5 GitHub Repos: Kill AI Slop, Go Viral, Make Money
A solo walkthrough of five open-source GitHub repos getting traction right now, an AI writing editor, an agent-run CRM, a video-editing agent, a skill security scanner, and a phone-controlling harness, each with the exact install command and the first small workflow to try.
Posted
5 days ago
Duration
Format
Listicle
educational
Views
42.8K
768 likes
57 · 43
Big Idea
The argument in one line.
GitHub surfaces the agent tools that become SaaS products months later, and five open-source repos reviewed here turn that early look into real leverage: believable writing, a self-updating CRM, automated video edits, a skill safety scanner, and phone-level agent control.
Who This Is For
Read if. Skip if.
READ IF YOU ARE…
A solo founder or creator who writes constantly (tweets, landing pages, cold emails) and wants copy that doesn't read as AI-generated.
Someone managing sales or partnership leads by hand who keeps letting warm intros go cold.
A creator or agency that edits the same footage into clips every week and wants that process turned into a repeatable system.
A builder who installs AI skills, plugins, or MCP servers from GitHub and has never checked one for security risk.
Anyone who wants an early read on the next wave of agent tools before they show up as paid SaaS products.
SKIP IF…
You want a deep technical tutorial for any single repo. Each gets a plain-English overview and an install command, not a full walkthrough.
You're looking for tools outside AI-agent workflows. Every pick here is specifically for agent-based tooling.
TL;DR
The full version, fast.
Greg Isenberg reviews five open-source GitHub repos worth installing this month. Peter Yang's No AI Slop strips patterns like throat-clearing and fake-profound endings from AI writing while keeping the writer's voice. Comp AI's CRM treats the database as a workspace an agent updates on its own, instead of one that goes stale. Browser Use's Video Use lets a coding agent transcribe, cut, caption, and self-check raw footage into a finished video. NVIDIA's SkillSpector scans agent skills for prompt injection and supply-chain risk before install, having flagged vulnerabilities in 26% of skills it studied. Phone Harness lets an agent see, tap, and verify a real phone screen. The method: install one, build a small workflow, then decide whether to productize it.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Greg explains why he's spending more time on GitHub: it surfaces the tools that become SaaS companies, agencies, and startup ideas before they go mainstream. All six repos he pulled are free and open source, with one dependency (11Labs) that costs money.
01:44 – 05:20
02 · Repo 1: No AI Slop
Peter Yang's writing skill strips the patterns that make AI writing feel synthetic, binary contrast, throat-clearing, faux insight, colon reveals, dramatic fragments, fake-profound endings, while preserving the writer's voice. Workflow: write a rough draft yourself, then run the skill as cleanup.
05:20 – 10:52
03 · Repo 2: Agentic CRM (Comp AI)
An open-source CRM built for AI agents rather than for humans to maintain by hand. The agent researches contacts, enriches company info, schedules follow-ups, and keeps notes current. Install needs bun and Docker; runs locally on :3000/:3001 with Google or Microsoft OAuth.
10:52 – 15:15
04 · Repo 3: Video Use
Browser Use's video-editing agent drops raw footage in a folder and lets Claude Code or Codex cut filler words, remove dead space, add subtitles, color grade, build overlays, render, and self-check the output against the source.
15:15 – 18:49
05 · Repo 4: SkillSpector (NVIDIA)
A security scanner that answers 'is this skill safe to install' before you grant an agent new tools. Scores skills 0-100 across 68 patterns in 17 risk categories, flagging prompt injection, data exfiltration, and supply-chain risk.
18:49 – 22:25
06 · Repo 5: Phone Harness
Connects an agent (Codex or Claude Code) to a real iPhone via Mac's iPhone Mirroring, or a real Android via ADB, no jailbreak, no Xcode, no app on the phone. The agent sees the screen, taps, types, scrolls, and verifies results.
22:25 – 24:43
07 · Closing thoughts: the three-step method
Greg recaps his process for any new repo: install it, build one small workflow that adds value, then decide whether to productize it for other people or keep it as personal leverage. Asks viewers whether he should do this monthly.
Atomic Insights
Lines worth screenshotting.
GitHub now shows the tools that become SaaS companies, agencies, and startup ideas months before they go mainstream.
