Zee

@MichLieben Ads

I'm giving away the Claude Code skills we use to manage $300k/mo in ad spend at ColdIQ. 4X ROAS on $1M+ spent. Ivan, our head of growth, built them off 300+ hours running ad campaigns for our clients. They run Google, Meta, and LinkedIn ads from the terminal in plain English: → bulk edits across platforms → custom audiences from CRM lists → creative fatigue detection before CTR dips → bid adjustments at scale → performance audits across periods Reply "ads" and I'll send the full repo. Must be following.

@yanndine Routines

I put the entire Claude Routines Playbook into ONE Notion doc. 8 sections. No fluff. - What routines actually are and how they replace n8n: same event fires, Claude reads natural language instructions, output lands in Slack or your CRM without a single drag-and-drop node built - Full routine setup in under 5 minutes: name, description as a numbered SOP, model selection, environment config, trigger, and connectors all from one screen - The three trigger types and when to use each: schedule for fixed cadence workflows, API call for passing data payloads from Claude Code, webhook for firing automatically when Fireflies finishes a transcript or a prospect signs a proposal - How to connect Gmail, Slack, and every other tool via OAuth once and reference them by name in every routine prompt forever - How to write a routine prompt that works every time without you watching: numbered SOP structure, explicit finish line, named connectors, and the three things that make outputs unpredictable - Three production routines worth stealing: daily inbox drafter running at 5:10am, transcript to proposal firing from a Fireflies webhook, and a field monitor sending signal digests to Slack in under 2 minutes of setup - How to convert any existing n8n workflow into a routine by pasting the JSON into Claude Code and letting it translate the node chain into a natural language prompt automatically - The decision rule for routines vs n8n: when to build new, when to convert, and when high-frequency mechanical workflows should stay exactly where they are This is the setup I would have KILLED for before spending hours building n8n node chains for workflows that should have taken 5 minutes to describe in plain language and wire to a connector. Like + comment "ROUTINES" and I'll send it over (must be connected for priority access)

@AdamrahmanGTM GTM

AI does 90% of our GTM execution. Not prompts you copy-paste into ChatGPT. 12 executable workflows that Claude Code runs autonomously - from first research query to live campaign. Massive unlock for speed to winning GTM across a diverse client base. > 9-dimension market research > TAM database building > ICP scoring > full GTM strategy generation > prospect worldview mining > hidden signal discovery > message-market fit testing > waterfall contact enrichment > local business enrichment (Maps to verified emails) > campaign launch from CSV > 5 Variables performance diagnosis > structured campaign debriefs Clone the repo. Add your API keys. Run it. Reply "GTM" and I'll send you the link.

@AlfieJCarter Code

I put the entire Claude Code GTM Engineering Playbook into ONE Notion doc. 8 sections. No fluff. - How to get set up correctly from day one: Pro plan, terminal install across Mac, Linux, and Windows, GUI install via Antigravity or VS Code, and bypass permissions mode - What to put in your project brain file, what to leave out, and how to get Claude to update it automatically when it keeps making the same mistake - How to run plan mode step by step and when to skip it for simple tasks - How to build a skill file from scratch, fix one that keeps failing, and install 5 GTM skills worth building first: lead scraping, email labeling, proposal generation, outbound sequence writing, and client onboarding - MCP install process, token cost checks after every install, the best MCPs for GTM work, and how to cut token usage by 50 to 100x by converting MCPs into skills - Sub-agents and agent teams: the 3 cases where they earn their cost, reliability math for parallel runs, and how to enable parallel variant exploration - What is eating your context before you type anything, how to use /compact and /clear correctly, and model selection for parent vs sub-agents - Modal deployment: any skill as a live URL in under 2 minutes, form interface setup, and connection to n8n, Make, or Zapier This is the setup I would have KILLED for before spending months piecing together how to actually get productive in Claude Code from documentation, YouTube tutorials, and scattered GitHub threads. Like + comment "CODE" and I'll send it over (must be connected for priority access)

@oliverwhudson 2026

Our 2026 playbook has been our most downloaded resource this year. We've updated it with new chapters added - including a full breakdown of Meta's algorithm update published 31 March 2026, the rise of personas, partnership ads, AI UGC and how the next wave of ugc is developing. The same frameworks behind £600M+ in revenue across the DTC brands we work with. Four pillars: Meta, TikTok, AI, and Creative. Platform mechanics. Account structures. AI workflows. The creative formats actually driving incremental growth right now. Retweet this post and comment "2026" and I'll send it over.

@mikefutia OS

I just built a Brand Operating System inside Claude Cowork 🤯 A connected system of files that every skill automatically reads from, so your hook writer, brief generator, and script writer all speak in your exact brand voice. All inside Claude Cowork. Perfect for DTC brands and agencies tired of generic AI output that sounds like every other brand in their category. If you're opening a new Claude chat and re-explaining your brand, re-pasting your voice guidelines, and re-describing your customers every single time, a Brand OS fixes the entire loop: → Build 3 foundation files once per brand → Every skill you create reads from the Brand OS automatically → Hook writer pulls your voice + customer pain points → Brief generator pulls your positioning + angles → Script writer pulls the brief + brand DNA → Every output is calibrated to your brand on the first pass No re-briefing Claude on every chat. No editing for an hour to fix generic AI phrasing. No creative that sounds like it could belong to any brand. What you get in the playbook: → The exact Brand OS file structure I use → Templates for all 3 files you can fill in for any brand → The architecture that makes every Claude skill 10x sharper → The exact setup for agencies running a Brand OS per client For agencies: this is how you build a perfect, reusable knowledge base for every client on your roster. Set up the Brand OS once per client, and every campaign after that is already calibrated. I put together a full playbook with the file templates, the architecture, and the exact setup process so you can build your own Brand OS for your brand or your clients. Want it for free? > Like this post > Comment "OS" And I'll send it over (must be following so I can DM)

