Oscar Lito M Pablo

@johnrushx Golden.

@iamkarendavila He’s good, really, really good. He has a way with words and can sell you anything — the ultimate snake oil salesman.

“HE DID NOT ESCAPE, HE CHOSE TO LEAVE” With the senate leadership asserting it will only recognize warrants from PH courts, Sen Bato was able to leave the senate ‘freely’. SP Cayetano’s position, “PH’s legal system requires any foreign warrant to be validated by local courts before enforcement.” However, the DOJ & other lawmakers cite RA 9851, which allows cooperation or surrender of individuals to international tribunals under certain circumstances. For Former Sen Franklin Drilon & Atty Gilbert Andres, “Bato can already be arrested” Until the Supreme Court issues a ruling on pending petitions including whether PH agencies can legally enforce ICC warrants, this issue will remain legally and politically contentious. Your thoughts?

@Kombaico Is support for Riverpod (Flutter state management) in your roadmap?

Review and improve the design Use Kombai's "Review Design" skill to navigate your app and find design inconsistencies. You can also specify certain aspects for review, such as accessibility or motion, to get focused feedback in those areas.

Ask Kombai to autonomously perform browser tasks on your behalf. Kombai can control the browser and automatically carry out tasks for you. It can navigate your application, interact with elements, and run complete workflows based on your instructions. Instead of manually navigating through your app to verify behavior, you can have the agent operate the browser to identify and fix issues across user flows, design fidelity, and responsiveness. Here’s what it looks like in action:

@MrAhmadAwais Is it Wow(!) or Whoa(!) or both?!

how does taste work in Command Code? kimi has replaced my sonnet usage at 4x the speed and 25x less cost. ↳ npm i -g command-code how can you beat commercial models with open source models, especially with your coding taste? the trick is "taste" (auto-generated skill) a per-project skill file that auto-learns your stack, your patterns, your preferences. point any model at it and the output looks like you wrote it. switch from claude to kimi mid-session. taste comes with you. guiding kimi to do as good as claude. built a full typescript cli with Kimi in this video. spent only $0.74!!

@MrAhmadAwais Already in CommandCode? :)

Wow I just made DeepSeek V4 Pro beat Opus 4.7 6/10 times in our internal evals by auto repairing many of its quirks in tool calling. It’s performing super solid for such a cheap model.

@tomcrawshaw01 BLUEPRINT

I made a free Claude Code Blueprint. Most Claude Code courses are tutorials. The Blueprint is interactive. You install Claude Code, open the folder I send you, type "Start Lesson 1," and Claude teaches you while you use Claude Code itself. 60 minutes from start to finish. You end with a real tool deployed on the internet, all for free. Watching tutorials doesn't teach you Claude Code. Using it does. Whenever I talk to non-technical folks about using Claude Code, the same problem keeps coming up. They install it, watch a few explainers, then quit when nothing they're seeing maps to what they actually want to build. The fix isn't another explainer. It's putting your hands on the tool from minute one. That's what the Blueprint is for. By the end of one short interactive session, you'll know: - How a single slash command can research any company in 60 seconds, instead of 30 minutes by hand - The trick to getting three Claude agents working in parallel inside one session - The CLAUDE .md pattern that makes Claude predictable, not chaotic - How to put your first Claude Code build on the internet, no terminal needed The tool you build is yours. A public URL on the open internet, the kind you can text to a friend. Comment "BLUEPRINT" below and I'll DM it to you (must be following)

@lukepierceops ASSESSMENT

A private equity firm came to us last quarter convinced they needed a custom AI build. We ran our standard audit first. Seven phases across three weeks. By the end, time spent on one of their core processes was on track to drop around 70%. And half of what they thought they needed didn't need to be built at all. That's usually how it goes. The audit is the part nobody wants to do because it's slow and unsexy. It's also the part that decides whether everything that comes after is worth a damn. I packaged the entire process into a self-serve SOP. Same framework we use across our engagements, written so an internal ops lead can run it themselves. What's inside: → The 7-phase audit framework → Stakeholder interview script → Process shadowing playbook → Current state mapping templates → Opportunity scoring matrix → ROI modeling and future state design → Audit document structure for leadership → 10 mistakes that tank internal audits Like + RT + Comment "ASSESSMENT" and I'll DM it to you. Make sure you're following me so I can DM.

@nowa_dev Read that Riverpod is more robust than Provider for medium-to-large projects and actually the recommended and preferred plugin by even the author of both plugins.

@FlipOneUp Hey! Feel free to reach out to us at team@nowa.dev or use our built-in chat. We want to know more about why you need Riverpod integration so we can help you the best.

How does AI in Nowa run so much faster than Claude, Replit, Lovable, and others? It comes down to one architectural difference in how the AI deals with your project inside those platforms. While all other tools deal with your project as a bunch of text files holding code, Nowa does it completely differently. It loads your entire project into memory upfront as a connected AST graph. AST stands for Abstract Syntax Tree. It's the structure your code actually has underneath the text, the same thing compilers build when they translate your code to run your app. This makes Nowa see your project as a Map that includes every component, function, and dependency, and how they all connected together. Like the difference between reading a recipe word by word vs. actually understanding how the dish comes together. Because the project sits in memory, the AI runs way faster. But there's more to it: - AI in Nowa is much better at extracting context. The in-memory graph lets it pull exactly what your prompt needs, nothing missed, nothing wasted. That makes it efficient and much better at handling complex, large tasks. - Nowa analyzes AI-generated code in real time against strict rules and fixes issues before the code even touches your project. So things stay consistent and scalable as the project grows. - The AI only writes parts of the code. Nowa auto-generates the rest, like structure and boilerplate. So prompts are not just more efficient but safer too! since key decisions like structure are made by the platform not the AI. So while other tools rely entirely on the AI to work with your project, Nowa does a lot of heavy lifting behind the scenes to make AI usage faster, better, and most importantly safer for production or big projects. That's why plenty of teams choose Nowa to build their production apps, such as Klubbrabatten that built an app for more than 150K customers in Sweden using Nowa And as always, happy building all! 🛠️ #DevTools #VibeCoding #ai #MobileDevelopment #Flutter #lowcode