AI-generated writing has a detectable fingerprint: binary contrast, throat-clearing, faux insight, colon reveals, dramatic fragments, and fake-profound endings.
Readers rarely say a post was written by AI, they just trust it less, stop replying, and keep scrolling.
The safer creative workflow is a human rough draft first, then an AI pass to remove AI-sounding patterns, not the reverse.
Most CRMs fail because they depend on a human remembering to update them, and the stale data just becomes a graveyard nobody opens.
An agent-first CRM runs on its own schedule instead of waiting to be remembered, researching contacts and flagging follow-ups without being asked.
Businesses rarely fail from a lack of opportunities, they fail because those opportunities get scattered across old emails and forgotten threads.
A video-editing agent can read a transcript, propose cut points, render the edit, and check its own output against the source footage.
Most creators repeat the same handful of edits on every video, which means their personal style can be turned into an explicit, repeatable system.
In a 42,447-skill study, 26.1% of AI agent skills contained a vulnerability and 5.2% showed signs of likely malicious intent.
Skills with executable scripts were 2.12 times more likely to be vulnerable than skills without them.
As builders assemble their own stack of coding agents, research skills, and browser tools, that setup starts to function like a small operating system, and security stops being an enterprise-only concern.
Phone Harness controls a real iPhone through Mac's iPhone Mirroring or a real Android through ADB, with no jailbreak, no Xcode, and no app installed on the phone.
An agent that can see, tap, and verify a phone screen can run onboarding and checkout QA on a real device instead of a simulator.
Face ID, camera flows, and DRM-protected video are still hard limits for phone-controlling agents.
The three-step method for any new repo is install it, build one small workflow that adds value, then decide whether to productize it for other people.
Takeaway
What five new agent tools actually change
AGENT TOOL STACK
Five new open-source repos show where AI agents are heading next: cleaner writing, self-running CRMs, automated video edits, security-checked skills, and direct phone control.
02Repo 1: No AI Slop
AI writing has a detectable fingerprint (binary contrast, throat-clearing, colon reveals) that readers register as untrustworthy even when they can't name it.
Writing your own rough draft first and running an AI cleanup pass second keeps your voice; asking AI to draft from scratch sands it away.
03Repo 2: Agentic CRM (Comp AI)
A CRM that depends on a human remembering to update it will eventually go stale, and the leads worth the most money sit unopened.
An agent-run CRM can research contacts, flag follow-ups, and keep notes current on its own schedule instead of waiting to be told.
04Repo 3: Video Use
A creator's personal editing style, pacing, subtitle look, cut rhythm, usually lives only in muscle memory until it's made explicit as a repeatable pipeline.
Content is often the real bottleneck for a good product, since even a strong product loses if nobody sees it.
05Repo 4: SkillSpector (NVIDIA)
In a study of over 42,000 AI agent skills, roughly a quarter contained a vulnerability and about 1 in 20 showed signs of likely malicious intent.
Once a builder's setup includes multiple coding agents, skills, and MCP servers, it functions like a small operating system, and unscanned installs become a real risk.
06Repo 5: Phone Harness
An agent that can see, tap, and verify a real phone screen opens up mobile QA and workflow automation that browser- and terminal-based agents can't reach.
Face ID, camera flows, and DRM video remain hard limits for screen-based phone agents, so the safest first test is a simple signup or onboarding flow.
07Closing thoughts: the three-step method
The repeatable process for evaluating any new tool is install it, build one small workflow that adds real value, then decide whether to productize it.
Spending time on GitHub regularly, even without deep technical skill, builds pattern recognition for what's coming before it becomes a mainstream paid product.
Glossary
Terms worth knowing.
Agentic-first CRM
A customer database designed to be operated by an AI agent on its own schedule, not just a form a human fills in after the fact.
Prompt injection
A security risk where hidden text or instructions inside a document, webpage, or tool response tricks an AI agent into taking unintended actions.
Supply-chain risk
The danger that a dependency, script, or package an AI skill installs is itself compromised or malicious.
EDL (edit decision list)
A structured list of cut points and timestamps that describes how raw footage should be assembled into a finished video.
ADB (Android Debug Bridge)
A command-line tool that lets a computer send commands to, and read the screen of, an Android device without modifying the phone.
Data exfiltration
An AI skill secretly sending a user's files, credentials, or other private data out to an external server.
