puertorossi

804 posts

puertorossi

puertorossi

@puertossaint

Katılım Ağustos 2025
19 Takip Edilen3 Takipçiler
puertorossi retweetledi
Tom Huang
Tom Huang@tuturetom·
Just open-sourced Open Design Skills 🚀 Your Claude Code still ships ugly web pages. With this design system, any landing page, slide deck, letter, resume, or portfolio gets a world-class, magazine-grade look ✉️. github.com/nexu-io/open-d…
English
16
82
966
60.7K
puertorossi retweetledi
Tom Huang
Tom Huang@tuturetom·
Open Design sekarang mendukung Bahasa Indonesia! 🇮🇩 Terima kasih @aqilaziz untuk kontribusi yang luar biasa 🙌 Mari bersama-sama membangun tools yang lebih baik ✨ github.com/nexu-io/open-d…
Tom Huang tweet media
Indonesia
5
21
218
8.2K
puertorossi retweetledi
A C X
A C X@ceogalxe·
ubah AI AGENT mu agar bisa practical hacker! HACK.SKILLS - Hacker Arsenal for Agents Link github : github.com/yaklang/hack-s… 🔸Isinya kumpulan SKILL.md untuk membantu agent memilih metode testing security secara terstruktur 🔸Target pemakaian: bug bounty, penetration testing resmi, CTF, authorized security research Struktur utamanya: - 1 master entry: hack - 6 category entries - 101 deep topic skills - mencakup 14 domain security Topik besar yang dicakup : 🔹Web security: XSS, SQLi, SSRF, 🔹SSTI, XXE, request smuggling 🔹API security: REST, GraphQL, BOLA/BFLA, JWT abuse 🔹Auth/Authz: OAuth, SAML, password reset, session bypass 🔹File attack: upload bypass, LFI/path traversal 🔹Business logic: race condition, payment/coupon abuse 🔹Infra/network: tunneling, pivoting, exposed services 🔹Linux/Windows/macOS privilege escalation 🔹Active Directory attacks 🔹Mobile security Android/iOS 🔹Binary exploitation, reverse engineering, crypto 🔹Smart contract/DeFi attack patterns 🔹AI/LLM security 🔹Forensics/steganography Be Nice Guy!
Indonesia
7
14
90
2.8K
puertorossi retweetledi
Chris
Chris@everestchris6·
this OpenClaw bot finds restaurants with ugly food photos, redrafts them as IG posts, and mails the owner a postcard...on autopilot. here's how social-media agencies can use this system and land clients: - scrapes every restaurant in a city in real time - filters by review count + rating + last post date + photo quality - pulls the strongest food photo from Google Maps reviews - samples the brand palette from the restaurant's own visual identity - AI-redrafts the photo into a 9:16 brand-matched Instagram post - writes a postcard quoting a real reviewer + dish - mails it to the owner by first name with a preview QR every step from discovery to brand-matching to outreach is automated. reply "GUIDE" + RT and I'll send you a free guide so you can build this too
English
897
545
2.3K
231.1K
puertorossi retweetledi
Swati Gupta
Swati Gupta@hrswatigupta·
I Cancelled Spotify. I cancelled Disney+. I cancelled Apple TV+. No more paying every month. Claude transformed my laptop into a free entertainment center. Here are 8 prompts to create this system:
Swati Gupta tweet media
English
70
448
5.1K
1.3M
puertorossi retweetledi
Max Spero
Max Spero@max_spero_·
Spotted some interesting street advertising
Max Spero tweet media
English
127
295
9.8K
489.6K
puertorossi retweetledi
Shizuka NFT
Shizuka NFT@Sizukanft02·
