We're excited to announce duckdb-skills, a DuckDB plugin for Claude Code!
We think the embedded nature of DuckDB makes it a perfect companion for Claude in your local workflows.
The skills supported include:
+ read-file and query โ uses DuckDB's CLI to query data locally, unlocking easy access to any file that DuckDB can read.
+ read-memories โ a clever idea to store your Claude memories in DuckDB and query them at blazing speed.
These are powered by two additional skills:
+ attach-db โ gives Claude a mechanism to manage DuckDB state through a .sql file linked to your project.
+ duckdb-docs โ uses a remote DuckDB full-text search database to query the DuckDB docs and answer all of your (and Claude's own) questions.
https://t.co/EvM965jglL
Why stick with giant models when a slim one + good context engineering nails it?
Lower costs, faster results, less stress.
Most of the time, big just means bloated. ๐
AI Industry Made $57 Billion Mistake and No Oneโs Talking About It.
While GPT-5 headlines kept you distracted...
NVIDIA quietly released a bold claim:
โ Small Language Models (SLMs) are the future of AI agents
Cheaper, faster and just as capable for 80% of real-world tasks.
Easily one of the biggest shifts in AI this year and most people missed it.
99% people havenโt read this but they should: ๐งต
@mckaywrigley Sure thing! I'm a technical marketer learning to code to build AI tools, so I really appreciate your content. Keep up the good work! ๐ช๐
@SunshineNRnbows @mckaywrigley Probably, though Iโd like to think an LLM at O1 Pro level would know better.
For GAds, I did find Gemini 2.0 working better than most LLMs (logical). Iโll be testing Pro soon. ๐
@Redwinelips@mckaywrigley CPC is almost too low to be an intent keyword! :)
I'm curious and would love to get more insights, @mckaywrigley. What data do you feed into O1 Pro, and do you pass search terms along with transactions?
@mckaywrigley 13-year PPC pro:
At first glance, the CPC looks good. However, the key factors to consider are the type of keywords you're using (top-of-funnel vs bottom) and the network youโre targeting.
Most importantly, what is your cost per conversion? Measuring clicks alone is just vanity
The 80/20 of AI Agents is basically:
- know xml
- know what a webhook is
- know how to use an api
- be good at prompting
Anything beyond that is just model capability + creativity.
Recently became much more productive with LLM coding assistants. Might be because I created a proper instructions markdown file that I add to the context