“You can have a great product, and you're still going to lose if no one's going to see it.”
tight, standalone line about content as a bottleneck→ newsletter pull-quote↗ Tweet quote
20:46
“Agents are moving from answering questions, they're operating tools, and phones is one of the biggest tool services in the world.”
names the shift from chatbot to operator in one line→ TikTok hook↗ Tweet quote
24:23
“Should I be doing this every month, every two weeks, every six weeks? Never again.”
direct engagement ask that doubles as a punchy sign-off→ IG reel cold open↗ Tweet quote
The Script
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
17px
metaphor
I don't know about you, but I've been spending a lot more time on GitHub lately, and there's a real reason behind it. I mean, it's turned into one of the best places to get an unfair advantage in the agentic era because you're seeing the tools people will be talking about in six months today. A lot of the things that eventually become SaaS companies, agencies, workflows, and startup ideas show up there first.
It's really... like that famous quote you know the future is already here it just isn't evenly distributed yet so i'm trying something new with today's episode i went through a ton of github repos that have been getting attention over the last 30 days and i picked the six that i think you should know about if you're trying to build products if you're trying to make money if you're trying to save time or you just want to get more done with ai Now, some are more technical than others, but I'll explain them all in plain English.
You know, what each one does, why it matters, how I'd actually use it, and how you can try it for yourself today. The last one is from Nvidia. A couple of the other ones are from smaller devs, but every one of them is something I can picture someone using to make money or to save real time.
All six are free and open source, meaning the code is free to use, but... As a lot of you know, some have dependencies, like one has a dependency on 11 Labs, which does cost money. So beware of that.
Let's get into the episode. I'll see you at the end. And if you haven't liked and commented and subscribed, just do it to get your algorithm pumping with a lot of valuable content like this.
Let's go.
So the first repo is my friend Peter Yang's no AI slop skill. And I like this one because everyone who uses AI for writing has felt this exact problem. I mean, you ask ChatGPT or Claude to help you write something.
It's a tweet. It's a LinkedIn post. And technically the writing is fine.
The grammar is fine. The syntax is fine. But it has this like weird smell to it.
Maybe it sounds like too polished or too symmetrical or formulaic. Sometimes it has like, it's not X, but it's Y, you know, or uses the word quietly a lot. You know, I feel like it feels like reading a keynote from a fake SaaS conference.
And once you notice it, I feel like you can't unsee it. You know, a lot of people are able to smell it now. So what's really cool is Peter's skill is basically an editor that strips those patterns out while trying to preserve your actual voice.
The last part's important because a lot of the writing tools make your writing cleaner, but sand off the interesting parts and make everyone sound the same. And if you're going to sound the same, it's hard to stand out. You know, you actually want to do the opposite.
So what's cool about this, this uh repo is it hunts for the patterns that make writing feel ai generated and helps the draft feel like a real human being wrote it uh why does that matter like i said if you're building products today you're writing constantly and you want to stand out you know i i personally am writing tweets i'm writing landing pages i'm writing cold emails launch posts, product updates, onboarding copy.
If you have investors, you're writing investor updates. And you don't want to sound like generic AI because people are going to feel it. They might not say this was written by AI.
They might not respond and say it. But they'll just trust you less. They're just going to keep scrolling.
They're not going to reply. They might even believe what you're saying because they're like, this is AI written. So this repo isn't really about making writing nicer.
It's really about making your communication more believable. So if you want to try this one, you can install it as a skill. That's what I would do.
You just type in npx skills add and then you put the GitHub link and I'll include the link to the repo in the show notes in the description and actually all of them so you can just go and do that. Then you can use it inside your agent workflow, wherever you have a draft of it, of something, right? So the practical way I would run it would be just to, you know.
Write a rough draft first. I wouldn't ask AI to invent the whole thing from scratch. Just write an outline and get the real points down, even if they're messy.
And then you would ask the skill to remove the AI sanding patterns while keeping your voice. So that's the workflow to think about. You have a human set of ideas first, and then you have AI cleanup.
Second, which is different than how a lot of people today are creating content, they're just either asking AI to write everything, basically trying to one -shot it, and then saying, hey, this doesn't look good, this doesn't look good. But this sort of hybrid approach with the skill here, super interesting. So there you go.
That's number one. So the second repo is the... is the CRM by TriCompAI.
