Links » AI » Tools

FileMaker AI Skills

Our own Mislav Kos created a skill that leverages the newly LLM-friendly Claris help docs.

CadenceUX’s claris-filemaker-pro-skill is a skill in the pure sense, and a good one. It ships reference catalogs — all 360 calculation functions, all 155 script steps, the error codes, the help-center URLs — with a local-first, live-verify strategy and even a version-drift detector that flags when a fetched doc references a newer FileMaker version than the skill was built against. What it fixes is what the model knows: it stops your model from hallucinating a function signature or inventing an error code. That is real value. But it is, by design, a knowledge layer. The model still authors the XML; the skill just makes sure the model is better informed while it does that.

Andrew Kear’s FileMaker Layout XML Skill (from Clockwork Creative Technology, with a companion skill…

Links » AI » Practical AI/agent usage tips

https://artificialcorner.com/p/claude-limits-fix

Decent article on how to query claude without burning too many tokens.

Summary:
1. Edit instead of following up
Go to your prompt → click the pencil icon → rewrite it → hit send. Claude regenerates as if the bad response never happened, so you avoid piling up conversation history.

2. Start fresh every 15–20 messages
When a chat gets long, ask Claude "Summarize everything we've discussed so far," copy that summary, open a new chat, paste it as your opening message, and continue there. Avoids the exponentially rising token cost of long threads.

3. Batch questions into one message
Instead of three separate asks, combine them — e.g. "Summarize this article, list the main points as bullets, then suggest a headline" — so context is only loaded once instead of three times.

4. Upload recurring files to Projects
Sidebar → Projects → create…

Links » AI

https://github.com/mattpocock/skills

Well-spoken of software engineer skill set for agentic coding.

From the readme:

Skills For Real Engineers

My agent skills that I use every day to do real engineering - not vibe coding.

Developing real applications is hard. Approaches like GSD, BMAD, and Spec-Kit try to help by owning the process. But while doing so, they take away your control and make bugs in the process hard to resolve.

These skills are designed to be small, easy to adapt, and composable. They work with any model. They're based on decades of engineering experience. Hack around with them. Make them your own. Enjoy.

If you want to keep up with changes to these skills, and any new ones I create, you can join ~60,000 other devs on my newsletter:

Sign Up To The Newsletter

Why These Skills Exist

Links » Fun

https://www.fractalkitty.com/there-is-3-such-that/

FractalKitty's fascinating project to create a visual language, with her signature mathematical bent, for designing animated clocks. She's got sample clocks posted at https://github.com/fractalkitty/ClockTalk and the live project, which can import them, is at https://te-st.ing.

Links

https://www.flyingpenguin.com/the-boy-that-cried-mythos-verification-is-collapsing-trust-in-anthropic/

The Boy That Cried Mythos: Verification is Collapsing Trust in Anthropic

A pretty good analytical piece deconstructing the hype that Anthropic's Claude Mythos release is so powerful it's dangerous—something the government immediately hopped on board with.

Links » How Stuff Works

https://ciechanow.ski/archives/

A site full of interesting explainers of real world engineering and technology designed for the layman, including many interactive javascript demonstrations: how naval architecture (keeping ships afloat) works, how GPS works, fascinating facts about the moon, and much more. Worth a browse.

Links » Just Plain Interesting

https://www.ericweinhoffer.com/blog/the-whitworth-three-plates-method/

A mechanical engineer's page about an old (pre-1830s) mechanical method for producing microscopically flat surfaces.