Activity
Mon
Wed
Fri
Sun
Jul
Aug
Sep
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
What is this?
Less
More

Owned by Josue

AI, Sales, Beer

660 members • Free

The pub where we build the future of sales. Crack a cold one, talk shop, and automate your way to the top.

The AI Lounge

21 members • Free

A space to learn AI and automation, share your journey, and grow together. 🚀

Memberships

Vibe Builders

155 members • Free

AI Automation Skool

2.3k members • Free

AI Income Lab

2.8k members • Free

Skoolers

183.6k members • Free

School of Content

1.3k members • Free

AI Systems & Soda

3.2k members • Free

Builder’s Console Log 🛠️

2.5k members • Free

Agent Space

707 members • Free

Chase AI Community

66.3k members • Free

21 contributions to Accelerants
The /goal command turns Claude Code into a worker + evaluator loop
Claude Code shipped /goal a few weeks ago. Codex and Hermes have their version too. It replaces the old Ralph loop plugin people were running on their own. The idea is simple. You set a goal, Claude runs until the goal is met. What's actually happening under the hood: A worker model (Sonnet or Opus) does the real work. Writes code, runs bash, reads files. An evaluator model (Haiku) reads the conversation every turn and checks if your condition is met. When the evaluator says done, the goal auto-clears and you get control back. The catch most people miss: the evaluator only sees the transcript. It cannot run commands or check files itself. So your end condition has to be something the worker's own output can prove. Otherwise it loops forever and burns tokens. The prompt framework that works for me: 1. End state. One measurable thing. A test result, a file count, a markdown doc. 2. State check. How Claude proves it. A command, a script. 3. Constraints. Guardrails so it does not take shortcuts on other files. 4. Safety cap. Stop after 28 turns or 45 minutes. Non-negotiable. Real example: migrating 50 skills from one repo to another. Without /goal, Claude pings you for approval every few files. With /goal in auto mode, it ran straight through. Zero misses, zero babysitting. One gotcha. You need auto mode or bypass permissions on. Otherwise it stalls waiting for input and the loop dies. Also worth knowing: only one goal per session, condition can be up to 4,000 characters, and the goal survives if you close the session. You can resume it. Watch my full breakdown here: https://youtu.be/dcOg_xm5LUc?si=Syt1oZ_rIFo7BZQ_
0
0
5 Best AI Podcast Niches
- Spirituality - Relationships - Making money with AI - Health - Beauty AI Tools needed to start: here
5 Best AI Podcast Niches
0 likes • 11d
Spirituality and relationships have crazy retention in this format because the AI voice ambiguity actually works for them. Making money with AI is the saturated one already. What's working better, AI host alone or AI host plus human guest?
Claude + Seedance 2.0 = 550 videos per day
Fully-realistic UGC ads — cinematic lighting, human motion, perfect pacing — all done by AI agents. Production time: 10 minutes Scale: instant Campaigns are scaling now. Workflow here
Claude + Seedance 2.0 = 550 videos per day
0 likes • 11d
Seedance 2.0 quality is the inflection point a lot of teams have been waiting for. 10-min production time plus cinematic lighting changes what testing volume small teams can run, used to need a full video team. What's the cost per video at this scale?
AI Content Factory 2.0 — 600 UGC Ads Every Day, Fully Automated.
This AI-powered system generates, tests, and scales short-form content around the clock. * 600 ultra-realistic UGC-style ads daily * Cinematic visuals with realistic movement * Automated posting twice a day * Replicates high-performing ad formats * Focuses on proven, high-converting niches * Monetized through affiliates and brand partnerships * Scales effortlessly across multiple theme pages No creators. No filming. No product samples. Launch it once — let AI handle the rest. Grab the workflow here
AI Content Factory 2.0 — 600 UGC Ads Every Day, Fully Automated.
0 likes • 11d
600 a day is wild scale. The hard part isn't generation, it's the testing and rotation layer that decides which ones to actually run paid. How are you handling fatigue across that volume, fresh creator pool or just constant rotation through Claude?
I automated my entire content strategy with one AI skill
I was spending 4-5 hours every weekend manually creating guides, writing LinkedIn posts, and crafting DM templates for my lead magnets. Same process every week. So I built a Claude Code skill that does the whole thing for me. Here's the workflow: 1. I paste a YouTube video URL 2. The skill extracts the transcript using yt-dlp (free open source tool) 3. It researches the topic further on its own using web search 4. It writes a full Notion guide with step-by-step instructions, formatting, and sources 5. It generates 3 LinkedIn post variations (story angle, problem angle, framework angle) 6. It creates a DM template with placeholders for the person's name and the guide link The whole thing runs in about an hour for a full week of content. The only manual step is the graphic in Canva because image models still can't nail that consistently. The key here is that skills are just text files. No code. You describe your workflow once in plain English and Claude follows it every time. The structure is simple: a SKILL.md file for the main instructions, a references folder for things like writing rules and guide templates, and optionally a scripts folder for any code it needs to run. If you have any repeating workflow in your business (content, outreach, reporting, onboarding) you can turn it into a skill the same way. Just do the task once with Claude, then tell it to package the whole process into a skill using the Skill Creator. I put together a full walkthrough showing the entire build if anyone wants to see how the pieces fit together 👇 https://youtu.be/Z1zx4SivZ2Y?si=ViSKIkQsRq8AjcT4
0
0
1-10 of 21
Josue Hernandez
2
14points to level up
@josue-hernandez-1795
Automation and AI Enthusiast Check out my YT! https://www.youtube.com/@AIJosue

Active 4h ago
Joined Mar 18, 2025
Phoenix, Arizona
Powered by