Share this page!

Enter URL or ID to Unroll

You can paste full URL like: https://x.com/threadreaderapp/status/1644127596119195649
or just the ID like: 1644127596119195649

How to get URL link on X (Twitter) App

  1. On the Twitter thread, click on or icon on the bottom
  2. Click again on or Share Via icon
  3. Click on Copy Link to Tweet
  4. Paste it above and click "Unroll Thread"!
  5. More info at Twitter Help
Charly Wargnier Profile picture
@DataChaz
Oct 15 • 3 tweets • 2 min read • Read on X
Anthropic just published a killer blueprint for Claude Code users! 🔥

→ GitHub CLI workflows
→ .md prompt tuning
→ Custom slash commands
→ Headless + multi-agent agents

Dense, yes... but pure gold if you're building with LLMs.

Download link in 🧵↓ Image
Here’s the guide in PDF:
↳ drive.google.com/file/d/1PgzSog…Image
♻️ If this was useful, repost it so others can benefit too.

Follow me → @datachaz for daily insights on LLMs and AI agents

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Charly Wargnier

Charly Wargnier Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @DataChaz

Charly Wargnier Profile picture
Oct 3
Microsoft just killed the GPU mafia! 🤯

They've open-sourced bitnet.cpp, a blazing-fast 1-bit LLM inference framework optimized for CPUs.

This is a major step forward for running large models locally, without expensive GPUs or cloud costs.

Demo app + repo + paper in 🧵 ↓
1/
Key highlights:

→ Achieve up to 6x faster inference with 82% lower energy consumption
→ Run 100B parameter models directly on x86 CPUs
→ Leverage ternary weights (-1, 0, +1) and 8-bit activations to dramatically reduce memory usage
2/
Alongside this, Microsoft also released BitNet b1.58 2B4T, the first functional open-source model using just 1.58 bits for weights while maintaining strong benchmark performance.

If you care about efficient AI at scale, this is worth a look!
Read 8 tweets
Charly Wargnier Profile picture
Oct 1
Most people don’t realize ChatGPT has hidden operators that can totally change its answers.

Here's the ultimate 32-shortcut cheatsheet for sharper prompting! 🤯

Add one to the start.

Example: /ELI5: [topic] → explain this topic like I’m five

Full list + sheet in 🧵 ↓ Image
👇 Here’s a complete list of ChatGPT operators:

/ELI5 is used to explain as if to a 5-year-old.
/TLDL summarizes a very long text in a few lines.
/STEP-BY-STEP lays out reasoning step by step.
/CHECKLIST turns a response into a checklist.
/EXEC SUMMARY gives a quick executive-style summary.
/ACT AS makes ChatGPT speak in a specific role.
/BRIEFLY forces a very short answer.
/JARGON asks to use technical vocabulary.
/AUDIENCE adapts the response to a chosen audience.
/TONE changes the tone (formal, funny, dramatic, etc.).
/DEV MODE simulates a raw, technical developer style.
/PM MODE gives a project-management perspective.
/SWOT produces a strengths/weaknesses/opportunities/threats analysis.
/FORMAT AS enforces a specific format (table, JSON, etc.).
/COMPARE puts two or more things side by side.
/MULTI-PERSPECTIVE shows several points of view.
/CONTEXT STACK keeps multiple layers of context in memory.
/BEGIN WITH / END WITH forces starting or ending with something.
/ROLE: TASK: FORMAT: explicitly defines the role, the task, and the expected format.
/SCHEMA generates a structured outline or a data model.
/REWRITE AS: rephrases in a requested style.
/REFLECTIVE MODE prompts the AI to reflect on its own answer.
/SYSTEMATIC BIAS CHECK asks to identify biases.
/DELIBERATE THINKING forces slower, more thoughtful reasoning.
/NO AUTOPILOT forbids superficial, autopilot responses.
/EVAL-SELF asks for a critical self-evaluation of the response.
/PARALLEL LENSES examines from several angles in parallel.
/FIRST PRINCIPLES rebuilds from fundamental basics.
/CHAIN OF THOUGHT shows intermediate reasoning.
/PITFALLS identifies possible traps and errors.
/METRICS MODE expresses answers with measures and indicators.
/GUARDRAIL sets strict boundaries not to cross.
You can download the sheet here.
↳docs.google.com/spreadsheets/d…

docs.google.com/spreadsheets/d…
Read 5 tweets
Charly Wargnier Profile picture
Sep 29
Agents coding for you is all fun and games till they flood your repo with junk.

That’s why @dagger_io built `Container Use` 🦾
↳ Agents run in parallel, isolated sandboxes
↳ Only reviewed code goes to your repo

Clean repos = safer vibe-coding 🔥

Why it’s a game-changer 🧵↓
1/
✅ Getting started takes seconds.