TIM DEV AI CUMA Rp1,6 JUTA PER BULAN HASILKAN Rp550 JUTA Seorang developer membangun tim engineering berbasis AI dengan biaya sangat rendah namun performanya melampaui tim mahal Biaya operasional hanya sekitar 100 dolar per bulan tetapi mampu menghasilkan pendapatan 34 ribu dolar per bulan Setup sederhana berisi 5 Mac Mini ditumpuk vertikal dengan kabel dan monitor konsumsi listrik real time di samping laptop dashboard pemantauan agent Di rak atas terdapat dumbbell pink sebagai detail unik Setiap mesin menjalankan AI agent dengan peran spesifik tanpa saling komunikasi langsung tanpa berbagi konteks tanpa konflik Sistem bekerja 24 jam nonstop bahkan saat pemiliknya tidur Struktur tim AI Mac Mini 1 bertugas sebagai arsitek Menganalisis kebutuhan produk memecah fitur menjadi task dan menyusun spesifikasi teknis tanpa menulis kode Mac Mini 2 bertugas sebagai coder Mengeksekusi spesifikasi menjadi kode dengan akses penuh tools tanpa mengambil keputusan arsitektur Mac Mini 3 bertugas sebagai reviewer Memeriksa setiap kode dengan fokus keamanan kualitas dan coverage testing tanpa ikut menulis kode Mac Mini 4 bertugas sebagai tester Membuat dan menjalankan seluruh pengujian sebelum produk dirilis memastikan tidak ada yang lolos tanpa validasi Mac Mini 5 bertugas sebagai ops Menangani deployment monitoring produksi dan perbaikan sistem CI tanpa menyentuh kode aplikasi Setiap agent bekerja terpisah dengan akses terbatas Tidak ada kebocoran konteks tidak ada tumpang tindih tugas Komunikasi dilakukan melalui task queue bersama bukan antar agent Model bisnis 4 klien retainer membayar 7 ribu sampai 10 ribu dolar per bulan Total pendapatan 34 ribu dolar per bulan Biaya langganan AI 100 dolar Listrik 15 dolar Margin keuntungan mencapai 99,6 persen Performa bulanan 847 commit di 3 proyek klien 12 fitur berhasil dirilis 2 produk diluncurkan 0 insiden produksi Workflow harian Pagi hari review hasil kerja AI Siang agent melakukan iterasi Malam siap rilis Model ini memungkinkan satu orang mengoperasikan agensi dengan output melebihi tim 10 orang Klien hanya melihat hasil fitur rilis lebih cepat dari ekspektasi tanpa mengetahui sistem di baliknya
Indonesia
3
24
100
4.6K
puertorossi retweetledi
Kepala Warga Tai.
Kepala Warga Tai.@handierawan·
Emang bener guys yang jualan” di ecommerce mulai pada bikin website sendiri ya?
Indonesia
41
17
359
55.8K
puertorossi
puertorossi@puertossaint·
@mkbijaksana what a move, yang begini pasti identik sama jualan kelas. emang kyknya lebih kaya dari jualan kelas daripada trading itu sendiri ya?
Indonesia
0
0
0
971
Kurnia Bijaksana
Kurnia Bijaksana@mkbijaksana·
Ngapain lah futars futurs susah sendiri Spot ajalah trading tu Nih caranya: Step 01 Setiap sekitar jam 7 pagi WIB, buka Coinmarketcap, lalu filter biar yang di-display top 200. Lalu sortir berdasarkan top gainers di 24 jam (lihat gambar) Step 02 Screening satu-satu. Maksimal 10. Buka tradingview. Cek apakah si aset tersebut di timeframe 1 hari membuat candle bullish dengan volume besar Definisi candle bullish: - Hijau. Body besar - Wick ke atas minim atau tidak ada - Close-nya lebih tinggi daripada high sebelumnya Definisi volume besar: Lebih besar dari rata-rata 5 bar sebelumnya Step 03 Masuk posisi beli dengan stop loss di bawah low candle tersebut. Masuk dengan resiko yang terukur (ukur sendiri). Lalu tunggu beberapa hari Step 04 Exit jika (pilih): - Sudah mencapai 2R atau cuan sebesar 2 kali resiko - Membentuk candle bearish (kebalikannya candle bullish) - Trailing atau pindahin stop loss setiap dia membentuk low baru Kalau saat screening tidak menemukan sesuai kriteria step 02 sampai 10 kali, lupakan. Screening lagi besok Ilustrasi ada di gambar semua. Cari aja yang kayak gini GM! Sekalian jangan lupa join membership Volubit buat dapet ilmu dan sinyal berkualitas. Murah bang gak kayak yang lain join sini: volubit.id/product/member…
