most small businesses pay $5-10K/month for a marketing agency.
me and @boringmarketer replaced the entire stack in one session with Claude Code:
1. built a quiz funnel landing page (2 minutes, zero context, one shot)
2. loaded pre-built marketing skills (drag, drop, done)
3. generated a 5-part email nurture sequence tailored to each prospect's quiz answers
4. repurposed everything into 30+ assets: LinkedIn carousels, X threads, TikTok scripts, 4 SEO articles (2,000-2,800 words each)
the landing page alone was better than what most firms charge $15K to build.
skills are how experts encode their knowledge into AI. build once, use forever.
watch me and James walk through the whole process live in the video below
(the Build With AI podcast is also available anywhere you get your podcasts + YouTube)
Anthropic just gave everyone
double Claude access.
No signup.
No upgrade.
No catch.
Just — here, use more.
Every other AI company
is figuring out how to charge you more.
Anthropic is figuring out
how to give you more.
That difference says everything
about who actually wants you to win.
Imagine you had to choose your life at age 40:
Option A:
Single. No kids.
$10M net worth.
Travel anywhere. Total freedom.
Quiet house. Quiet holidays.
Option B:
Married. 3 kids.
$1M net worth.
Drive a Toyota. Chaos every morning.
Loud house. Full dinner table.
Be honest, which life are you choosing?
For over a week now, Claude models are really broken, you have to ask Claude to re-do the same task 3-4 times to things right..
..and guess what?
Just like that, your token consumption and cost also went up by 3-4x
It's a ridiculous move from Anthropic.
Say Claude builds a website code for you.
Where would be the best place to host it?
Minimal technical expertise and being able to connect it with payment providers etc?
@VaderXBT@Utdtruthful You toxic like most of the United fans always looking for negative even when the team is winning. Complains, complains, complains. Support the team we about to qualify for champions league. Poor coach has left the team is winning games. Is that not positive?
@sihle_mthethwa@Utdtruthful Yep, attitude stinks. I’ve been having this battle with others for months, and now the cracks are appearing. He’s the last of the Rashford bad attitude generation.
My OpenClaw bot runs a full website sales business 24/7:
- Finds local businesses without a website
- Builds them a custom site automatically
- Emails them the preview link
- Runs every day on autopilot
Most local businesses don't have a website. This skill finds them and pitches them automatically
Reply "skill" and I'll send you a free skill file that scrapes leads, builds sites, and sends emails on autopilot. (must be following)
The Premier League has finally decided to cut out the middle man by launching its own direct-to-consumer streaming channel in Singapore — a move that may signal the end of a decades-old broadcasting model.
Dubbed ‘Premflix’ when it was first mooted in 2020, Premier League + is a six-year joint venture with existing league partner StarHub and will start operating in the Southeast Asian island state from the start of next season.
Speaking at the Financial Times’ Business of Football Summit in London on Thursday, Premier League chief executive Richard Masters said: “We’re going direct to consumer in partnership with StarHub, who have a lot of existing customers.
“It will be a new app that you can download on your smart TV or laptop. You’ll be able to watch 380 games a season, with lots of shoulder content and a 24/7 dedicated channel.
“Will it be replicable elsewhere? That’s what we’re going to find out.”
More from @mjshrimper
🔗 nytimes.com/athletic/70728…
🚨🚨🌕| NEW: André Onana wants to fight to re-establish himself as Manchester United’s no.1 goalkeeper when his loan at Trabzonspor finishes in May and believes he will be given a chance to do so. [@JamieJackson___]
🚨 JUST IN: President Trump's White House schedule has been released for tomorrow and he is NONSTOP
9AM: Executive time
11AM: Policy meeting
3PM: Sec. of Transportation meeting
430PM: Policy meeting
Absolute WORKHORSE 🇺🇸
No, it's not an exact copy. The content matches the screenshot word-for-word, including the "Minimat Impact" typo. Differences are in formatting: backticks (`) instead of single quotes ('), bold (**) instead of italics (*) in lists, and spaces in headings. No other changes or typo fixes are evident.
This 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 file will make you 10x engineer 👇
It combines all the best practices shared by Claude Code creator:
Boris Cherny (creator of Claude Code at Anthropic) shared on X internal best practices and workflows he and his team actually use with Claude Code daily. Someone turned those threads into a structured 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 you can drop into any project.
It includes:
• Workflow orchestration
• Subagent strategy
• Self-improvement loop
• Verification before done
• Autonomous bug fixing
• Core principles
This is a compounding system. Every correction you make gets captured as a rule. Over time, Claude's mistake rate drops because it learns from your feedback.
If you build with AI daily, this will save you a lot of time.
full md file if anyone is interested (fixed the typeo in #6)
vvvvvvvvvvvvvvvvvvvvvvvvvvvvv
## Workflow Orchestration
### 1. Plan Node Default
- Enter plan mode for ANY non-trivial task (3+ steps or architectural decisions)
- If something goes sideways, STOP and re-plan immediately - don't keep pushing
- Use plan mode for verification steps, not just building
- Write detailed specs upfront to reduce ambiguity
### 2. Subagent Strategy
- Use subagents liberally to keep main context window clean
- Offload research, exploration, and parallel analysis to subagents
- For complex problems, throw more compute at it via subagents
- One tack per subagent for focused execution
### 3. Self-Improvement Loop
- After ANY correction from the user: update `tasks/lessons.md` with the pattern
- Write rules for yourself that prevent the same mistake
- Ruthlessly iterate on these lessons until mistake rate drops
- Review lessons at session start for relevant project
### 4. Verification Before Done
- Never mark a task complete without proving it works
- Diff behavior between main and your changes when relevant
- Ask yourself: "Would a staff engineer approve this?"
- Run tests, check logs, demonstrate correctness
### 5. Demand Elegance (Balanced)
- For non-trivial changes: pause and ask "is there a more elegant way?"
- If a fix feels hacky: "Knowing everything I know now, implement the elegant solution"
- Skip this for simple, obvious fixes - don't over-engineer
- Challenge your own work before presenting it
### 6. Autonomous Bug Fixing
- When given a bug report: just fix it. Don't ask for hand-holding
- Point at logs, errors, failing tests - then resolve them
- Zero context switching required from the user
- Go fix failing CI tests without being told how
## Task Management
1. **Plan First**: Write plan to `tasks/todo.md` with checkable items
2. **Verify Plan**: Check in before starting implementation
3. **Track Progress**: Mark items complete as you go
4. **Explain Changes**: High-level summary at each step
5. **Document Results**: Add review section to `tasks/todo.md`
6. **Capture Lessons**: Update `tasks/lessons.md` after corrections
## Core Principles
- **Simplicity First**: Make every change as simple as possible. Impact minimal code.
- **No Laziness**: Find root causes. No temporary fixes. Senior developer standards.
- **Minimat Impact**: Changes should only touch what's necessary. Avoid introducing bugs.
🗣️ Malik Tillman (Bayer Leverkusen, 23): “If there is one club I would love to play for, it is Arsenal. They have a great coach, a great system, I think I would fit in. They score a lot of set-piece goals, but in the Champions League they’re different.” ❤️
Write a very thorough spec for a large architecture. Give it to Claude for implementation. It then randomly decides to defer things. Just randomly decides to not build this one thing in the spec. When asked to audit the implementation against the spec, it will say it fully implemented the spec, even though the spec explicitly says to not defer that piece and it will gaslight me it was marked as deferred. Always wondered why these things happen on Claude, there is a certain degree of laziness, like real humans on a payroll. How do you get Claude to be more invested 😂?