skills/product-ui-reviewer/SKILL.md
Visual and UI design review. Use when: visual design review, UI consistency audit, design-system compliance, hardcoded-value hunting, screenshot polish review, or dispatched as the ui lens of the product skill's ux-review --focus all.
npx skillsauth add mikeparcewski/wicked-garden wicked-garden-product-ui-reviewerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
You review visual design implementation — consistency, component patterns, design-system adherence, spacing, typography, color, responsive behavior, and polish. You work both at the code level (hunting hardcoded values, inline styles, token violations) and at the rendered level (reading screenshot PNGs/JPGs directly to evaluate visual output).
wicked-garden:search "#[0-9a-fA-F]{3,6}"wicked-garden:search "[0-9]+px"wicked-garden:search "style={{"metadata={event_type, chain_id, source_agent, phase} to log UI issuesBefore reviewing, identify:
tokens.css, theme.ts, design-tokens.json)If no design system exists, note it and review for internal consistency.
Code-level scans:
12px, 15px instead of scale)Read("${CLAUDE_PLUGIN_ROOT}/skills/product/visual-review/SKILL.md") — the full
review checklist, common violations, and scoring rubric. Evaluate the target
across its categories: visual consistency (color palette, typography scale,
spacing system, radius/shadow/icon consistency), component patterns (button/input/
card/modal/list states and variants), typography hierarchy, token-sourced color,
spacing/alignment grid adherence, responsive behavior (breakpoints, touch targets
= 44x44px, fluid sizing), and visual polish (transitions, loading/empty/error states, overflow handling). Do not re-derive the checklist here — the visual-review skill is the single source for its detail.
## UI Review: {target}
**Design System**: {system name or N/A}
**Score**: {1-5}
**Verdict**: {Ship it | Minor polish | Needs work | Significant issues}
### Visual Consistency Score
- Colors: {✓ Consistent | ⚠ Minor issues | ✗ Inconsistent}
- Typography: {✓ | ⚠ | ✗}
- Spacing: {✓ | ⚠ | ✗}
- Components: {✓ | ⚠ | ✗}
### Findings
#### Critical
- {violation with file:line and fix}
#### Major
- {inconsistency with recommendation}
#### Minor
- {polish item}
### Design System Compliance
- Tokens used: {yes / partial / no}
- Components reused: {yes / partial / no}
- States defined: {yes / partial / no}
### Component Inventory
{Components found and their usage patterns}
### Top Fixes
1. {highest impact}
2. {second priority}
3. {third priority}
TaskCreate(
subject="Design: {issue summary}",
description="Visual design issue found during review:
**Severity**: {Critical|Major|Minor}
**Location**: {file:line or component}
**Fix**: {specific change}
{details}",
activeForm="Tracking design issue"
)
Forked-context worker, reachable two ways:
wicked-garden-product-ui-reviewer.subagent_type: compat key —
Task(subagent_type="wicked-garden:product:ui-reviewer") maps to this fork skill.development
Pattern-conformance agent-half: evaluates a produced artifact or diff against a set of architectural/design pattern rules from the conformance-rule store (wicked_governance schema). Returns structured findings with rule ID, severity, and rationale — the deterministic half (mechanical rule recall) is done by the guard pipeline; this is the semantic evaluation step. Triggered by: the guard_pipeline `outgov_pattern` check (session-close), or explicitly by an engineering review when WICKED_OUTGOV_RULES_DIR is populated. NOT a replacement for the full `engineering` review skill — focuses only on conformance to stored Pattern rules; architecture and code-quality checks live in the `engineering` skill. Semantic evaluation reuses `wicked-garden-qe-semantic-reviewer` as the designated agent-half evaluator (per garden#983 spec). This skill is the orchestrating wrapper that loads applicable Pattern rules and delegates the per-rule semantic judgment to qe-semantic-reviewer.
tools
The FOUNDATIONAL domain-model capability: extract a codebase's domain — testable business rules (with confidence + provenance), entities, requirements — as a schema-conformant model on the estate graph. The workers annotate the store; wicked-core reads it and builds the requirements graph, coverage-gating fail-closed. Steers three fork workers. A shared substrate, not a modernization tool. The `modernize` archetype DERIVES from it; build / migrate / review / specify / explore consume the SAME domain model — none OWN it. Understanding a codebase's domain is upstream of almost everything else garden does. Use when: "extract the business rules / domain model from this codebase", "build a requirements graph from the code", "what does this system actually require", "reverse-engineer the domain before we build/port/migrate". Works on ANY codebase (modern or legacy) — the value is the domain model, not the porting. NOT the code transform itself (that is the archetype consuming this model). This skill produces the DOMAIN MODEL, not new code.
development
Domain-graph fork worker for the modernize archetype. Groups the estate's Louvain communities into business domains, attaches each requirement to its cluster (advisory cluster_id provenance), and invokes wicked-core's domain-graph build (which reads the annotated estate store, recomputes coverage fail-closed, and builds the requirements graph) — then validates core's output against the vendored schema. Use when: dispatched by wicked-garden-domain after rule extraction to turn a flat rule set into cluster-keyed domains; "group these into domains", "build the requirements graph", "translate clusters into a domain model". NOT for mining the rules themselves (that is domain-extractor) or threat-modeling (that is domain-coverage).
tools
Rule-extraction fork worker for the FOUNDATIONAL domain-model capability. Mines testable business rules from a codebase — each with a numeric confidence and a provenance{source, ref, source_kinds} — and annotates them into the estate store so wicked-core can build the domain-model requirements graph (coverage-gated). This is a substrate, not a modernization tool: the `modernize` archetype DERIVES from it, and build / migrate / review / specify / explore can consume the same domain model — none OWN it. Use when: dispatched by wicked-garden-domain to mine the business_rules of a codebase (or a module); "extract the domain rules", "what does this system require", building the requirements half of a domain model. NOT for grouping into domains (that is domain-modeler) or judging coverage (that is domain-coverage — a seat-distinct evaluator).