Kurnia Bijaksana tweet mediaKurnia Bijaksana tweet mediaKurnia Bijaksana tweet mediaKurnia Bijaksana tweet media
Indonesia
36
502
2.4K
72.4K
puertorossi retweetledi
Blaze
Blaze@browomo·
This Chinese developer launched 6 agents under 1 orchestrator, and they run his UI design agency at $32,000 a month on their own. He built a system of 6 agents on Claude Sonnet 4.6 that single-handedly runs his agency for UI auditing and redesign for SaaS startups and e-commerce. No contractors, no project manager, and no team. Just him, a MacBook, and 1 API key. Traditional design agencies out of Shenzhen keep teams of 8 people on salaries for the same volume, while he keeps only API tokens. 6 agents work through a single orchestrator on Claude Code Router. Usage is about 4 million tokens a day, the average API bill is just $480 a month. All 6 go through MCP servers and write shared state to the file system, without shared state in memory and without race conditions. And here is the system prompt he gave the orchestrator before launch: "you are the orchestrator of a one-man UI agency. you delegate read-only research tasks to 5 sub-agents and own all writes. sub-agents: // Hunter (finds SaaS and e-commerce sites with outdated UI) // Auditor (runs each site through Lighthouse, accessibility, and design system checks) // Pitcher (writes cold outreach and redesign proposals with before/after screenshots) // Splitter (breaks accepted projects into typed milestones) // Designer (generates Figma mockups and Tailwind components) // Checker (runs evals on every artifact before it leaves the harness). you never let 2 sub-agents touch 1 file. you stop and request human approval only when an invoice exceeds $5,000 or when the design system eval score drops below 0.88." Meaning the system knows exactly what it is and within what boundaries it operates. It knows it is supposed to find clients on its own. It knows it is supposed to write proposals with screenshots and mockups without intervention. It knows the human only plugs in when the amounts go above $5,000 or when the design system eval does not converge. → The system runs 24 hours a day → Hunter finds about 200 sites with outdated UI a day → Auditor runs each one through Lighthouse and WCAG → Pitcher prepares about 28 personalized proposals with before/after screenshots → Splitter breaks 3 accepted projects per week into milestones → Designer generates mockups and components, Checker runs evals on every artifact And only when the invoice breaks $5,000 or the eval drops below 0.88 does the orchestrator wake the human. Here is what the system outputs in his log during 1 of the sessions: "hunter report, tuesday: 213 sites found, 31 with last redesign before 2020, 14 with Lighthouse score below 65, 6 with active redesign RFP. passing top 6 to auditor." "pitcher: 27 cold outreach sent with before/after screenshots, 5 replies, 3 discovery calls scheduled. passing to splitter." "designer: milestone 2 of Lotus Tea Co redesign complete. Figma frames exported to /Users/dev/agency/clients/lotus/v2. checker running design system evals." "eval flag: proposal for $6,800 exceeds the approved limit of $5,000. sending for manual review." He has no remote server. No separate backend. Just a local file sandbox in /Users/dev/agency, an MCP router, and an API key to Claude. Out of everything I have seen this year, this is the cleanest one-person UI design agency: $480 in, about $32,000 out, and between them 6 prompts and 1 file system.
Khairallah AL-Awady@eng_khairallah1

