Location: Turin, Italy

Remote: Yes, with European or North American time-zone overlap

Willing to relocate: For an exceptional role

Technologies: TypeScript, React, Redux, Storybook, Material UI, D3; PHP, Laravel, Symfony, SQL, MongoDB; automated testing and CI/CD

Résumé/CV: https://www.linkedin.com/in/manuelejsarfatti

Email: [email protected]

===

I am a Senior Frontend Engineer with ~15 years of experience specialised in TypeScript/React, with a background in design, and comfortable across the backend too (mainly around PHP, SQL, MongoDB, Node.js and CI/CD).

My work usually covers frontend architecture, component systems, automated testing and API contracts for multi-tenant applications; UI/UX analysis and design; data visualisation; team lead and mentoring as well.

I have experience taking a greenfield project from the first line of code to production, as well as embedding in existing teams to improve the product.

I have taught design and programming. I am comfortable working in remote-first environments, and interested in 6-12 month contracts or longer.

Because it’s wrong, and you are right. It should be in your global AND per-project md’s… Perhaps in a custom output style too.

You don’t need a skill. Just tell it to BLUF (bottom line up front) and ASD-STE100.

And stop using Opus 9 Pro Max XHigh 10.0 for everything. If you choose a hyper-thinking model for asking the weather you can’t but expect yapping.

How do you actually incorporate these into your prompt? Because I've tried and I've seen many others try and report that it does not work well, especially over long sessions.

I also don't know how much to trust the model, but I've had the model tell me specifically that certain aspects of ASD-STE100 are unactionable and will just create more noise.

The OP's own skill even leads with something in a very similar vein:

> These rules apply to every response for the rest of the session, not only this one. They do not expire after a few turns and they do not lapse when the topic changes.

My understanding is that phrases like this are at best a _very_ weak signal to the model. It's simply contradictory to how the model works at a level that can't be overridden by injecting tokens.

Weak is even giving it too much credit imho, a yapping skill telling Claude to not yap can’t but fail.

I placed those instructions in setting > personal instructions, in my global CLAUDE.md, and in each project’s CLAUDE.md. I also use the concise output style in CC. If I choose a high thinking model it will start deviating in long sessions, then I just remind it in my next message:

“Remember ASD-STE100 style.

[rest of my message]”

BLUF sticks a lot easier than STE to be honest… but Claude knows what STE is, and using the “ASD-STE100 style” locution avoids the compliance issue (it’s true that strict ASD-STE100 compliance isn’t really possible, nor desired)

There's no physical reason "smartest/most capable model" should be "most yappy model". Smart people can write concisely. It's unfortunate you have to tolerate/fight yappiness to get intelligence with current SotA models.

SEEKING FREELANCER | Frontend-with-some-backend | Brussels, Belgium | REMOTE

I'm looking for a frontend developer to build a React PWA, with enough knowledge to build a PHP/October CMS (Laravel) backend as well. Healthcare sector, so you will be doing something for a good cause!

Job to be carried out between October 1st and Novembre 30th.

Must have: - 1-2 years of professional experience with React - 1-2 years of professional experience with a PHP CMS - Feeling comfortable building a PWA with backend from A to Z - Proactive attitude - Attention to details (for real, not the fake claim everybody puts in their cover letters) The workload I estimate is 20-40 hours per week for 6-8 weeks (it will depend on your experience with the tools/tech).

Will pay central european rates.

To apply send an email to [email protected] with THE FOLLOWING:

- Subject: Job Application - Link to your portfolio - Link to ONE relevant project (it doesn't have to check all the boxes, it should be somehow relevant though) - A paragraph about the project explaining ONE difficulty/challenge you encountered and how you solved it, or anything cool about the project that you enjoyed particularly - (optional) your CV

Any other type of email or application will be ignored!