@PrajwalTomar_ APP

MY AI AGENT FOUND A $500K/MO APP MARKET NOBODY IS BUILDING FOR. I gave Perplexity Computer ONE prompt: find me an app worth building. It didn't just Google "best app ideas 2026." Here's what it actually did in one session: → researched 5 creators on X doing $10-100K/mo from simple apps. verified their revenue. found one was inflating numbers (did this one for fun lol) → pulled Sensor Tower data on 9 app categories. real downloads. real revenue. not blog estimates. → cross-checked TikTok for which app formats were actually going viral right now. view counts. content hooks. distribution proof. → scored every idea on 4 dimensions: virality, build difficulty, revenue ceiling, and competition gap. → I rejected the top 3. it went deeper. found an entire category doing $500K/mo where every app had the same blind spot. This one session replaced a full week of manual digging. Running this twice a month now for @ignytstudio. Comment "APP" and I'll send you the full workflow. 👇

@Kombaico Unrelated, but interested to know when you'll include Riverpod (Flutter state management plugin) in your list of supported plugins for Flutter -- I don't see it in your online docs.

Visualize architectures with Excalidraw diagrams. Kombai's new "Create Architectural Diagrams - Excalidraw" skill lets you generate architectures as editable Excalidraw diagrams. It's one of the most effective ways to visualize how your new feature connects to existing services before you write your next line of code.

Instead of watching Netflix tonight. Spend a day mastering Claude here: claude101.com → Level 1 - 24 min: The basics. Claude For Dummies: ruben.substack.com/p/claude-for-d… Claude Setup: how-to-claude.ai → Level 2 - 1 hour: Real workflows. Claude Cowork: claude-co.work Claude for teams: how-claude.team Claude Design: claudedesign.free Cowork + Projects: ruben.substack.com/p/claude-cowor… Claude for slides: how-to-gamma.ai Claude Skills: claude-skills.free → Level 3 - 3.5 hours: The pro moves. Avoid sycophancy: ruben.substack.com/p/i-love-to-be… Claude Code: claudecode.free Claude 101: anthropic.skilljar.com/claude-101 Stop hitting Claude limits: ruben.substack.com/p/how-to-stop-… Stop Prompting: ruben.substack.com/p/stop-prompti… → Level 4 - 8 hours: Expert mode. Claude Computer: ruben.substack.com/p/claude-compu… Build with Claude API: anthropic.skilljar.com/claude-with-th… Pro tip: Don't binge it. Do one level per sitting. Actually apply each guide before moving to the next

@AlfieJCarter COWORK

If you don't have my "Full Course: How To Run 99% Of Your GTM Work With Claude Cowork" yet... The one I built to cover every recurring GTM workflow you run manually with scheduled tasks, project memory, and connected tools across email triage, sales reporting, pipeline management, and monthly reporting... Just comment "COWORK" and I'll DM it to you for free (must follow)

@bidah What's happening? Went to the website and got this:

Releasing designdotmd.directory. More than a hundred design.md to choose from for free with desktop and mobile previews, kitchen sink design system samples, filters by category and search. Also accesible through the CLI `npx designdotmd add gym-kettlebell`.

@HeyGen Website

An easter egg skill we hid in hyperframes: /website-to-hyperframes - create DESIGN.md - screenshot the page - download assets - build logo animations + more we hope to support the launch of anyone's businesses RT + comment "Website" for codebase access (must follow)

@AlfieJCarter MASTERCLASS

Claude just replaced the $100K/year GTM Engineer telling your team how to use AI... (most GTM engineers are still using it like a fancy search engine) → No more paying for generic AI training that doesn't apply to your actual stack → No more 10+ hours weekly figuring out which Claude layer to use for which task → No more one-off prompts that produce output you can't reuse or scale → No more sessions that start from scratch because nothing was saved or systematised → No more generic output because Claude has no idea who you are or what you're building Just load the Masterclass → full Claude GTM infrastructure running across Code, Managed Agents, and Cowork. Here's how it works: → GCAO Prompting Framework (forces specific actionable output every time instead of generic advice) → GTM Project Setup (loads your ICP, voice, files, and standards into every chat automatically) → Skill File System (slash commands that run qualification, enrichment, and personalisation on any list) → Co-work Prospect Engine (blank slate to 10 researched prospects with screenshots and cold emails in one session) → CRM and Gmail Integration (reads contact history and drafts 15 personalised follow-ups from actual notes) → Opus 4.7 Decision Framework (adaptive thinking, 3x image resolution, and cost management mapped to GTM tasks) Built on the full Claude stack. Runs without consultants, agencies, or infrastructure teams. Zero re-briefing. Zero wasted sessions. The difference isn't the model. It's the system built around it. While everyone's opening a new Claude chat and typing from scratch, this turns the full stack into a repeatable GTM engine. Want the complete Claude GTM Masterclass? Like + comment "MASTERCLASS" + repost, and I'll DM it to you. (must be following)