It's an open source CRM built for AI agents. And that sounds a little technical and maybe boring. I'm going to try to break it down as simple as possible so you can understand how to actually get value out of this if you're building a business.
A normal CRM is a place where you store your relationships and your customers and your leads. It's basically a database with names, emails, and notes. Sometimes deal stages if people are using it for sales.
The problem is almost all of them depend on you doing the work. So you have to remember to update the person, remember what happened last time, what they said, who went cold, and just basically keep your CRM clean. And because of that, if you're anything like me, you've had a CRM and it's just turned into these graveyards that you just sort of stop updating.
It starts off really exciting. And then a few weeks, the data goes stale and the notes get messy and you just stop updating it. And the people who could actually make you money end up sitting in a tool that nobody wants to open.
So what's interesting about this particular repo. is that it treats your CRM as a workspace for an agent instead of a filing cabinet for you. So the agent can look at records and research people and enrich company info.
It could do scheduled follow -ups and then it could keep the notes current. All the stuff that basically you didn't want to do, it could do it for you and do those tasks. The whole idea of this AI CRM is that It shouldn't just store information.
It should maintain the relationship graph for you. It's a big deal if you're a founder because most businesses actually don't fail from a lack of opportunities. A lot of times they fail because the opportunities are just scattered everywhere.
You get this warm intro maybe six months ago or you get feedback from a customer who says, check back later, and you forget about it. And there's real money sitting inside those emails. So the use case here isn't to replace Salesforce.
I'm not suggesting that. It's like a smaller, useful use case. So the way I would do it is, say I'm looking for sponsorships for my podcast.
I can run my sponsorship pipeline through it. tracking agency leads. I can manage investor updates or if I have investors, I can follow up with everyone who's joined a wait list to something that I've vibe coded.
Or I can have it handle customer success just fully for a small SaaS. So if I were testing this, I would actually start with one small workflow. I'd make a pipeline called something like warm leads I can't afford to forget.
And then I'd drop in Every person who's shown any buying intent and they replied to any email or booked a call or asked about pricing or said they'd circle back in 45 days or after Christmas or something. And then I'd let the agent do the hard work to keep that alive.
In the past, you'd hire someone to do this. Now you have this agent that's doing it for you. Who needs a follow -up?
What should I say? What's changed at their company since we last talked? That's why this is really cool.
Okay, so how do you install this? Well, you're going to need bun and docker installed. So the basic setup is you're going to want to git clone the repo.
Again, I'll have that repo in the show notes. You're going to want to do cd crm cpenv .example .env. You're going to want to do bun install docker -compose -up -d.
bun run db deploy bun run db seed and bun run dev and i'll include um i'll maybe i'll get some notes up and if you go in the description i could uh have that and i can also show it up you know on the screen here so you can see it uh then what it does is it runs locally So usually it runs locally on localhost 3000 with the API on localhost 3001.
So there's environment variables to set, especially for auth. So you want a Google or Microsoft OF client. If you want sign -in and email or calendar integrations, which I assume you're going to want.
So this isn't like a one -click, everything is set up. beautiful thing but it's real it's a product shape repo and i think it's really interesting um i think like the bigger opportunity of something like this is that everyone has a crm problem and they just never really call it that right they they say i forgot to follow up or i forgot who to email or our leads are a mess um or they have this feeling like oh my god i'm leaving money on the table i've certainly felt that and that's a And that's all the same pain and this repo just like points at the fix.
And like the big idea is how do you create relationship systems that actually do work with you, agents actually do it. I think it's interesting and that's why I put it on the list. So the third repo is by browser use and it's called video use.
And it's one of my favorites because you're going to instantly get it. It lets you edit videos with coding agents. So you drop your raw footage in a folder and you can ask an agent like Cloud Code or Codex to edit it.
It'll remove filler words. It'll cut dead space. It could add subtitles and color grade and build overlays.
It can render the video and it can actually check the output. There already exists a bunch of AI video editing softwares out there. But I think what's really cool about this specific repo is that the editing workflow here becomes something that your agent can understand and repeat.
So think about this. Most creators or people who create content have the same handful of edits over and over. They have the same subtitle.
