Alienpickle
125 posts
This Craniosomatic Technique Will Fix Your Facial Issues
Here Is How To Do Thumbpulling 👇
English
Alienpickle がリツイート
GOOGLE JUST GAVE AI AGENTS THE FULL POWER OF CHROME DEVTOOLS
your ai coding agent can now open a real chrome browser, click around, inspect network requests, take screenshots, record performance traces, run lighthouse audits, and read console errors all through mcp
debugging a slow page? it records a trace and gives you actionable insights.
weird network request? it lists them all with full details.
console errors with garbled stack traces? source-mapped and readable.
one `npx` command. works with cursor, vs code, windsurf, gemini cli, and more
this is what browser debugging looks like when your ai agent has devtools access
github.com/ChromeDevTools…
English
Alienpickle がリツイート
One folder changes how Claude Code works.
Most users never set it up properly.
Here is the anatomy of .claude/:
✦ CLAUDE.md
This is your project's memory. Write your build commands, architecture decisions, and conventions here and keep it under 200 lines. Claude reads it at the start of every session and follows it throughout.
✦ CLAUDE.local.md
These are your personal overrides. Your preferences stay out of the shared version, so you can change them without touching anyone else's setup.
✦ settings.json
This is where you set permissions. Allow npm run *, block .env files, and spend five minutes here to avoid a lot of surprises later.
✦ commands/
These are your custom slash commands. review.md creates /project:review, and fix-issue.md creates /project:fix-issue. You build the workflow once and run it in every session.
✦ rules/
This is where you put modular instructions. When CLAUDE.md gets crowded, split it into focused files like code-style.md, testing.md, or api-conventions.md. You scope each file to the directories where it matters.
✦ skills/
These are auto-invoked workflows. Claude reads the task, matches it to a SKILL.md description, and runs it without you typing anything. Security reviews and deploys run hands-free.
✦ agents/
These are subagent personas. code-reviewer.md checks PRs to your standards, and security-auditor.md scans for vulnerabilities. Each one runs in an isolated context window and returns only the findings.
The decision rule:
✦ Project instructions → CLAUDE.md
✦ Recurring workflows → commands/
✦ Context-triggered tasks → skills/
✦ Specialised review work → agents/
Most just prompt harder when Claude gets confused.
The fix is almost always better project architecture.
Repost ♻️ to help someone in your network.
P.S. Have you set up your .claude/ folder?
English
@magoniareview @UAPWixy When an internal psychological phenomena wakes you up at 3am, you'll have a moment to reconsider that opinion. Not all things are able to be Forted away.
English
@UAPWixy As 'alien abductions' are an entirely internal psychological phenomena, anything you think will help will actually help if you really believe it.
English
@UAPWixy What if the alien wants to talk about Jesus? I've had some weird conversations.
English
@wise_moments @sukh_saroy Claude Code works with any model. Fire up Ollama, run Gemma 4 and point CC at it.
English
@sukh_saroy Enough, really enough of the Claude and Claude code shit. You will never be smart than their shity limits. The best Claude practice is to cancle any relation with them and live normal as we always were. There are tons of better models out there, just make some effort to find them
English
Every serious Claude Code user is using this repo. if you're not, you're leaving 90% of Claude Code's power on the table.
It's called claude-code-best-practice - 84 sourced tips, implementation examples for every major feature, workflow comparisons across 8 major repos, and the actual tips from Boris Cherny (creator of Claude Code) compiled in one place.
Here's what's actually in it:
→ 84 tips organized by category -- prompting, planning, CLAUDE.md, agents, commands, skills, hooks, workflows, debugging, utilities, daily habits
→ best practice + implemented examples for every core concept: subagents, commands, skills, hooks, MCP servers, plugins, settings, memory, checkpointing, CLI flags
→ workflow comparison table -- Superpowers, BMAD-METHOD, Get Shit Done, OpenSpec, gstack, HumanLayer -- what makes each unique, how many agents/commands/skills each has
→ orchestration workflow -- Command → Agent → Skill pattern with a live demo
→ Boris Cherny tips compiled across 3 tweet threads (13 + 10 + 12 tips) and 5 podcast/video appearances
→ "billion dollar questions" section -- open questions about CLAUDE.md, agents vs commands vs skills, specs -- that nobody has definitively answered yet
here's a few of the tips that actually change how you use it:
→ use subagents with "say use subagents" to throw more compute at a problem -- offload tasks to keep your main context clean
→ spin up a second Claude to review your plan as a staff engineer before executing
→ CLAUDE.md should target under 200 lines -- wrap domain-specific rules in `` tags so Claude doesn't ignore them as files grow
→ compress KV context at max 50%, not at the end -- avoid the "agent dumb zone" by doing manual /compact proactively
→ after a mediocre fix: "knowing everything you know now, scrap this and implement the elegant solution"
was #1 trending on GitHub in March 2026.
