relevant_observer retweetledi
relevant_observer
5.7K posts

relevant_observer retweetledi
relevant_observer retweetledi
relevant_observer retweetledi
relevant_observer retweetledi

Stop telling Claude: "build this"
Stop telling Claude: "write code"
Stop telling Claude: "fix this bug"
You're using a staff-level AI like a junior intern.
Claude performs best when you give:
• role
• constraints
• architecture expectations
• output format
• real-world context
Here are 10 production-grade Claude prompts you can copy-paste:

English
relevant_observer retweetledi

0 AP stories on this attack in NYC
0 PBS stories on this attack in NYC
0 NYT stories on this attack in NYC
0 NPR stories on this attack in NYC
0 WSJ stories on this attack in NYC
0 BBC stories on this attack in NYC
0 CNN stories on this attack in NYC
0 WaPo stories on this attack in NYC
0 Reuters stories on this attack in NYC
0 MSNBC stories on this attack in NYC


English
relevant_observer retweetledi
relevant_observer retweetledi

This is not a real picture. The girl "Emilie" on the right is a digital fabrication. She never existed. You don't even need the circumstantial evidence of the father laughing before the press conference to prove Sandy Hook was a psyop. This single image is all the proof you need.
Foundring 🇺🇸@foundring1
It's time to revisit "Sandy Hook" 🧐🧐🧐
English
relevant_observer retweetledi
relevant_observer retweetledi
relevant_observer retweetledi

That’s a lot of illegal immigrants
End Wokeness@EndWokeness
Each. Dot. Represents. 100. Migrants. This is what an invasion looks like:
English

@jimmydean197 I’m just waiting for interest rates to drop so I can refinance lol
English
relevant_observer retweetledi
relevant_observer retweetledi
relevant_observer retweetledi
relevant_observer retweetledi
relevant_observer retweetledi

How to set up Claude so it never forgets you:
Prompts → Projects → Skills (explained in 3 mins)
Prompts = telling a stranger your job every morning.
Projects = giving a new hire a binder on day one.
Skills = training an employee once. For forever.
Step 1: Start with a Prompt (but don't stay there)
✦ Open Claude. Type your task. Get an answer.
✦ It works. But tomorrow? Claude forgot everything.
✦ You re-explain. Again. Every. Single. Chat.
✦ That's Level 1. Most people never leave it.
Step 2: Move to a Project
✦ Go to Claude .ai → Create a Project.
✦ Upload your voice file. Upload your instructions.
✦ Now every chat inside that Project knows you.
✦ Your context, style, and tone stick.
But you still have to open the right Project.
You still have to say "read my file first."
Step 3: Graduate to Skills
✦ Open Claude Cowork.
✦ Select Opus 4.7 + Extended Thinking.
✦ Prompt: "Use the skill-creator to help me build a skill for [your most repeated task]."
Claude interviews you. Answer extensively.
"I write reports" is useless.
"I write weekly reports that start with the headline metric, 3 sections max, next steps as bullets" is a Skill.
The specificity is the skill.
Step 4: Install and test
✦ Save the Skill folder.
✦ Go to Settings → Capabilities → Skills → Upload.
✦ Open a new chat. Type your task normally.
✦ The Skill fires on its own. No slash command.
✦ Claude just knows.
I just wrote my full Claude Skills breakdown. It covers setup, the skill-creator walkthrough, and the 7 hacks I found buried in Anthropic's docs.
Read it here: claude-skills.free
To download all of my Claude infographics:
Step 1. Go to how-to-ai.guide.
Step 2. Subscribe for free. Don't pay anything.
Step 3. Open my welcome email (most skip this).
Step 4. Hit the automatic reply button inside.
Step 5. Download my infographics from my Notion.
♻️ Repost this to help someone on your team stop re-explaining themselves to Claude every morning.

Ruben Hassid@rubenhassid
English
relevant_observer retweetledi

ANTHROPIC LITERALLY JUST HANDING US THE BLUEPRINT🤯
Their new 33-page guide on Claude Skills is the cheat code.
Make sure to bookmark this before it gets lost in your feed.
Link in 🧵↓
m0h@exploraX_
English
