I mean, even if you look at my YouTube channel, you can see it's like a very similar style every single video. It's at a certain pace, a certain way of cutting pauses and opening clips and turning a long conversation into shorts and mids. So normally all that...
actually lives in a person's brain and muscle memory. But with a repo like this, it becomes like way more explicit. And the agent can actually read the transcript, look at the timestamps, propose an editing strategy, render it and check the cut points.
I mean, how cool is that? Because if you're a creator or founder, content is going to be probably one of your biggest bottlenecks. And you know this, you can have a great product.
And you're still going to lose if no one's going to see it. So I think this repo is like a way to shrink the distance between raw material and the published content. If I were using this, I wouldn't try to automate my whole YouTube channel on day one.
I think that's way too much. And I think when people use a repo like this on day one and then they start and they don't get the results, it's because they just... ask for too much i would start with one small repeatable format so maybe it's taking a founder's loom and turning it into a 60 second launch video or taking a podcast recording and just being like i need three banger clips from it um that is good enough to start and then once you have one format then you can turn it into a system and then once it's a system then you can run it yourself or Sell it to other people.
Startup idea right there, right? Every niche needs content and pretty much no one enjoys editing it. Real estate agents need listing videos.
SaaS founders need product videos. Coaches need clips. And agencies need different ad variations.
All these... types of companies have different workflow where they're creating content. And it's fun to create content a lot of time, but the actual editing is really hard.
Okay, so if you want to try this, how can you try it? The setup is really agent -friendly. So all you have to do is paste the setup prompt into Cloud Code or Codex with Shell Access, actually.
So you just say setup. the GitHub, read the install .md first, install the repo, wire up ffmpeg, and then register the skill with the agent I'm using. And then ask me for the 11labs API key when needed.
Could you install this manually? Yes, you can do git clone and ln, sfn, and all that stuff. But for 95 % of people listening to this, might as well just have the agent install it for you.
That's an interesting one. I feel like try it, see if it works for you and let me know what you think. So the fourth repo is by NVIDIA and it's called Skill Spectre.
a no -brainer one to install because people are starting to install skills and MCP servers and plugins and agent tools straight from GitHub, which is exciting because it gives your AI new abilities, but it creates a problem because a skill isn't just a block of text, right? It can include instructions and scripts and dependencies, tool access, and basically behaviors that...
change how your agent works. And in some cases, it can actually touch files, call tools, and connect to services. So before you install random capabilities from GitHub, you should probably ask whether it's safe.
And that's what Skills Spectre is for. It can scan AI agent skills for security issues, things like prompt injection, data exfiltration. supply chain risk, hidden instructions, basically any malicious patterns and MCP -related risks, SkillSpectre has your back.
So the way I think about it is before you hand your AI a new tool, scan the tool, right? And this matters a lot more now because AI workflows are getting more modular.
So most people use one chatbot today, but builders are already assembling their own AI work environments, like a coding agent, a research skill, a design skill, maybe it's a browser tool, a video workflow. And at some point, you're set up starts to look like a little operating system for your work.
And once that happens, security stops being an enterprise -only problem and becomes a normal builder or founder problem. So I think it's a really important one. No affiliation with NVIDIA.
But if you want to try it, you can use UV. The quick install is uv -tool -install -git -plus and then you just post the GitHub.
And then just scan a skill directory with skillspectorscan .my -skill. Or you could just scan a GitHub repo directly with skillspectorscan with the link. If you want a faster static scan that doesn't send file contents to an LLM provider, if you add dash dash node.
It matters if you're scanning sensitive files or private files in general. There's also a Docker option if you'd rather not install Python locally, which I think some people would want to know that. I've been thinking about this a bunch.
If teams are going to install AI skills and MCP servers, someone's going to need to help them decide what's safe. That could be a trusted marketplace, a security scanner. an install gate for companies or a feature inside every agent platform.
I like that NVIDIA is attached to this one. That's why I included it because it gives the whole category credibility. And it also is just admitting that, hey, like a lot of these skills, plugins, things like that could be malicious and you got to be careful.
So I had to put that in there, had to keep it real with you all and check it out. So the fifth repo is called PhoneHarness, and it lets an AI agent actually control your phone. Most AI agent tools are built around browsers and terminals, also desktop apps.
obviously makes sense because a lot of the work happens there. But think about it. A huge amount of work happens on phones now and banking apps and messaging and social and food delivery, all that sort of stuff.