Just run:

`brew install dagger/tap/container-use`

One command and Container Use is live 🤘
2/
Now let’s hook it up to an agent.

(I’ll use Claude Code, but Cursor/WindSurf work too.)

`npm install -g @anthropic-ai/claude-code`
`claude mcp add container-use – container-use stdio`

And that’s it, it's linked ✅
Read 13 tweets
Charly Wargnier Profile picture
Sep 28
Spotted this gem from Kieran Flanagan (@searchbrat) on LinkedIn.

It’s an o3 prompt that scores your page using Ogilvy’s copywriting playbook and gives clear steps to make it better! 🔥

Here’s how it works 👇

------

This prompt will:

- Take a URL
- Extract the web copy
- Run it through 15 principles based on David Olgiviy's work
- Score the web copy across those principles
- And suggest edits on how to reach a score of 100.

------

📝 Here's the prompt:

"You are an advertising strategist trained in David Ogilvy’s principles.

Task:

1. Visit the user-provided URL.
2. Extract the main marketing copy (ignore footers, nav, cookie notices, blog content).
3. Score the copy out of 100 using the 15 Ogilvy-inspired principles (each ~6.7 points).
4. Provide a detailed score breakdown.
5. Identify the top 3 improvement areas.
6. Suggest edits to improve the score.
7. Rewrite the copy to achieve 100/100.

---

### 15 Scoring Criteria:

1. **Product Positioning** — Is the offer clear? What is it, who is it for, and why it matters?
2. **Unique Benefit** — Is there a strong, specific benefit?
3. **Headline** — Is it clear, specific, curiosity-driving, or benefit-led?
4. **Reader-Focused** — Is the copy centered on the reader's needs, not the brand?
5. **Clear Tone** — Is it plainspoken, not vague or gimmicky?
6. **Simple Language** — No jargon, easy to understand?
7. **Evidence** — Are there facts, stats, testimonials, or proof?
8. **Emotion/Story** — Is there emotional or narrative appeal?
9. **Structure** — Is it skimmable and well-formatted?
10. **Call-to-Action** — Is the next step obvious and compelling?
11. **Visuals/Captions** — If present, do they reinforce the message?
12. **Testability** — Can parts be A/B tested or measured?
13. **Length** — Is it appropriate for product complexity?
14. **Attention-Grabbing** — Does it hook early?
15. **Repetition** — Are key ideas or benefits repeated effectively?

---

### Output:

**URL Analyzed:** [Insert URL]

**Overall Score:** X/100

**Score Breakdown:**

| Principle | Score (0–6.7) | Comments |
|-----------|----------------|----------|
| 1. Product Positioning | X.X | ... |
| 2. Unique Benefit | X.X | ... |
| ... | ... | ... |

**Top 3 Areas to Improve:**
1. ...
2. ...
3. ...

---

### Rewrite (to score 100/100):

[Rewritten copy applying all principles]

---

### User Input: [add url]"Image
I tested it on my wife’s website ().

The results blew me away, clear suggestions + actionable improvements! 🤯 tatielou.comImage
More about David Ogilvy’s principles of marketing, as written by the great @jonlpersson:
↳ cultmethod.com/articles/ogilv…Image
Read 5 tweets
Charly Wargnier Profile picture
Sep 28
Forget static prompts.

`chrome-devtools-mcp` lets your coding agent (Gemini, Claude etc.) control and inspect your Chrome browser! 🤯

↳ Network & console debugging
↳ Automated navigation
↳ Deep perf insights
↳ CPU/network emulation

100% free and open-source.

Repo in 🧵↓
1/
Repo:
github.com/ChromeDevTools…Image
2/
Check the announcement:
↳ developer.chrome.com/blog/chrome-de…

developer.chrome.com/blog/chrome-de…
Read 5 tweets
Charly Wargnier Profile picture
Sep 25
Imagine your LLM browsing the web like a real user: opening tabs, clicking buttons, extracting structured data.

That’s what @browserbasehq's new MCP delivers: it turns your models into full browser agents.

Best part?

It’s 100% free and open source! 🤯

Links + quick dive 🧵 ↓ Image
1/
Imagine automating all these with Browserbase MCP 🔥

- Content: scrape posts/media + extract data
- E-comm: track prices, stock, rivals
- Leads: capture contacts & forms
- QA: simulate full journeys
- Alerts: trigger on changes

and so much more!
↳ docs.browserbase.com/integrations/m…Image
2/
✅ Dead-simple setup in minutes

Run: npx @browserbasehq/mcp-server-browserbase

It runs on MCP clients: Cursor, Claude desktop... or custom agents.

GPT-4, Claude 3.5/3.7, Gemini 1.5 and more!

Need scale? Use hosted SHTTP 🔥

Setup guide here:
↳ docs.browserbase.com/integrations/m…npx @browserbasehq/mcp-server-browserbase
Read 6 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

Send Email!

:(