@lukepierceops NICHE

I mapped every AI automation opportunity across 25 industries. 10-15 pain points each. With the exact positioning, pricing range, and who to sell to. This took me 4 years and 80+ client engagements to figure out. A lot of AI agencies pick a niche and pray. They don't know the actual pain points. They don't know who the buyer is. They don't know what these companies are already paying for broken solutions. They don't know what the realistic project size is. So they end up competing on price for generic "AI automation" gigs. I've worked with marketing agencies, recruiting firms, e-commerce brands, law firms, real estate companies, healthcare practices, financial services, SaaS companies, manufacturing, construction, logistics, and more. Every single one has 10-15 processes that are bleeding money because they're still done manually. Here's what the guide covers for each industry: → The top 10-15 automation pain points (ranked by ROI) → Who the actual buyer is (CEO, COO, ops manager, etc.) → What they're currently paying for manual labor or broken SaaS → Realistic project pricing ($5K-$60K+ depending on scope) → The discovery questions that unlock the deal → How to position yourself as the expert even if you've never worked in that industry → Red flags to avoid (industries and company sizes that aren't worth it) 25 industries and 300+ specific automation opportunities. This is the cheat code for picking your niche and knowing exactly what to sell before you ever get on a call. Like + RT + reply "NICHE" and I'll send you the full guide (Must be following so I can DM)

Before limited-releasing Claude Mythos Preview, we investigated its internal mechanisms with interpretability techniques. We found it exhibited notably sophisticated (and often unspoken) strategic thinking and situational awareness, at times in service of unwanted actions. (1/14)

@GlobeEyeNews @grok verify this

BREAKING: All young men between the ages of 17 and 45 are now no longer allowed to leave Germany for more than three months without permission.

@starks_arq @EXM7777 DRUSKI

We made this viral Kitkat x Druski video in just 20 minutes... I just made a guide covering the complete workflow: - Agent pipeline - Storyboard flow - Video models And I'm giving it away for free Comment “DRUSKI” and RT to receive the full guide

@0xSero What would you suggest for M5 max, 128gb?

Best models to run on your hardware: —— 64 GB —— - Qwen3-coder-next-80B-4bit (coding, Claude code, general agent) - Qwen3.5-122B-reap: (browser use, multimodal, tool calling, general agent) —— 96 GB —— - GLM-4.6V (multimodal and tool calls) - Hermes-70B (Jailbroken) - Nemotron-120B-Super: (openclaw) - Mistral-4-Small (general agent) —— 192 GB —— All these are excellent top tier LLMs and approach sonnet in capabilities - Step-3.5-Flash - Qwen3.5-397B-REAP - MiniMax-M2.5 (soon M2.7) - GLM-4.7-Reap

@FirstSquawk @grok Is this true?

Iranian Revolutionary Guards: Location of US military in Dubai Marina successfully targeted - Statement.

@C1phervoyager @tryfomo Will you do another challenge?

2nd 1k-100k on @tryfomo completed, this one took 33 days Did it to reset bc I was trading bad, and pretty happy with the performance Didn’t shill a single coin here or in my tg in a while because CT makes it -EV when ppl dunk on you for taking profit/rotating, so still figuring how to do that Anyways, let’s keep cooking Fomo is the best place to trade by far fomo.family/r/cipher

opus 4.6 + codex 5.3 launching within 20min of each other is both insanely cool & crazy overwhelming. i honestly have no idea what to make of the pace of ai anymore. zero clue. we all knew it was coming, but now that we’re clearly in the start of the takeoff it feels different. my day is just using 9 different ai tabs at once and commanding them to do everything for me. agents are here, they work, and every week they get better. the exponential is ramping up. i do this all day and i can hardly keep up. everyone will have an ai that can do or build anything they need on-demand. you’ll have fleets of these things working for you 24/7 that can do knowledge work better and faster than any human. and that’s gonna be hear within what? a year? what are you supposed to make of that? feels like we’ll collectively have to raise our ambitions and that new unimaginably cool things will be possible. i’m looking forward to those things. best advice is probably just be happy and don’t die i guess? or put more beautifully: don’t forget to live. but the acceleration is speeding up in a *very* tangible way. not enough people read “machines of loving grace” and took it seriously. it’s all happening. it gets even weirder when you consider that the average person has absolutely no clue that any of this is happening. that part weirds me out. it all sounds so schizo even though it’s obviously not. sometimes i wish i was one of those blissfully ignorant normies haha. but it’s all just too fun. wouldn’t change a thing tbh. rare rant from me. but today had a particularly strong dose of “feel the agi” to it. crazy this is all real, as ilya would say. turns out that living through the singularity is pretty wild.

Claude code is actually as good as all the insane Silicon Valley people on your timeline are saying It appears 80% of jobs are totally debunked and we’re just waiting for people to notice

Been using Claude Code, and had this thought come to my mind over and over.

@Vithrax Yeah it gives equal dose of dreams of insane productivity and existential crisis at the same time

@zeekayzed yeah i saw how it works not long ago damn this is fire, i use perplexity and it's included there life can become so easier if u use it properly

Claude Opus 4.5 is nothing short of a genie, the advancement in a year is crazy!