Practices/ Real-Life Claude
3 days · 12 units
Pradhya Practice 09 · Real-Life Claude Operator

Workflows that change your week.

Not theory. Twelve workflows other professionals have published — tested, sourced, and reproduced here so you can run them by Sunday. Content production, investing, ops, briefings.

Audience
Anyone with a busy week and an apps stack
Length
3 sessions · 90 min each
Walk-away
Three workflows on your calendar, running
Prereq
Claude Pro + Notion (or Drive) connector
What you’ll be able to do by the end
  • Set up the LinkedIn + Notion + Claude content pipeline
  • Run a monthly content batch in one Sunday afternoon
  • Build the 4-level investing setup, starting at Level 1
  • Wire one “wire your own” workflow that fits your actual week
§ 09.01.01 · Unit 01 · The content stack

LinkedIn + Notion + Claude.

The most-copied content workflow on the internet right now. Notion is the brain, Claude is the writer, LinkedIn is the surface. The whole stack is three connectors and a saved chat.

Notion content calendar read Claude writes in your voice draft You · LinkedIn review · ship log engagement back to Notion → loop
Notion as brain · Claude as writer · LinkedIn as surface

The skill, in one prompt

Read my Notion "Content Calendar" page. Find the next planned post.
Then read my last 3 published posts (in "Published" sub-page) to study the voice.

Draft three variations of the post:
- Hook A: a contrarian claim
- Hook B: a personal story
- Hook C: a number that surprises

Each variation: 250-400 words, one hook + one story + one ask.
Use my voice from the samples. No "leverage" or "unlock".

Format the output as three numbered drafts I can choose between.
Do NOT publish. I will review and post manually.

Source: Síntesi Studio — Claude + Notion content automation.

Connect Notion to Cowork.

You’ll do
Set up the Notion + LinkedIn workflow from U01. Run it once for real.
Steps
  1. In Claude Desktop, add the Notion connector. Authenticate.
  2. Pick the Notion page you use for content ideas.
  3. Run the prompt from this unit on next week’s draft.
  4. Compare output to what you would have written manually.
Verify
You generated one real LinkedIn post in ~3 minutes that you actually want to ship.

Stretch. Schedule the workflow to run every Sunday night. Walk into Monday with a week of drafts queued.

§ 09.01.02 · Unit 02

The monthly batch.

The leverage move: plan a month of content in one Sunday afternoon. Then your weekly writing sessions become pure execution.

One Notion page per month with the calendar:

# May 2026 · Content Calendar

| Date    | Channel  | Topic                                   | Hook angle      | Status |
|---------|----------|-----------------------------------------|-----------------|--------|
| Mon 5/4 | LinkedIn | What a personal AI second brain can do       | Contrarian      | Draft  |
| Wed 5/6 | LinkedIn | The 60-token trick (Claude Skills)      | Number          | Idea   |
| Fri 5/8 | LinkedIn | Three things I shipped this week        | Personal        | Idea   |
| Wed 5/13| Email    | The agent harness, in plain words       | Education       | Idea   |
| ...     | ...      | ...                                     | ...             | ...    |

The Sunday batch: ask Claude to read the calendar, propose topics for “Idea” rows that fit themes you’ve been writing, and queue first drafts of each. By Sunday night you have a month of starting points. Each weekly session is 30 minutes of edit, not 90 minutes of staring.

Source: Alex’s 11 Claude workflows for freelance ops.

Batch your next month of content.

You’ll do
Run the monthly-batch workflow on real planning notes. Get 10+ drafts.
Steps
  1. Open your content calendar (Notion / wherever).
  2. Run the batch workflow on a month’s worth of ideas at once.
  3. Skim the 10 drafts. Mark the 3 worth refining.
  4. Refine the 3. Schedule them.
Verify
You walked away with 3 publication-ready drafts in 30 minutes.

Stretch. Run again next month. Patterns of strong-vs-weak drafts emerge after 2 batches.

§ 09.01.03 · Unit 03

Voice → publication.

You had a thought on a walk. By the time you’re at your desk, a LinkedIn draft is sitting in your inbox.