So there's a ton of workflows that are hard to automate because the only real interface is a phone screen. So phone harness connects an agent like Codex or Cloud Code to a real iPhone or Android. Super cool, right?
For iPhone, it uses Mac iPhone mirroring. And for Android, it uses ADB. So you don't have to jailbreak it, which I was like, oh my God, I don't want to jailbreak anything.
You don't have to jailbreak it. No Xcode. You don't need a special app on the phone either.
Basically, the agent sees what's on the screen and it could tap and it could type and it can scroll and it could open apps and it verifies what happens. I know there's someone thinking like, why? Why does that matter?
Well, if you're building a mobile app, think about the QA, right? You can have an agent test, onboarding, sign up. checkout on an actual real device.
If you're building any sort of automations, it could open up mobile apps that have no API. And if you're a creator or even an operator, it could eventually handle repetitive mobile workflows across things like TikTok and Instagram. So if you want to try this, the first thing to do is test the mobile signup flow.
Super simple. Open up the app. create an account, tap through onboarding, try checkout, take screenshots, and tell me where it gets confusing or breaks.
That's super valuable. Every mobile team should be constantly doing that, but most don't because it's tedious or they don't want to hire that person to go and do it. Or they honestly make mistakes.
So this is going to help you there. If you want to try this one, the repo gives you a setup prompt to paste into Codex or Cloud Code. I'll include it.
I'll include it, basically set up phone harness for me, clone the GitHub, read the install .md, install it so phone harness is on my path, register it as an agent skill, and then read onboarding .md and walk me through the setup. For iPhone, you do need macOS Sequoia or later. with iPhone mirroring, plus accessibility and screen recording permissions granted to your terminal.
For Android, from Android friends, turn on developer options and connect through ADB over USB or it actually works wireless too. Then run phone harness dash dash doctor to check the setup. It's early.
This one is early and it has its limits. Some phone flows won't work perfectly. For example, lock phones need you, and face ID and camera flows are pretty tricky.
But the direction is obvious, right? Agents are moving from answering questions, they're operating tools, and phones is one of the biggest tool services in the world. And if you figure out some of these workflows, there's startup ideas right there.
productize mobile QA, would someone be willing to pay $100 a month, $500 a month for that? How many clients do you need to get to $10 ,000 a month? That's in general what's interesting about a lot of these GitHub repos is you can install them.
Step two is have a small workflow. Get it to work. add value.
And step three is then, should I be productizing this for other people or just continue using this in my own workflows to be more productive, to make money and create value? So there you have it, folks. Five GitHub repos I think are really interesting.
Obviously, I don't want to be a full -time open source analyst, but because GitHub is one of the few places you can still find genuinely useful tools before they go mainstream. You've got to be spending time there. I think it's totally worth it.
And as you install some of these repos, even if you're not technical, you learn things, right? You start learning what works for you. What's this repo missing?
How can you make this work for your company? How can you sell this to other people? I just think it's a really interesting thing to do, to just do monthly.
finding new GitHub repos, installing them. You'll be able to build faster and it'll just connect the dots in your head in this agentic era that I think it's worth it. So I don't know if this has been fun for you, interesting for you, valuable for you.
If you listen to this podcast, you know I live to serve and all I care about is just increasing your probability of success in this era with ideas, with tools, with frameworks. So please let me know in the comments what you thought of this. Should I be doing this every month, every two weeks, every six weeks?
Never again. All good. I appreciate you so much.
And I'm rooting for you. So I'll see you next time. And have a creative day.
The Hook
The bait, then the rug-pull.
Greg Isenberg has been living on GitHub lately, and this solo episode makes his monthly ritual explicit: five open-source repos already getting traction, an AI writing editor, a self-running CRM, a video-editing agent, a skill security scanner, and a phone-controlling harness, each with the exact install command and the first workflow worth trying.
Frameworks
Named ideas worth stealing.
02:29list
The AI Slop Patterns (6)
Binary Contrast
Throat-Clearing
Faux Insight
Colon Reveal
Dramatic Fragment
Fake-Profound Ending
Six recurring patterns that make AI-generated writing feel synthetic; the no-ai-slop skill scans for and removes them while preserving the writer's own voice.