19.7K GitHub stars. 1.7K forks. MIT license.
100% open source.
(link in the comments)
English
Alienpickle がリツイート
Learn AI for free directly from top companies.
1 - Anthropic:
anthropic.skilljar.com
2 - Google:
grow.google/ai
3 - Meta:
ai.meta.com/resources/
4 - NVIDIA:
developer.nvidia.com/cuda
5 - Microsoft:
learn.microsoft.com/en-us/training/
6 - OpenAI:
academy.openai.com
7 - IBM:
skillsbuild.org
8 - AWS:
skillbuilder.aws
9 - DeepLearning.AI:
deeplearning.ai
10 - Hugging Face:
huggingface.co/learn
👇Comment "Learning" if you find this helpful.
Repost so others can take help.
Must bookmark for future reference.
English
Alienpickle がリツイート
I honestly thought this map was made up
Hundreds of supertankers, the kind that carry two million barrels each, are currently racing toward the US Gulf Coast from every direction. Atlantic, Indian Ocean, around Africa, the scenic route, the "we were heading to Saudi Arabia but NVM" route.
Iran closed the Strait of Hormuz and everyone panicked. Oil hit $126 a barrel. Gas hit $4 a gallon. Cable news did the thing where they put a red banner on screen and say "CRISIS" in a font that suggests you should be hoarding toilet paper.
And then something happened that nobody in media seems interested in reporting, for obvious reasons. The world just... switched suppliers? Like changing your internet provider except the internet provider is the entire effing global energy economy.
American oil exports are approaching record levels. Gulf Coast refineries are running at 95% capacity. Supertankers that were mid-ocean on their way to the Persian Gulf literally turned around and headed to Texas. That's not a metaphor. Ship tracking data shows them doing U-turns in the Indian Ocean.
Meanwhile China, which was getting 45% of its oil imports through Hormuz and paying basement prices for sanctioned Iranian crude, is now competing with Japan and Europe for the same expensive American barrels. Chinese manufacturers are already raising prices 20% on goods headed to the US.
So to summarize: Iran played its biggest card and the main result is that the United States became the world's emergency gas station and China's cheap energy subsidy evaporated.
This is either the most elaborate coincidence in the history of geopolitics... or someone planned the sequence Venezuela -> Iran -> profits!
I'll let you figure out which one
English
@JOKAQARMY1 You going to give @robertsepehr credit? That's very clearly his voice narrating.
English
This Rabbi just Exposed the Painters 🎨 actual purpose.
English
If I hit the powerball, there will be signs.
Architecture Presentation@arcpresentation
The Ultimate Off-Grid Fortress: Luxury Meets Total Security. [AI]🌲🛡️
English
Alienpickle がリツイート
INSTEAD OF WATCHING NETFLIX TONIGHT.
Spend 1 hour building this.
Obsidian + Claude Code = your own personal JARVIS.
A second brain that captures everything, connects every idea, and thinks alongside you using the most powerful AI model available.
Takes 1 hour to set up.
Works while you sleep.
The people who build this tonight will never work the same way again.
The people who skip it will still be taking scattered notes and losing their best ideas next year wondering why they cannot think clearly.
Your call.
English
Recent update on Eliezer Berland, the convicted rapist and cult leader said to be the Messiah in prophecies by Telepathy Tapes participant Ben Golden: x.com/davidsheen/sta…
David Sheen@davidsheen
Israeli police escort child rapist to Western Wall outside al-Aqsa, saying they fear the child rapist will incite his child-raping followers to riot if he is denied access
English
@InterstellarUAP Tim is just repeating what he's been told. He has zero personal experience, just humans telling him "trust me bro" stories, who have consistently lied for 80 years. Yes, they're here and real, but he knows jack shit thus can't answer any meaningful questions at all.
English
🚨 **BREAKING** Congressman Tim Burchett just dropped a BOMBSHELL : Aliens are REAL and there’s been HUMAN CONTACT! 👽🛸😱
He revealed a classified briefing where a source looked him dead in the eye and said, “Tim, they’re real.”
Burchett confirmed “A form of life that is not earthly”… plus “both” life AND machinery.
He described underwater crafts “Big as a football field moving at over 200 miles an hour.”
It’s pretty wild… but he’s not backing down.
Do you believe him? 👽 Are we alone… or have they been here all along? What would you do if full disclosure dropped tomorrow?
Sound off below....what’s your take?
English
@InterstellarUAP You wouldn't run a UAP account if you didn't know it was real, right? I found out in 1996 when I spent an hour with one of them. He came back in 2022 to talk again. But does it take priority in my life? No, because it doesn't pay the rent. So I focus on my family and job.
English
@JonMajerowski The real key is for software developers to run this against their stuff BEFORE they ship it. Then everything is iron out of the box. Github should have a built-in exploit ninja AI that just disables your repo for downloads if it sees an exploit in your code.
English