The pipeline

  1. Capture. 60-second voice memo into the Claude mobile app (or your second-brain bot).
  2. Transcribe. Whisper (local or hosted).
  3. Extract. Claude pulls the one claim worth defending out of the rambling.
  4. File the idea. A new row in Notion’s “Ideas” database, with tags + the original transcript.
  5. Draft. Claude composes a LinkedIn-ready 350-word draft in your voice.
  6. Send to inbox. The draft lands in your Drafts folder. You polish on the train.

End-to-end latency: ~2 minutes from the moment you stop talking. The cost of the thought going from your head to your audience drops by an order of magnitude.

Voice-record a 5-minute rough take. Turn it into a piece.

You’ll do
Walk-and-talk. Then let Claude turn it into a publishable draft.
Steps
  1. Open Voice Memos or Granola. Record 5 minutes on a topic you’ve been thinking about.
  2. Get the transcript.
  3. Paste into Cowork: ‘Turn this into a tight 600-word blog post in my voice. Use these 3 samples for voice: [...].’
  4. Read the draft. Decide if it landed.
Verify
From rough thoughts to a publishable draft in 10 minutes total.

Stretch. Voice-to-content compounds. Most thinking happens on walks. Capture it. Process later.

§ 09.01.04 · Unit 04 · The whole stack

The eleven-workflow freelance ops stack.

From the most-shared Claude workflow post of 2026: how one freelancer runs an entire client-facing business on eleven Claude workflows.

WorkflowWhat it does
Client onboarding Drafts the SOW + kickoff doc from a single discovery call transcript.
Weekly status Reads the project Notion + Linear and writes the client-facing status email. Ready-made: Cowork U05 · Weekly review.
Invoice triage Cross-references QBO with project hours; flags any mismatches.
Scope-change capture Listens to call recordings; when a scope change is mentioned, drafts the change-order email. Related: Cowork R13 · The post-call write-up.
Proposal generator Reads inbound RFPs and produces three pricing options with rationale.
Daily inbox triage Sorts into REPLY / FYI / ACTION / SKIP each morning at 7:30. Ready-made: Cowork R09 · The inbox reset.
Content batcher The Sunday workflow from Unit 02.
Bookkeeping reconcile End-of-month: bank CSV + receipts photos → categorized expense report. Ready-made: Cowork R07 · The receipt sort.
Testimonial collector 30 days after project end, drafts the testimonial-request email.
Birthday / anniversary Two-week-ahead reminder for client renewal anniversaries; drafts the note. Related: Cowork R16 · The renewal risk.
Weekly review Friday afternoon: reads the week and writes the Sunday Substack. Ready-made: Cowork R19 · The newsletter draft.

Each workflow is one Cowork saved chat with explicit tool wiring (Notion, Calendar, Gmail, Linear). The author claims the eleven combined save ~9 hours a week. Adopt the three that match your work; skip the others — and where a row links a Cowork recipe above, that recipe is a ready-made, copy-able version you can run today.

Source: growthwithalex.substack.com.

Pick 2 of the 11 freelance workflows. Run them.

You’ll do
Skim the list. Pick the 2 that match your current pipeline. Try this week.
Steps
  1. Read the 11 workflows from this unit.
  2. Pick 2 that map to your real work. For the fastest start, pick rows with a Cowork link — e.g. inbox triage (R09), bookkeeping (R07), or weekly status (U05) — and copy that ready-made recipe.
  3. Run each on a real input, not a hypothetical.
  4. Note: did it save time? Was the output good enough to use?
Verify
Both workflows ran successfully on real inputs. You saved time on at least one.

Stretch. Add the 2 to your weekly routine. Drop them after 2 weeks if they don’t stick.

§ 09.02.01 · Unit 05 · Investing

The 4-level investing setup.

From The AI Corner: how to layer Claude across research, projects, skills, and Cowork for investing. Four levels, increasing leverage.

Level 1 · Research ad-hoc chat with Claude on a stock Level 2 · Projects a Claude project pinned to your watchlist + screening rules Level 3 · Skills portfolio-analysis SKILL.md you run on demand Level 4 · Cowork scheduled weekly briefing + auto-triage leverage
Build up the stack as your habit deepens

Start at Level 1, not Level 4. Move up only when the level below has become a real habit. The mistake everyone makes: try to wire Cowork to your brokerage on day one and burn out. Spend three weeks at Level 1, three at Level 2, then layer up.