Steal forauditing any AI-drafted tweet, landing page, or cold email before publishing
07:46model
Most CRMs vs Comp AI CRM
Who does the work: You -> The agent, off its own work queue
When it runs: When you remember -> On its own schedule, browsing the inbox and keeping going
What it writes: Whatever you typed -> Only what a tool observed; weak evidence becomes a question for a human
The hard rule: None, a guess looks like a fact -> Nothing about a person is guessed
The comparison table Comp AI uses to pitch an agent-run CRM against a traditional, human-maintained one.
Steal forpositioning any agent-run tool against the manual-labor version it replaces
12:16model
Video Use pipeline
Transcribe (word-level timestamps)
Pack (~12KB text file of every take)
Reason (cuts come from speech boundaries)
EDL (the edit list)
Render (final.mp4)
Self-Eval (checks every cut boundary)
The six-stage pipeline an agent runs to turn raw footage into a rendered, self-checked video.
Steal forstructuring any agent-driven content pipeline into distinct, checkable stages
16:17model
SkillSpector risk bands
0-20 Low: safe, allow it
21-50 Medium: caution, warn the user
51-80 High: do not install, block
81-100 Critical: do not install, block
The 0-100 risk score SkillSpector assigns to an AI agent skill before installation, based on 68 detection patterns across 17 risk categories.
Steal forbuilding an install gate or trust score for any plugin or skill marketplace
20:46model
Phone Harness: See, Act, Verify
See: capture the iPhone Mirroring window, read it with OCR
Act: CGEvents posted at the HID tap, taps, long-presses, drags, scroll, and typing
Verify: screenshot again, there is no DOM so the capture is the truth
The perception-action-verification loop Phone Harness uses to let an agent operate a real phone screen with no API access.
Steal fordesigning any screen-based agent automation that has to trust what it sees, not a DOM
22:34list
The three-step method for any new repo
Step 1: Install the repo
Step 2: Build one small workflow
Step 3: Decide whether to productize it or keep it for yourself
Greg's closing framework for evaluating any new GitHub repo before committing further time to it.
Steal fora monthly ritual of testing new AI tools before deciding whether they're worth building on
CTA Breakdown
How they asked for the click.
VERBAL ASK
00:34subscribe
“if you haven't liked and commented and subscribed, just do it to get your algorithm pumping”
quick, low-pressure ask dropped mid-intro before diving into repo one, then a soft comments ask again at the very end
Add Modern Creator as a preferred source and Google shows you more of our breakdowns in Search, Top Stories, and AI Overviews. It only changes what you see, and you can undo it in your Google settings anytime.
Add to Preferred SourcesOpens your Google source preferences with us pre-loaded. Tick the box and you're done.
Greg Isenberg and developer Vinny break down WebMCP, the experimental browser feature that lets any AI agent search, compare, and buy on a website without scraping the page, then price two startup ideas built on it.
Cloudflare quietly built the payment rail for AI agents to pay tiny fees for web resources, and that rail is about to spawn a whole generation of businesses selling clean data, agent-readiness, and packaged expertise.
Greg Isenberg gets a live, screen-shared tour of Jack Dorsey's new agent-native chat app from an early user — and presses him on whether it actually beats Slack.
Cody Schneider maps the exact infrastructure — pipeline, warehouse, agent — behind a Facebook ads system that researches, creates, publishes, and kills its own losing ads.
Nick Vasilescu spins up an AI co-founder running on Grok 4.5 and, in one live session, takes it from idea to landing page, thumbnail, and cold-email sequence.
Greg Isenberg names the role he thinks AI agents are about to make the most valuable job in tech, and hands over the folder structure, tool stack, and 30-day plan to become one.
00:21
00:39
00:53
01:18
01:35
02:11
02:29
02:47
03:05
03:23
03:41
03:59
04:17
04:35
04:53
05:11
05:49
06:08
06:28
06:47
07:07
07:26
07:46
08:06
08:25
08:45
09:04
09:24
09:43
10:03
10:22
10:42
11:20
11:38
11:57
12:16
12:35
12:54
13:12
13:31
13:50
14:09
14:28
14:46
15:05
15:41
15:59
16:17
16:35
16:53
17:10
17:28
17:46
18:04
18:22
18:40
19:16
19:34
19:52
20:10
20:28
20:46
21:04
21:22
21:40
21:58
22:16
22:54
23:10
23:34
23:53
24:13
24:33
28:58
34:10
38:44
Video of the Day37:47
Video of the Day56:00
35:18