Fourth Rep of 7 - Built and deployed an automation generating leads, which I'll reach out to clients and build their websites with. Later, I plan to extend it to their automation pipeline. Under the hood it's TypeScript on Trigger.dev with auto-deploy from GitHub #AISChallenge

Built a skill named /forge that serves as a default quality wrapper for Sonnet/Haiku work. While Nate's /fable-mode works fine on Opus/Sonnet but harmful below. - Ran 56 tests on dealing with edge cases on sonnet and haiku against fable using two skills: - - /fable-mode and /frontier - Screenshot Attached below #AISChallenge

Hi everyone, this is my day 2 built. I was able to successfully scrape 450 jobs from a website. While MCP works great Claude suggested after going through Firecrawl documentation that they do have an option of using Firecrawl CLI which works much faster and much smoother according to what I have experienced and even the credit utilization is quite less for the same task. - Optimize Clients Promotion Campaign: I can scrape their website to get screenshots of their promotion. - Understand what's the idea, what's their brand identity. - Optimize my plan based on that (even like creating videos or blogs). - Those are helpful in for my client study. #AISChallenge

I’ve been tracking my Claude Code token usage over the last week using Headroom and RTK, and I found the combination surprisingly useful. Headroom gives me the long-term picture across models, while RTK optimizes the prompts that actually get sent to Claude Code. Check the umbers of my last 8 days: * Headroom: 281M+ tokens saved (~$1.3k in proxy compression) * RTK: 7.0M tokens saved from 9.0M input tokens (78% reduction) One thing I learned: don’t judge these tools after one session. RTK, for example, dropped below 50% savings for a while because I was working on tasks where there simply wasn’t much redundant context to compress. A few days later it climbed back to 78% as my workload changed. So the percentage depends heavily on: * the type of work you’re doing, * how repetitive your prompts become, * and how long you measure. Looking at a single day can be misleading. For me, the interesting part isn’t the exact percentage, it’s that over hundreds or thousands of Claude Code commands, the savings become significant. The installation of both tools is pretty easy, if anybody want to give it a try: RTK Headroom

Just finished my day 1 AIS days challenge. i received my newsletter in my inbox. I'm very proud of me for that first big step. Thanks to nate and AI Automation Society #AISChallenge