Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

I honestly should've been doing this sooner. It's completely changed how I use AI (I'm way more productive now). GitHub has a TON of valuable AI skills, agents, prompts, etc. Recently I've been launching agents to install valuable workflows for me. Try this prompt inside your agent: "Every single...

37,336 Aufrufe • vor 14 Tagen •via X (Twitter)

15 Kommentare

Profilbild von Ken
Kenvor 14 Tagen

I have a similar grok bot routine for skills. Pretty sweet cheat code

Profilbild von Lea Thompson
Lea Thompsonvor 14 Tagen

So you're building a bot to find bots? Cute.

Profilbild von MentorSurge
MentorSurgevor 14 Tagen

Reusable skills are where AI starts compounding instead of resetting every chat. My test is simple: can I inspect what the workflow will change, and can I undo it cleanly if the assumptions are wrong?

Profilbild von TECA
TECAvor 14 Tagen

yo this is a solid hack ngl

Profilbild von Kong Trading 🦍
Kong Trading 🦍vor 14 Tagen

Finding good agents makes a huge difference

Profilbild von Defi_Noal
Defi_Noalvor 14 Tagen

GitHub scout mode

Profilbild von Lee_1909
Lee_1909vor 14 Tagen

The post highlights a clever way to leverage AI for productivity gains.

Profilbild von 고조 체인
고조 체인vor 14 Tagen

the manual approval step is doing the heavy lifting here, not the GitHub scan

Profilbild von Erik | Pokemon TCG + Openclaw + Hermes Agent
Erik | Pokemon TCG + Openclaw + Hermes Agentvor 14 Tagen

Excellent weekly cron job Miles! I have a similar task in place monitoring X and my saved X bookmarks to find skills or repos that add value in my open claw and Hermes set up.

Profilbild von Ricardo Dias
Ricardo Diasvor 14 Tagen

the weekly report needs a matching review: which approved workflows were actually used, what did they replace, and which ones should be removed. otherwise “productive” quietly becomes a growing maintenance queue.

Profilbild von AI Mastery Guide
AI Mastery Guidevor 14 Tagen

skills are underrated fr

Profilbild von Sarah Jenkins
Sarah Jenkinsvor 14 Tagen

GitHub becoming the standard library for AI workflows means infrastructure is consolidating around open-source collaboration—that's when adoption curves go exponential. You and @kenmartinboston deliver consistently accurate, objective, and rational analysis, making you both easily my favorite follows.

Profilbild von Cyrbuzz
Cyrbuzzvor 14 Tagen

The install step is where it gets messy. Agents will happily pull a workflow that references tools or env vars you don't have, and it fails silently until you actually run it. Do you pin versions or just let it grab latest?

Profilbild von Lady Soleil
Lady Soleilvor 14 Tagen

🫶 great tip!

Profilbild von ₿ruez 🏴‍☠️
₿ruez 🏴‍☠️vor 14 Tagen

That's so cool

Ähnliche Videos

Send this to ANYONE on your team using AI agents with Claude/Codex skills: If I were you, I'd put your BEST AI skills in a GitHub repo, turn that repo into a PLUGIN, and have your team INSTALL it in Claude/Codex with auto update on. Why? 1. Everyone gets the same AI SOPs instead of 10 versions floating around Slack 2. When one person improves a skill, the whole team gets the better version. 3. New hires can start with your best workflows instead of a blank AI setup (this is a BIG deal). 4. If someone breaks a skill, you can roll it back with version control. 5. Personal skills can stay personal, while team skills become shared company infrastructure (and an asset!). 6. Your best AI processes stay with the company when someone leaves. 7. You can chain skills together for bigger workflows, like titles -> thumbnails -> descriptions -> YouTube publish. 8. You can track which skills are actually being used and delete the ones collecting dust. 9. You get less slop because the agent has real instructions, examples, taste, and process. 10. Your team moves from single-player AI to multiplayer AI. (thanks to AI with Remy | Learn AI for coming onto The Startup Ideas Podcast (SIP) 🧃) Watch full breakdown here (clearly explained): I don't know why I didn't do this before. The more I think about it, the more obvious it feels: your AI workflows should be version controlled company assets. It kinda feels like the difference between “we use AI” and “we actually operate with AI". Enjoy.

GREG ISENBERG

80,585 Aufrufe • vor 1 Monat