so this belongs in that same conversation. A fresh chat here would lose the context the skill is made from.
Diligence · Human Capital · Step 4 of 7 · Reuse
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Run it again — a new workstream.

The ask ▸ Type / and pick the skill you just made, then point it at the comp & benefits exposure workstream.

What good looks like

The same one-pager, same shape, for a new workstream — produced in a single step.

Watch for ▸

Same format, new inputs — the second time should feel instant. Don't see your skill in the / list? The teammate who built it has to Save and Share it first.

Why it compounds ▸

Every skill you build makes the next task faster. The returns stack across the whole engagement.

New driver, new chatThis is a fresh task on a teammate’s laptop — open a new chat and invoke the shared skill with /. From here on, each remaining step is fine to start in its own chat.
Diligence · Human Capital · Step 5 of 7 · Schedule
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Set a standing digest.

The ask ▸ Every weekday morning, give me a short digest of what’s open and what’s at risk across the diligence, pulling from background/workplan.md.

What good looks like

A standing task set to run on a cadence — a morning digest of what's open and at risk.

Watch for ▸

You're learning the setup — it won’t fire overnight here. Note how little you had to specify. Then open the task and hit Run now once to watch it work — approve each step as “always allow,” so the scheduled run won’t stall waiting on you.

Why it compounds ▸

Move from doing the recurring work to delegating it. Cowork keeps working when you're not — your time goes to judgment, not the weekly pull-together.

Diligence · Human Capital · Step 6 of 7 · Live artifact
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Turn it into a living view.

The ask ▸ Turn the findings one-pager you just built into a single-page HTML dashboard you can open as a live artifact — and have it pull the latest from the workplan each time you open it.

What good looks like

A dashboard that opens as a living view and pulls current data each time you open it.

Watch for ▸

It's not a static export — each time you open it, it pulls current data from the workspace on its own, no re-prompting. The view reflects today, not the day you built it.

Why it compounds ▸

Outputs that refresh on open beat documents that go stale the moment you save them. Build once, current every time you open it.

Diligence · Human Capital · Step 7 of 7 · Handoff
1 Orient2 Build3 Skillify4 Reuse5 Schedule6 Live artifact7 Handoff

Leave a trail for the next session.

The ask ▸ Take stock of this workspace — the deliverables, the workplan, what’s been decided — and write a short handoff so a teammate, future-me, or a fresh Claude session can pick it up cold: what’s done, what’s open, what’s decided, and what to watch.

What good looks like

A tight handoff — status, open items, decisions made, and what to watch — enough that someone cold can carry on.

Watch for ▸

Prove it: open a fresh session, give it the handoff, and ask it to keep going — it shouldn’t need the deal re-explained.

Why it compounds ▸

Context is something you capture on purpose, not something that vanishes when the chat closes. A good handoff is how work survives people and sessions.

The takeaway

This is a way of working, not a one-off.

You can get a lot done just by chatting — and that’s genuinely useful. But the practitioners who optimize how they work get further: capture the context once, package what you do into skills, and let the routine run itself.

Context compounds

Capture the deal once; every future session starts current instead of cold.

Skills compound

Save the procedure once; each skill makes the next task faster.

Automation compounds

Delegate the recurring work — what’s left is the part that needs you.

Small investments in how you work pay off every week after — and the way you work carries into everything you take on next.

What’s next · Plugins

When the work becomes a routine, package it.

Everything you did today — the primed workspace, the skills, the scheduled digest — can be bundled into a plugin: one install that sets a whole team up the same way. Anthropic ships plugins today, like finance and legal.

In development

Practice plugins are in development. More to come soon!

?
APPENDIX
Quick reference

Where to find things

Three things new users ask first — here’s exactly where they live in the desktop app.

Quick reference · 1 of 3 · Connectors

Add the Microsoft connector.

  1. 1Open Customize from the Cowork sidebar.
  2. 2Choose Connectors.
  3. 3Pick the Microsoft 365 connector.
  4. 4Click Connect, sign in with your work account, and approve.

One Microsoft 365 connector covers SharePoint, OneDrive, Outlook and Teams — read-only, within the permissions you already have. (The + in the message box has a Connectors shortcut too.)

Customize1
Skills
Connectors 2
Personal plugins
Legal
Finance
Connectors · Web
Microsoft 365 3
Covers SharePoint · OneDrive · Outlook · Teams
Connect 4
Quick reference · 2 of 3 · Skills

Where your skills live.

  1. 1You don’t have to open skills — Claude loads the right one automatically when your request matches it.
  2. 2To see or run one, click + in the message box → Skills.
  3. 3Browse or manage them all under Manage skills — or Customize → Skills.
  4. 4Make your own — or add one you’ve already built — with Add skill. Or just ask: “turn what we just did into a skill.”

Skills you create or add show up right here in the + menu — no menu to hunt through.

Message box · +
Add files or photos
Skills 2
Connectors
Plugins
Skills
context
schedule
setup-cowork
skill-creator
Manage skills 3
Add skill 4
Quick reference · 3 of 3 · Your folder

Point Cowork at your folder.

  1. 1Switch to Cowork at the top of the sidebar.
  2. 2In the message box, click the folder selector (bottom-left).
  3. 3Choose your engagement folder — or + Add folder if it isn’t listed.
  4. 4Claude now works in that folder — it reads CLAUDE.md and starts current.

This is the whole idea — point Cowork at a primed folder and every layer above is in play the moment it opens.

Claude · Cowork
ChatCowork 1Code
New task
Scheduled
Live artifacts
How can I help you today?
your-scenario ⌄ 2 Act ⌄
Choose a folder
your-scenario/ 3
workspace
+ Add folder

Use ← → or space to navigate