Run the investing memo on one real position.

You’ll do
Apply the 4-level analysis to a stock or fund you actually hold.
Steps
  1. Pick one holding. Note your original thesis (what you thought would happen).
  2. Run the ready-made investing-memo prompt from Cowork Recipe R01 · The investment memo through Cowork. Ask it for a 4-section memo: (1) the thesis in 3 sentences, (2) what changed since you bought, (3) the top 3 risks, (4) buy / hold / trim with a reason.
  3. Compare its analysis to your thesis. What did the memo flag that you missed?
  4. What did your thesis include that the memo didn’t address?
Verify
You have a memo with all 4 sections (thesis · what changed · top-3 risks · buy/hold/trim) on your real position. It contains 1+ insight you hadn’t considered.

Stretch. Run quarterly. The diff over 4 quarters is more useful than any single memo.

§ 09.02.02 · Unit 06

Portfolio analysis with Claude Code.

From Matt Stockton’s portfolio analysis skill: the surprising fact that Claude Code, not the chat app, is the right tool for messy financial data.

brokerage.csv 401k.csv 529.csv bank.csv Claude Code portfolio.md skill briefing.md allocation · drift · trades
Messy CSVs in · structured briefing out · 20 minutes a month

Why Code over chat

  • Brokerage exports are CSVs in mixed formats. Code can parse them programmatically.
  • You have multiple accounts — brokerage, 401k, 529, bank. Code can read all of them in one session.
  • You want reproducibility. The Code session is git-tracked.

The workflow

  1. Drop holdings CSVs (one per account) in ~/Investments/raw/.
  2. Drop a static-assets note with bank balances, employer plans, debts.
  3. Run claude in that directory.
  4. Ask: “Combine these into a portfolio view. Compute allocation vs my target (60/30/10). Identify the 3 biggest drifts. Suggest two rebalancing trades.”
  5. Claude writes a markdown report; you review; you trade.

Total time: 20 minutes a month. Quality higher than most teams’ advisor outputs because the model can question your assumptions exhaustively before concluding.

Audit your portfolio with Cowork.

Why Cowork here, when the unit argued for Code? Because today’s lab is a one-shot read of a single exported list — Cowork does that with no terminal and no setup. Graduate to the Code workflow above once you have several messy CSVs across accounts or you want the analysis git-tracked and repeatable. Same analysis; Cowork is the on-ramp, Code is the destination.

You’ll do
Send Cowork your full portfolio (handle sensitive data carefully). Get the overview.
Steps
  1. Export your portfolio (broker download or manual list).
  2. Strip identifying info. Keep symbols, allocations, cost basis.
  3. Run a portfolio-level prompt: ‘Analyze concentration, sector mix, hidden correlations, top risks.’
  4. Compare to what you thought was going on.
Verify
You see at least one concentration or correlation you didn’t know about.

Stretch. Set a quarterly review on the calendar. Portfolio drift compounds silently.

§ 09.02.03 · Unit 07

The twelve-prompt stock analyst.

From The AI Corner: a 12-prompt pipeline that produces an investment-committee-grade analysis on any single ticker.

The twelve, in order:

  1. The thesis — “Write the 3-sentence thesis for owning this company.”
  2. The history — revenue, margin, FCF trends over 5 years.
  3. The unit economics — what makes one dollar of revenue?
  4. The moat — quoted, not asserted. Cite the 10-K.
  5. The customer — who buys, why, what would make them switch.
  6. The competitive set — the three real comparables with one-line takes.
  7. The macro — the two macro variables that matter most for this company.
  8. The risks — specific, quantified, not generic.
  9. The valuation — three frames (DCF, comps, scenario).
  10. The pre-mortem — assume the stock is down 50% in 3 years. Why?
  11. The trigger — what specific signal would change your mind?
  12. The position — size, time horizon, exit rule.

Each prompt is a saved Cowork skill or a slash command in your investing repo. Run all twelve on one ticker in an evening. The output is a markdown file that beats most sell-side reports. For a ready-made starting point that bundles the thesis / risks / valuation prompts into one pass, copy Cowork R01 · The investment memo; for the research-gathering step (prompts 2–7), Cowork R02 · The topic brief.

