🌅 Morning routines — let's compare notes. Mine looks like this: ⏰ [Wake time] - 7.30am ☕ [First habit] - COFFEE 📖 [Second habit] - SKOOL 🚀 [How you start work] - Slowly ⏰ [Bedtime] - when i fall asleep What does yours look like? Drop it below — I'm always looking to optimize. 👇

Turns out… it's not the model. It is how I am using it. Turns out Claude doesn’t count messages. It counts tokens. Once that clicked, everything changed. Here are 10 things that make a massive difference: 1. Edit your prompt instead of sending follow-ups If the response is off, don’t send: “No, I meant…” or “That’s not right…” Every extra message gets added to history. Claude re-reads ALL of it every time. Token cost grows fast: At ~500 tokens per exchange 5 messages = ~7.5K tokens 10 messages = ~27.5K tokens 20 messages = ~105K tokens 30 messages = ~232K tokens Instead: edit your original prompt and regenerate. You replace the history instead of stacking it. 2. Start a new chat every 15 to 20 messages Long chats are expensive. Most tokens get burned re-reading old context, not generating new output. One dev tracked usage: 98.5% tokens = re-reading history 1.5% = actual output Fix: Ask Claude to summarise → copy → start fresh chat → paste summary. 3. Batch your questions Stop sending multiple messages. Bad: “Summarise this” “Now list points” “Now give a headline” Better: “Summarise this, list key points, and suggest a headline.” One prompt = one context load. 4. Use Projects for repeat files Uploading the same file repeatedly = repeated token cost. Projects cache your files. Upload once → reuse without re-tokenising. If you use PDFs, briefs, or docs often, this alone saves a lot. 5. Set Memory and Preferences If you keep typing: “Act as…” “I’m a…” “I write like…” You’re wasting tokens every time. Save it once in settings. Claude remembers it. 6. Turn off unused features Search, connectors, advanced thinking all add token cost. If you didn’t intentionally turn it on, turn it off. 7. Use the right model Not everything needs power. Haiku → quick, cheap tasks Sonnet → standard work Opus → deep thinking Most people overuse powerful models and burn budget fast. 8. Spread usage across the day Claude uses a rolling 5-hour window. If you burn everything in one session, you waste the rest of your day.

Happy Easter 🐰 Wishing you a day filled with joy, chocolate, and a little bit of magic. May your Easter be as sweet as the treats and as bright as the season. MJ certainly had fun this easter, hope you all did to

What They Are, How to Install & Use Them Most people use Claude out of the box. But there's a layer most users never unlock: Skills. Here's everything you need to know. What is a Skill? A Skill is a file that teaches Claude how to do a specific task really well — before it even starts helping you. Think of it like giving Claude a specialist's playbook. Instead of a generic answer, you get a structured, high-quality result every time. Examples: 📄 Create polished Word docs 🎨 Build beautiful web designs 📊 Extract data from PDFs 🗂️ Automate file organization Step 1 — Get a Skill You have two sources: From Anthropic's public library → Browse available Skills at claude.ai → Download the .skill file you want From this community → I share Skills in the classroom Step 2 — Install It Pick whichever method works for you: Option A — Upload via Claude.ai settings Go to claude.ai → Settings Find the Skills section Upload your .skill file Done ✅ Option B — Drop it into a folder Locate your Claude skills folder on your computer Drag and drop the .skill file in Claude picks it up automatically next session ✅ Option C — Paste it directly in chat Open the .skill file in any text editor Copy the contents Paste it at the start of your Claude conversation Claude will use it for that session ✅ (Option C is great for testing a Skill before committing to installing it) Step 3 — Use It Once installed, Claude activates the Skill automatically when your request matches. You can also trigger it manually: "Use the PDF skill to extract the table from this file." That's it. Claude reads the Skill, follows the workflow, and delivers a much better result than it would without it. Why bother? Without a Skill → Claude gives you a decent general answer With a Skill → Claude follows a proven, expert workflow The output quality difference is real. 💬 Questions about any of these steps? Drop them below and I'll help you get set up.

@Krista Brea birthday wish is to welcome a few more people into the community so KDP Publishing can reach 800 members. She’s only 5 away now, and it’s very likely she’ll hit the goal.