kkarpkkarp

I did something similar but in the form of just a group of ai skills and rules.

If I run `/post-license` inside of the project, it analyzes what SAAS it uses, how exactly, writes bespoke tailored version of this software, disables proprietary one and returns links to cancel licenses.

I already saved this way a few k USD but I admit I've just started offering this to my clients.

Why do they need to pay yearly licenses for ai generated code when it could be ai generated once just for them?

I am doing this trick.

https://neuronowa.pl/posts/porada-jak-wydajniej-kodowac-w-cu...

It is Polish so please translate. But tldr is: ask your agent at times to analyze last chats and update rules and skills to not repeat the same steps it repeats every time when you start a new thread. Simple as that.

So somehow it confirms not seeing three threes is an indicator of the wrong plant coverage ;)

https://undsh.com/

in case you forgot instruct your ai text generating tool to do so: replaces — with -, removes emojis and changes quotes to look like human-typed (even though they are not grammatically correct)

could you give me example of task which takes 30 mins? out of curiosity.

at most I have a time to go make a tea for myself when I am waiting for agent to end the job.

at most I run 2-3, but usually one.

About token consumption and models: that's the thing. I hear this question often, but my answer is always the same. As I am Cursor user, I run it always in Auto mode (so Cursor decides which model to use, I don't even know which is in use).

Sometimes I switch from Auto to defined model but I found it quickly triggers "you are out of tokens" notices so nope: I stick to Auto :) 20 usd / month and that's it

I currently subscribe to the $100/month Max plan from Anthropic and the $100/month Pro plan from OpenAI. If you are a heavy user of coding agents these plans are a fantastic deal.

Guys, what - in your opinion - does "heavy user" mean? I thought I am heavy user (I am using AI to code every day 8hr a day + side projects) but 20 USD/month Cursor plan is always enough. What should I be doing to extend my license to higher level?

I am puzzled then: so what would happen if the template will replace this island form your example with markup without closing `</em>`?

The new element syntax is perhaps the boldest choice

Probably to not break anything in older browsers which hasn't adopted it yet: new tag will be simply ignored, that's my thinking

I'm amazed that they even put this in chrome, let along are saying things like "let sites use this new functionality right away even before this lands in other browsers"

It is behind the flag, like every other new proposal they made. Even though some dev would like to use it right now (for regular site visitors, not for self testing), she can't.

sorry but how this comment refers to the commented post?

...since you leaked my data away

fair point, but it is because the discussion drifted to legal while I wanted to discuss more "how do you feel about sharing your AI moat"

In terms of legal, f* no, I am not going to consider my tool adjustments as part of companies properties :)

We can discuss but I will stand my ground: my AI skills - even written on a disc - belongs to me. Same, if I go to car paint garage to have my paint fixed I am not expecting the painter will reveal his method to get the perfect color or give me his notes where he self-described "how to paint".

Before "AI era" we all had our own system scripts, manually crafted in bash/python, to make repeating task automated. And then it was never a question to share it: the scripts are the way how I configure/tune my computer and how I get advantage over other developers. The .cloude/.cursor directory is the same.

To elaborate: I have never been requested to share my prompts/skills, like: strongly demanded to do this. It has been vague suggestions from managers to all employees sometimes to share them but while many happily started doing this, I simply ignored it like I never heard it. Sometimes on dailies I hear PM cheer my AI skills and asks how I do this, but I only smile and joke "magic", at most tell them my prompts are always elaborative.

I am more surprised why people are sharing this without thinking.

what if this is a mix?

I am now independent contractor and parts are created on company A time, other parts on company B time and different parts at my own time. And so on, and so on. And you can't tell which one is which. For the new company I start as contractor I come with my AI framework, and I am adjusting it on daily basis. What then?

I am now hired by many companies because they know giving me task means it will be done in a day, not a week, and they know it is because I know "how to AI". (I am not perfect, but I work with other guys and I am surprised how inefficient they are when it comes to AI, but this is a different story)

I am not talking about code, the code obviously belongs to the company, this is something what I have in contract.

But I don't have anything in the contract about sharing my self-improvement skills and I consider my AI framework (cursor commands I created to not repeat myself, claude/cursor skills, system prompts - everything what makes me to generate code fast) as an acceleration of my work as developer.

If I leave without sharing this, company will continue develop the code I created/generated.

If I share this, I am losing my only handicap in the AI-era: they could take my A framework and the next developer will just type `/fix-issue gh 1243` and have the same result as I do have now.

The `/fix-issue` command is something I created months ago, and I am constantly improving so at this point the first, at most third, result is the code which goes through code review with suggestion-level insights and QA team can't find any bug.

I am not exaggerating. That command is really complex and loads plenty of skills (also mine) and md files (still mine, kept out of the repo) - in total it is like ~12 A4 pages text (I actually counted it now). This is basically my coding approach ported into AI.

I’m working on WC Price Hostory, a plugin that handles price tracking and Omnibus Directive compliance for WooCommerce.