Pick 3 of the 12 analyst prompts. Save them.

You’ll do
From the 12 listed, pick the 3 that’d be most useful in your work. File them.
Steps
  1. Read the 12 prompts. Pick 3 you’d use weekly. (If you want a head start, lift the matching sections from Cowork R01 · The investment memo.)
  2. Save each as a starred chat in Cowork.
  3. Use one this week on a real input.
  4. Reflect: did the prompt need editing for your context? Save the edited version.
Verify
You have 3 personalized analyst prompts saved. You used one this week.

Stretch. Build the habit: every prompt you use 3+ times gets saved as a starred chat.

Make it recur — three ways to put any prompt on a schedule The next two units say “schedule it.” Here is exactly how, from no-code to code. Pick one; you only need one.
  • claude.ai scheduled tasks (no terminal). In Claude on the web or desktop, open your saved chat, click the menu → Schedule, and set a cadence (e.g. every weekday 7am). Claude runs the prompt on its own and shows the result waiting for you. Available on paid plans.
  • Claude Code /schedule (terminal). If you live in Claude Code, save the prompt as a slash command and schedule it with cron syntax: /schedule '0 7 * * 1-5' /morning-brief runs /morning-brief every weekday at 7am. Taught in Power Patterns U10 · Scheduled local loops.
  • No-code fallback (works on any plan). Save the prompt as a starred chat (or paste it into a note), then create a recurring calendar event at the time you want — title it “Run [workflow]” and paste the chat’s URL into the event’s notes/location field. The event is the reminder; you click the link and hit enter. Thirty seconds, zero setup, and it never silently fails.
§ 09.02.04 · Unit 08

Weekly automated briefing.

The scheduled version: every Friday at 5pm, Claude reads the week’s news on your watchlist, your Gmail, your scratchpad, and emails you the “here’s what changed and what to do” brief.

# weekly-investing-briefing.md (skill spec)
Every Friday at 17:00 local:

1. Read my watchlist (Notion page "Investments / Watchlist").
2. For each ticker, search news from the last 7 days, top 5 results.
3. Read my Gmail for any "earnings", "analyst", "downgrade" mentions.
4. Cross-reference with my scratchpad notes since last Friday.

Produce a one-screen briefing:

WATCHLIST CHANGES
[ticker]: one-line summary of what changed.

EARNINGS NEXT WEEK
[ticker]: date, consensus EPS, key thing to watch.

DRIFT VS THESIS
Any ticker where the news suggests my thesis needs updating.

ACTION
Zero items, one item, or two items max. Specific.

Email to me. Do not place trades. Do not edit holdings.

Source for this pattern: Growwstacks weekly stock/ETF analysis template.

Set up your weekly automated review.

You’ll do
Pick one weekly briefing (Friday afternoon). Schedule it. Use it Monday.
Steps
  1. Pick the briefing shape: status note, learning log, decisions made, or commitments.
  2. Put the prompt on a Friday-4pm schedule using any of the three methods in the “Make it recur” box above (claude.ai scheduled task, Claude Code /schedule, or the no-code calendar event).
  3. Receive the first run. Edit until it’s genuinely useful.
  4. Lock it in. Same prompt every Friday for 4 weeks.
Verify
Every Friday afternoon you have a status note waiting. You actually read it Monday morning.

Stretch. After 4 weeks, look at the diff. Patterns of what moved vs stalled become visible — that’s the value.

§ 09.03.01 · Unit 09 · Composable

The daily Cowork briefing.

Adapted from jaindl’s daily-briefing essay: a Cowork chat saved as a starred prompt that runs every morning before you sit down with coffee.

Already covered in depth in the NanoClaw practice (Unit 08). The cross-reference: the same skill can run in Cowork (no Pi required) for users who don’t want hardware. Reach for Cowork if you don’t want a Pi; reach for the Pi when uptime matters.

Set up your daily morning briefing.

You’ll do
Schedule a daily 7am briefing. Make it useful enough to keep.
Steps
  1. Pick what goes in: today’s calendar, top 3 priorities, anything stuck.
  2. Schedule it for 7am daily using any method in the “Make it recur” box above — the no-code calendar event is the fastest if you’re not in the terminal.
  3. Receive it for 5 days. Note when you actually used it.
  4. Refine: drop sections you skip, expand sections you re-read.
Verify
You used the briefing 4 out of 5 days. It’s a habit by week 2.

