Join me in WhatsApp - we can communicate faster https://chat.whatsapp.com/JuqbToSN6bcJAY94jLzZEd

For the last two days I have been experimenting with GSD for Claude and its doing wonders to my workflow by brinign in spec driven development and I am able to follow the best practices out of box. Before this I have been using claude-flow but GSD is much simpler and creates a structured, roadmap, phase by phase implementation where you brainstorm on every phase. You spend more time in planning and then it creates a much better outcome. Just wanted to share whats working for me well. https://github.com/glittercowboy/get-shit-done

🚀🔔"Join us in celebrating digital empowerment—where automation meets freedom in our RPA course!" 🚀Title: RPA : Microsoft Power Automate Desktop - Zero to Expert : 2 🔗https://www.udemy.com/course/microsoft-power-automate-desktop-course-zero-to-expert-2/?couponCode=JAN-FREE-1000 Please share the post with others & provide your valuable feedback on these course without fail. 🔔Our Best 5 courses on Power Automate Cloud , Power Automate Desktop & PL 500 Certification are now available in Udemy & Udemy Business. 🚀 Title 1: Become RPA Master in MS Power Automate Desktop 🔗https://www.udemy.com/course/microsoft-power-automate-desktop-tutorials-for-beginners/?referralCode=03D49B549EE2193E79EE 🚀 Title: Become Master in Microsoft Power Automate for Cloud 🔗https://www.udemy.com/course/learn-rpa-microsoft-power-automate-step-by-step/?referralCode=C95593A93019200C87F1 🚀 Title : PL-500 Microsoft Power Automate RPA Developer BootCamp 🔗Link: https://www.udemy.com/course/pl-500-microsoft-power-automate-rpa-developer-bootcamp/?referralCode=891491BAB7F20B865EE6 🚀 Title 2: RPA : Microsoft Power Automate Desktop - Zero to Expert : 2 🔗https://www.udemy.com/course/microsoft-power-automate-desktop-course-zero-to-expert-2/?referralCode=783F39A1D0CDB4A70A7C 🚀 Title 3: RPA:Microsoft Power Automate Desktop:Intelligent Automation 🔗https://www.udemy.com/course/power-automate-desktop-course-intelligent-automation/?referralCode=E8C51F3C27EA98FE100C

Hey everyone, if you're looking to run your agents locally for privacy or cost reasons, I found a breakdown for a Moltbot + Ollama setup that actually handles tool-calling (exec, read, write) reliably. Why most local setups fail: Most models under 70B struggle with Moltbot's complex system prompts—they hallucinate tools or ask for permission too much. This setup solves that. The Setup Specs: - Hardware: 48GB VRAM (2x 3090s). - Model: Qwen 2.5 72B Instruct (Q3_K_M). - Throughput: ~16 t/s. 3 Critical "Gotchas" Fixed in This Guide: 1. API Settings: You MUST use api: "openai-completions" in your clawdbot.json. If you use openai-responses, you'll get empty output. 2. Tool Permissions: You have to explicitly allow "read" in the tools config, or the agent can't even read its own skill files. 3. The Prompt: It includes a custom Modelfile that tells Qwen to "Act first, report results later." This stops the AI from talking about what it could do and makes it actually do it. Pro-Tip: If your local model is too wordy, add a SOUL.md to your workspace with "Brevity" instructions. It saves a ton of time and tokens. Check out the full config details here: https://gist.github.com/Hegghammer/86d2070c0be8b3c62083d6653ad27c23 Let me know if you're running agents locally—what hardware are you using?