Design & UX Skill
Accessibility Compliance
Implement WCAG 2.2 compliant interfaces with mobile accessibility, inclusive design patterns…
$15
Design Craft
Apply a neuroscience-driven, decision-oriented UI craft methodology to any web design or…
A neuroscience-driven, decision-oriented working method for elevating any web design that feels amateur or cheap. Instead of random CSS tweaks, it treats every UI element as a behavioral task and runs a disciplined three-iteration craft loop with visual verification and WCAG contrast measurement. Turns vague 'I don't like it' feedback into surgical, evidence-backed improvements.
$15 one-time
Add to a kit → Prices include 20% VAT. · Forged on real agency work · one-time, no lock-in
- Type Skill
- Category Design & UX
- Delivery Email · instant
- License One-time
Inside the run · no black box
See the actual work before you buy it.
Not a style guide but a working method: every UI section goes through a 3-iteration craft cycle with visual verification and a self-audit after each pass. The exact loop:
- Before touching a new section, reads the audit lessons from the previous section so the same mistakes are not repeated in iteration 1, then takes a Playwright screenshot of the current state and reads the code. Working blind is banned.
- Iteration 1 starts with structural and composition craft, never surface tweaks: every element gets a neuroscience job (H1 as focal hammer, CTA as Fitts magnet, accent color as Von Restorff isolation at exactly two spots per page).
- After each iteration, takes a fresh screenshot and runs a three-question self-audit: what went wrong (HATA), what was skipped (EKSİK), which capability went unused (KULLANILMAYAN YETENEK). Findings feed the next iteration.
- Measures dark-theme contrast with a parent-chain alpha-composite calculation instead of guessing: ancestor backgrounds are blended bottom-up to find the real opaque ground, then the luminance ratio is checked against 4.5:1 normal and 3:1 large-text thresholds.
- Interprets negative feedback surgically: the narrowest possible reading, asking a clarifying question before ripping out surrounding structure, because over-correction has burned real sessions before.
- Records every technique in a decision format (trigger, technique, verification) with an evidence tag: approved techniques get reused, experimental ones used with care, rejected ones are never tried again.
One power source. 6 lines out.
design-craft · core
core active · 6 lines
- ✓ a section looks amateur
A section looks amateur or generic and you can't pin down why
- ✓ acting on design feedback
Acting on design feedback without rewriting the whole layout
- ✓ verifying dark-theme text
Verifying dark-theme text readability by measurement, not guesswork
- ✓ smoothing harsh color bo…
Smoothing harsh color boundaries between adjacent sections
- ✓ redesigning a flat, airy
Redesigning a flat, airy page into a crafted composition
- ✓ carrying craft lessons f…
Carrying craft lessons from one section into the next
Yours to keep.
Drag time forward. Watch what stays.
Forever
That's what owning means.
The rented stack
ai writing tool: subscription
expired · access lostanalytics suite: subscription
expired · access lostdesign platform: subscription
expired · access lost(nothing left)
Your forge
-
Replace guesswork with verified, screenshot-backed design decisions
license: perpetual -
Stop endless revision rounds with a bounded three-iteration discipline
license: perpetual -
Avoid over-corrections by interpreting feedback in its narrowest scope
license: perpetual -
Build a memory of approved and rejected techniques so mistakes aren't repeated
license: perpetual
subscriptions expire · deeds don't
Everything in the box.
Pick a piece up. Watch it work.
Decision-oriented technique format: trigger, technique, verification, plus an evidence tag
6 parts · one working system · ships instantly by email
This wasn't forged for everyone.
- Not for you if you'd rather rent a tool than own one.
- Not for you if you want someone else to run your stack.
- Not for you if you're happy guessing.
Designers and front-end builders who keep hearing 'this looks cheap' and need a repeatable method to make a design genuinely premium.
then this was forged for you.Works with
Universal by design: these run in any AI. Delivered in the open Agent Skills + MCP format (native in Claude); ChatGPT, Gemini, Cursor and Copilot adapt the same files their own way.
- Claude Native format
- ChatGPT Adapts via open standards
- Gemini Adapts via open standards
- Cursor Adapts via open standards
- Copilot Adapts via open standards
Catch what's on your mind.
the air is clear. nothing between you and the forge.
catch a spark: the forge will answer
-
Can I apply this to an existing site without ripping out my CSS framework?
It works element by element on whatever you already run, Tailwind, plain CSS or a component library. You point it at the section that feels off, not the entire codebase.
-
Is the three-iteration loop a hard cap, or can a stubborn section take more?
Three is the disciplined default that forces a real decision each round instead of endless tweaking. A section can run another loop, but if three rounds change nothing the problem is usually the content or layout, not the styling.
-
Will this turn a weak layout into a good one, or only polish what is there?
It elevates craft on a sound structure: contrast, spacing, type and hierarchy. It will not invent a new information architecture or rescue a section that is the wrong layout for the job.
-
How is it delivered?
By email right after purchase: ready to run, downloaded instantly, no setup wait.
-
One-time or subscription?
A one-time purchase; no subscription or hidden fees. VAT (20%) is included.
-
Can I get a refund?
As a digital product, it can’t be refunded once downloaded. That’s why we show exactly what’s inside and who it’s for, right here.