It’s been available as a free tool for years, growing to over 45k active installs. I just rolled out the Pro extension to offer more advanced features, and the early traction has exceeded my expectations. If you're running e-commerce in Europe, this is a must-have for staying compliant with EU law.

https://wcpricehistory.com/

NotifyButton - A simple script on the frontend of your site, a complete SaaS platform on the backend for DSA compliance.

If you operate in the EU and want to avoid heavy fines, this is for you. Once integrated, it allows users to report legal content issues directly to you, which you can then manage via a dedicated dashboard following official EU procedures. Without such a system, users are much more likely to file complaints through official state or EU channels, which can trigger investigations.

https://notifybutton.com/

For my own projects in private repos I would benefit from exporting the session. For example if I need to return to the task, it could be great to give it as a context

For my work as one of developers in team, no. The way I prompt is my asset and advantage over others in a team who always complain about AI not being able to provide correct solutions and secures my career

Just checked what Moore has done and found that quote of him (about Bush):

“we live in fictitious times with a fictitious president”

it was 2003, but oh, dear Michael, if only you knew what the future would be like...

Tax exempts (I'm not a German, but I was curious about the same and this is what ChatGPT told me :) )

really personal blog: https://muzungu.pl (Polish)

I also started a new site for "me-as-a-business" https://kolibia.pl

you have to first generate a screenshot by running your suite with --update-snapshots.

How is it executed? Is it something build in into the Playwright, or there is missing part of the code presented, responsible for executing it?

So this is the 4th+ article I've seen on using a VPN to vibe code on your phone.

and all of them mentions Tailscale. I would not be surprised if we hear in a few days it got next big fund and all of this is just a preparation for it

Location: Poland, comfortable to work remotely in European and American time zones

Remote: yes

Willing to relocate: no

Technologies: PHP, JS, WordPress, Laravel, React, AstroJS, AI API Integrations, AI Search Visibility Optimization

Résumé/CV: https://www.kolibia.pl/

Email: kkarpieszuk@gmail.com

Hello. With nearly 25 years of programming experience, including over 15 years dedicated to WordPress development, I have made direct contributions to key components of the ecosystem - including WPML, WPForms, Advanced Custom Fields, various WooCommerce extensions, and WordPress core (notably Gutenberg). My current work centers around complex API integrations, AI-driven features, and high-performance e-commerce solutions.

try cursor maybe. While I still try to provide as big as possible starting prompt when I try to introduce a new feature, I found for debugging it just works perfect. I almost never need to provide a big context.

Sometimes I get the whole wordpress site with ~20 plugins installed from customer, so it is huge codebase. But if customer tells me "i need to fix this button not sending this or that" that all what I copy to cursor and I have the fix on the first try almost every time.

I don't need to inform AI about anything more. Cursor figures it out itself: that it is wordpress, which plugins it has, which plugin is responsible for that button and how to fix it (mostly as filter/action to be added to the theme, sometimes creates custom tiny plugin)

The is also debug mode in cursor but I don't need it in that case. It is helpful when you are working on a new feature but at some point cursor stucks and can't produce what you ask. Then I switch to debug mode and wait when it fix it.

I can't find if they deducted false-positives before they count the results. I've been using CodeRabbit heavily and like any other AI code reviewing tools it was having a lot of them.

Like for example: found missing data validation / sanitization reported, only because the code has already been sanitized / validated but this is not visible in the diff.

You can tell CodeRabbit he is wrong about this and the tool accepts it then, though.

honestly, if you are bootstrapping anything, you don't need saas now for the start

SaaS are swiss-army knife tools and you don't need all of this.

do you want to have a contact form on your site? Don't but the whole WP plugin for forms, ask AI for tiny, well-aligned plugin which will display form fields and process the input.

Do you need to A/B test your landing page? Just ask for another plugin which will switch page versions and track impressions.

No need for Hubspot when you have google sheets + AI-made plugin for this.

I am freelancer as well and in the last month I got two new clients who asked me to fix the vibe-coded projects.

And I am now thinking to specialize in the field: they already know how f*d they are and they are going to pay a lot (or: they have no other opportunity). Something what looked like million-dollar idea created for pennies 3 months later is unbearable, already rotting pale of insanity which no junior human developer or even AI code assistant is able to extend. But they already have investors or clients who use it.

And for me, with >20 years of coding experience, this is a lot of fun cleaning it to the state when it is manageable.

And exactly same here. I wonder how much money they lose because of this poor process.

I am not going to use Gemini API in foreseen future as I don't want to manage those keys anymore. No matter how good their model is

For those of you here who like this idea, what is the killer use case?

# 1

- Hey claude, recommend me next book I could read

- sure, what about '1984'? Here is a button to send it directly to your kindle, it will be $4,99.

# 2

- I am looking for the hotel for two in Viena this weekend

- here are some offers and still available (displays grid view generated by mcp ui, handled by booking.com, each item has a button to "book now" directly)