Stretch. Add a 6pm wrap-up. Bookending the day with briefings is the daily-briefing pattern.

§ 09.03.02 · Unit 10 · Composable

The reading-list filter.

You have 80 unread articles in Pocket / Instapaper. Six are worth reading. Which six?

Read my Pocket queue (or paste the list of URLs).

For each item:
- Estimate read time
- Tag with one of: PRO (career), HOME (personal), BROAD (curiosity), SKIP

Then for items NOT tagged SKIP, score 0-10 on:
- Specific to my work this quarter (Q3: agents, AI practices, AI eng)
- Novel vs things I've already read this month
- Timeliness (decays after 30 days)

Output the top 6, ranked, with one-sentence pitches.
The rest: pile into "skip" and forget about them.

Filter your reading list.

You’ll do
Open Pocket / Readwise / browser bookmarks. Filter ruthlessly with Cowork.
Steps
  1. Export your reading queue.
  2. Run through Cowork: ‘Categorize each as MUST-READ, INTERESTING, or SKIP. Justify in one line.’
  3. Read the 3 MUST-READs this week. Archive the SKIPs.
  4. Note which sources keep showing up as SKIP. Unsubscribe from those.
Verify
Reading queue shrinks. Quality of what you do read goes up.

Stretch. Run weekly. Reading-queue triage is a habit, not a project.

§ 09.03.03 · Unit 11 · Composable

The dinner-conversation file.

A small, surprising one. You’re having dinner with someone interesting. Five minutes before they arrive, Claude reminds you what the two of you talked about last time, what they care about, and one fresh thing to bring up.

I'm about to have dinner with [person name].

Read my wiki entry for them (people/[slug].md if it exists, otherwise everything in my notes that mentions them).

Tell me:
- Two things we agreed on last time
- One thing they were worried about that I should ask about
- One specific story from my week that connects to something they care about
- One thing I should NOT bring up (anything they were tired of discussing)

Plain words. 200 words max. No "leverage".

The first time you run it, the answer is generic because the wiki is thin. The fifth time you run it (with the wiki having grown from the conversations between), the answer is uncanny. This is what compounding looks like in personal life.

Prep for one dinner.

You’ll do
Use the dinner-prep workflow before your next meaningful meeting.
Steps
  1. Pick the next dinner / meeting where you want to come prepared.
  2. Run the dinner-prep prompt: their work, recent moves, mutual connections, 5 questions to ask.
  3. Skim the brief in < 5 minutes before walking in.
  4. Note which talking points actually landed.
Verify
Conversation flowed because you came prepared. They mentioned at least one thing you knew about.

Stretch. Prep before every external meeting for a month. Coming unprepared becomes the exception.

§ 09.03.04 · Unit 12

Wire your own.

A dozen workflows shown across this practice. None of them is right for you exactly. The point of the practice is the shape, not the workflows themselves.

The pattern, once and for all

  1. Pick one repeated task from your week. Not your year — your week.
  2. Identify its inputs (apps, files, notes).
  3. Identify the output (one-page memo, draft email, ranked list).
  4. Write the prompt that goes from inputs to output. Hand it to Claude once, by hand.
  5. If the output is good, save the prompt. Connect the inputs to Cowork. Schedule it.
  6. If the output is not good, look at where it broke. Fix the prompt or supply better inputs. Loop.
The closing The workflows in this practice are someone else’s. By the end of next week, you will have built one of your own that is better than any in this list — because you built it for your week, with your inputs, against your standards. Then bring it back to the cohort. Next year’s Unit 13 will be yours.

Wire your own third workflow.

You’ll do
You’ve seen 30+ workflows. Pick one from your real life that wasn’t in the practice. Build it.
Steps
  1. List 5 recurring tasks in your week. Pick the most painful.
  2. Sketch it as a Cowork recipe: inputs, steps, output, reversibility.
  3. Run it on a real input this week.
  4. Iterate until it’s good enough to share with a friend.
Verify
You have a wired workflow that’s yours, not borrowed.

Stretch. Share it. The act of writing it up for someone else sharpens the workflow.