Workflows
The Daily Practice
Most people use Claude Code like a chatbot and wonder why it doesn't feel like an upgrade. Here's the daily system that actually compounds.
On this page (15 sections)
Capture meetings without lifting a finger
Granola uses AI to transcribe and summarize your meetings automatically. Pair it with Claude Code via MCP to turn meeting notes into action items, tickets, and code.
Try Granola freeNot a developer?
The system on this page applies to PMs, designers, and anyone doing knowledge work, not just people who write code. The specific examples (git log, sub-agents, sessions) are developer-flavored, but the core habits are universal.
If you're a PM or designer, your daily rhythm looks like this:
- Morning (5 min): Open your notes or project docs. Run a quick pulse: what's blocked, what's due, what decisions are pending. Paste the context into Claude if it helps synthesize faster.
- Before each meeting (2 min): Paste the person's name, recent context, and open items into Claude. Get a one-page brief. Full walkthrough here.
- After each meeting (3 min): Paste your notes into Claude. Get decisions extracted, action items listed, and the relevant project doc updated.
- End of week (5 min): Paste this week's highlights into Claude. Ask it to write your status update draft.
The principle is the same as below: context compounds. Every meeting you process, every decision you record, every brief you generate makes the next one faster. The first week feels like extra work. The second week it starts paying back.
Feeling productive and being productive are different things.
Most people use Claude Code like a chatbot. Open it, ask a question, get an answer, close it. Next day, same thing. Clean slate every time.
It feels productive. Code was written. Things happened.
But you're spending 30% of every session re-explaining who you are, what you're working on, and what happened yesterday. That's not productivity. That's a treadmill.
The difference between "I use Claude Code" and "Claude Code is my operating system" comes down to daily habits that take less than 15 minutes total.
The Three Principles
Before the how, the why. Three ideas explain everything that follows.
1. Context compounds. Every handoff, every memory entry, every correction you save makes the next session better. After a month, Claude Code knows your projects, your people, your preferences, and your past mistakes. Without this, you reset to zero every day.
2. Workflows beat prompts. You don't type "help me prepare for my 1:1 with Sarah." You run /meeting-prep Sarah and the system pulls recent interactions, open items, and talking points automatically. Prompts are one-shot. Workflows are repeatable and they get better over time.
3. Decisions are traceable. Six months from now, you can trace why a decision was made, who was in the room, what the alternatives were. That's not magic. It's living documents that update after every meeting and carry forward through handoffs.
The Daily Rhythm
Morning: 5 minutes
Run your morning check-in. If you've set up a /pulse skill (or equivalent), it reads all your active project docs and gives you:
- What needs attention today
- What's blocked
- What deadlines are approaching
- What changed since yesterday
Without this, you're operating on yesterday's mental model. Which, honestly, was already half-wrong by the time you went to sleep.
Before Each Meeting: 2 minutes
Run /meeting-prep {person or topic}.
This pulls recent interactions, open items, relevant project context, and suggested talking points. All synthesized from your connected systems.
No more scrambling through Slack and Jira five minutes before a call. No more walking in going "uh, remind me where we left off?"
After Each Meeting: 3 minutes
Run /post-meeting.
This extracts action items, decisions, and insights. Updates the relevant project's living document. Flags anything that needs follow-up.
The meeting's value gets captured while it's fresh. Not two days later when you're trying to remember what was decided.
During Work Sessions
Four rules I follow every day:
- Plan first for anything non-trivial. Think before coding. This saves tokens and prevents wrong-direction work.
- Delegate to sub-agents for focused tasks. Research, code review, analysis. Each gets its own agent. Your main session stays clean.
- Capture corrections immediately. Every mistake Claude Code makes (and you fix) becomes a permanent rule. Do not skip this step.
- Verify before done. Tests pass. Logs are clean. Behavior matches what was asked. "Looks right" is not done.
End of Day: 2 minutes
Write a handoff. Three bullet points:
- What was done
- What's the priority tomorrow
- Any blockers
This two-minute investment saves ten minutes of context loading the next morning. Every single time.
Friday: 5 minutes
Run /weekly-status. Auto-generates an accomplishment report from Jira, GitHub, Slack, and your meeting notes.
No more "what did I do this week?" scrambling. No more staring at a blank status update trying to remember Monday.
The Before and After
| Before | After |
|---|---|
| Every session starts cold | Context resumes automatically |
| "Let me explain the project again..." | Memory + handoffs = zero re-explanation |
| Status updates take 30 minutes | Generated in seconds |
| Meeting prep is 20 min of tab-switching | Synthesized across all sources |
| Project decisions are lost in Slack | Living docs, traceable, searchable |
| AI is a chatbot you ask questions | AI is an operating system you drive |
The First 30 Days (Honest Timeline)
Week 1: Set up CLAUDE.md, memory, and handoffs. Start writing handoffs at the end of each session. It feels like extra work. It is extra work. Do it anyway.
Week 2: Add your first 2-3 skills. Meeting prep, pulse, or whatever matches your workflow. Start running them daily. Notice the time savings. Start trusting the system a little.
Week 3: Memory starts paying off. Claude Code stops making mistakes you've already corrected. Sessions start faster. You stop re-explaining things. The compound effect kicks in and it's honestly a little wild.
Week 4: You can't imagine working without it. The "extra work" from week 1 now saves you 30+ minutes daily. You start wondering why you didn't set this up sooner.
Who This Is For
- PMs, developers, and managers juggling 3+ projects
- People who use Claude Code daily, not once a week
- Anyone who values systems over one-off hacks
- People willing to invest 15 minutes of setup for hours of ongoing savings
Who This Is NOT For
- People looking for a prompt library. These are systems, not prompts.
- People who don't use Claude Code yet. Get started first, then come back.
- People who want a magic button. This takes a week to build the habit. After that, it's automatic.
Real Talk
The skills and workflows on this page aren't free features built into Claude Code. They're things you build with CLAUDE.md, memory files, slash commands, and skills. It takes about a week to set up a basic version and a month to have something that feels like a real system.
The people who invest that week never go back to the chatbot-style workflow. The gap is just too big. It's like going from "I Google things" to "I have a research workflow." Same tool, completely different outcome.
Start with the CLAUDE.md guide. That's the foundation. Everything else builds on it.
Need somewhere to deploy?
Railway gives you one-click deploys from GitHub with generous free tier. Perfect for shipping what Claude Code builds.
Deploy your first app on RailwayPick the right Claude plan for your workflow
Use our side-by-side comparison to match plan to workload so you never hit limits mid-sprint.
Open plan comparisonNew guides, when they ship
One email, roughly weekly. CLAUDE.md templates, workflows I actually use, and the cut-for-length stuff that does not make the public guides. One-click unsubscribe.
Or follow on Substack