x.com/i/article/2050…

English
26
48
378
53.4K
puertorossi retweetledi
rob.
rob.@robiartec·
Alguien creó un Simulador de Diseño de Sistemas basado en web. Copias y pegas (API gateways, bases de datos, cachés) y simula tráfico en tiempo real. Puedes ver la latencia, los puntos de saturacion y los fallos mientras ocurren en directo...
Español
17
162
1.4K
74.7K
puertorossi retweetledi
Oskar
Oskar@o_kwasniewski·
this is what AUTOMATED UI testing looks like
English
70
88
2K
200.6K
tara_
tara_@TechByTaraa·
Bro disappeared like never existed.
tara_ tweet media
English
194
24
1.2K
167.9K
puertorossi retweetledi
无颜
无颜@WY_mask·
这个网站牛逼啊,只需要输入网址就可以把这个网站的“所有底层信息”全扒出来 web-check.xyz 📡 DNS、IP、服务器位置 🔐 SSL证书、安全配置 🧱 技术栈、框架、用的什么服务 🕵️ Cookie、追踪器、甚至潜在风险 做开发的可以用来排查问题,做安全的可以做初步渗透分析,我们也可以用来判断一个网站靠不靠谱,但也要注意有些第三方检测对它的信任评分不高,涉及敏感数据时要谨慎使用
无颜 tweet media
无颜@WY_mask

Agent必装的skill之一,快速让你的AI成为工程师 github.com/mattpocock/ski… 这个存储库直接把程序员的工作流程拆成一套“可复用技能包”,它不是教你写代码,而是教AI怎么 📌 写PRD、拆任务、做架构设计 📌 用TDD开发、排查Bug、优化代码 📌 自动管理Git、生成文档、整理知识

中文
12
47
225
33.3K
puertorossi retweetledi
Leon Lin
Leon Lin@LexnLin·
the prompt for this was: "github.com/Leonxlnx/taste… Based on the skill above, generate images for a website for an AI agency. The design should include eight sections, with one image per section, for a total of eight distinct images. The website is for a creative AI company focused on research in creativity and design. Because of that, I want the visuals to feel highly original, playful, and art-directed, with text integrated thoughtfully into the design. Make it feel ultra-creative and intentional, like an Awwwards SOTD-level website in both concept and execution. Please go beyond standard layouts. Do not rely only on simple text-left, image-right compositions. Explore more experimental and varied layouts. Feel free to go completely wild, but keep it purposeful, not random. I want different section structures, including horizontal images, fullscreen sections, full background imagery, and more minimal sections with beautiful colors and a strong sense of motion or animation. Please use full background images or strong full-background color compositions, not just plain white sections. Keep it in light mode. Overall, try to stay somewhat consistent across the site while still making each section feel distinct. I want it to look crazy creative, thoughtful, and visually impressive, with strong UX and a clear sense of purpose. Generate 8 different images total. Do not combine them into one image. Each image should represent one section of the website."
Leon Lin@LexnLin

image-to-code only thing you need these days for design as a vibecoder: images 2.0 and codex

English
5
14
211
14.3K
puertorossi retweetledi
Peter Steinberger 🦞
This is the most useful tooling I built for OpenClaw to date. It's open source, runs on codex and you can fork and use it for any repo. For all the hard working oss folks that drown in issues and PRs, this is for you.
OpenClaw🦞@openclaw

ClawSweeper 0.2.0 🦞 The OpenClaw maintenance bot now handles the loop: issue → @clawsweeper fix/build → guarded PR → review → repair → re-review → automerge Still conservative. Much less manual. clawsweeper.bot

English
45
114
2K
285.2K
puertorossi retweetledi
zen.
zen.@zentalksai·
Nadie te está contando que ya puedes crear diseños de redes sociales de nivel profesional con IA. Claude + Nano Banana. Sin experiencia. Sin dinero. Tutorial completo de 18 minutos ⬇️
Español
13
80
555
22.3K
puertorossi retweetledi
そう|Claude Codeで始めるAI自動化
これはやばい。 AIエージェントが144体収録された「丸ごと1社のAIカンパニー」がオープンソース公開されました。名前は The Agency。GitHubのスター数9万超。 ・エンジニア/デザイナー/マーケ/営業/財務など12部門の専門エージェント ・Claude Code、Cursor、GitHub Copilot、Gemini CLI、Windsurfなど主要コーディングAIにスクリプト2本で導入 ・MITライセンスで完全無料 など、コーディングAIを「専門家チーム」に変えられます👇
そう|Claude Codeで始めるAI自動化 tweet media
日本語
9
103
626
36.2K