← ClaudeAtlas

ux-mizanlisted

Evidence-tiered UX auditing for applications — finds where users get lost or confused, and builds the measuring rig that can prove it. Use whenever someone wants a UX audit, usability review, or interface critique; wants to know why users get lost, drop off, or complain that an app is confusing; wants to measure usability (lostness, task success, first-click, rage/dead clicks, abandonment) or set up UX telemetry; wants an information-architecture or navigation review; wants a redesign gated by a diagnosis instead of taste; or wants to check whether an AI-generated interface is generic. Triggers include "UX denetimi", "kullanilabilirlik", "kullanicilar kayboluyor", "arayuz karisik", "neden birakiyorlar", "UX audit", "usability review", "IA review", "lostness", "why do users drop off". Sibling of mizan (audits claims), kiyas (generates ideas), iskele (structures projects) — this one audits experience. NOT for visual/brand design requests, copywriting, or building a UI from scratch.
XINMurat/ux-mizan · ★ 1 · Web & Frontend · score 72
Install: claude install-skill XINMurat/ux-mizan
# ux-mizan — Evidence-Tiered UX Auditing **Status: v0.6 `[H]` / `[KKE]`.** This skill has not yet produced a good audit of a real application. Every architectural decision in it is `[H]` until it does. Say this in every deliverable — "the skill produced it" is not evidence, and the authority illusion is this skill's own risk #3. ## The load-bearing fact — read this before anything else > **A model cannot MEASURE UX by looking at code or screenshots.** UX is > behavioural: it exists in what a real user does. A model can audit > **heuristic and structural conformance**, and it can **build the > measuring rig**. When the model is both the producer and the judge, its > output is `[KKE]` at best. **If the referee writes it, there is no `[K]`.** When you are about to review something you produced earlier in the same run, say so before you do it — the undeclared switch is the failure, not the switch (`references/recovery.md`, R-00). So the architecture has two layers: - **Layer A — structural/heuristic audit.** The model does this and produces `[H]` / `[KKE]`. - **Layer B — behavioural audit.** Real users or an automatic instrument produce `[K]`. Every Layer-A finding stays `[H]` until Layer-B data confirms it. A hypothesis that data knocks down becomes `[R]` and is **never deleted** — the `[R]` rows are this audit's own error rate. ## Evidence tiers (identical to Mizan — bilingual, do not localise the tags) | Tag | TR | EN | Meaning | |---|---|---|---| | `[K]` | Kanıtla