tasterolllisted

# Tasteroll (roll for taste, keep what sticks) Tasteroll audits what exists, asks at most three questions, fixes what is broken, then rolls valid alternatives. Lock what works; re-roll what does not. **Project constraints produce taste even when choices are random.** ## The pipeline ``` 1. AUDIT → scan what exists → mandatory findings (craft-only) 2. INTAKE → infer from context/repo OR 3-question mini-interview 3. FIX → resolve all findings (seed-independent, non-negotiable) 4. GENERATE → fresh candidates for open dimensions (context-aware) 5. ROLL → seeded pick between valid alternatives 6. LOCK → keep what works, re-roll what doesn't, converge 7. GATE → relaxed gate (readable + WCAG AA + self-contained + inert) ``` ## 1. Audit (mandatory fixes) Scan rendered surfaces, source CSS, repo files, and content. Resolve every **non-negotiable** craft finding before rolling: - **Contrast**: body < 4.5:1 or UI < 3:1 on actual surfaces - **Spacing**: no scale, arbitrary margins with no token system - **States**: interactive elements missing hover/focus/active/disabled - **Tells**: named AI slop patterns present (gradient, centered hero, 3 cards) - **Accessibility**: missing alt, unlabeled controls, broken heading order - **Structure**: missing main landmark, no skip link, no focus-visible Flag findings outside craft scope (bad copy, content gaps, broken features) and hand them off; tasteroll does not fix them. A single-word "preserve" overrides an