dvy1987/agent-loom / .agents/skills/design-review
design-review
VerifiedReview a built frontend against its chosen direction, catch drift back to generic AI defaults, enforce state coverage, ethical patterns, UX heuristics, and polish, and check contrast with APCA (not the legacy WCAG ratio). Produces specific, prioritized fixes — never vibes-based feedback. Works with pasted screenshots or Playwright MCP automated capture. Load when the user asks to review a UI, audit a design, check if a frontend looks generic or vibecoded, evaluate visual quality or polish, says "review this UI", "is this design good", "audit my frontend", "does this feel like [product]", "design QA", or when frontend-design routes here. Sub-skill of frontend-design.
| File | Kind | Size |
|---|---|---|
| SKILL.md | skill md | 8.0 KB |
| references/apca-contrast.md | markdown | 2.0 KB |
| references/ethical-patterns.md | markdown | 1.7 KB |
| references/examples.md | markdown | 1.8 KB |
| references/playwright-flow.md | markdown | 3.1 KB |
| references/review-rubric.md | markdown | 5.8 KB |
| references/ux-heuristics.md | markdown | 1.8 KB |
| scripts/apca.mjs | script | 2.5 KB |
references/examples.md
View on GitHub# Design Review — Full Session Examples
Read when you need a complete walkthrough beyond the inline teaser in SKILL.md.
---
## Example 1 — SHIP with minor fixes
**Input:** Review billing settings built against DIRECTION.md "Ledger"
**Agent actions:**
1. Capture screens at 1440px + 375px (Playwright or user paste).
2. Run `scripts/apca.mjs` — 2 pairs fail on secondary button dark mode.
3. Ethical patterns pass; UX heuristics: empty state missing for invoice list.
4. Findings (max 8 prioritized):
- P0: Add empty state for zero invoices
- P1: Secondary CTA Lc 42 → target 45 (token `--muted-foreground`)
5. Write `.design/billing-settings/REVIEW.md` — Verdict: **REVISE** (2 blockers).
---
## Example 2 — APCA hard gate
**Input:** "WCAG 4.5:1 passes, ship it"
**Response:** WCAG misreads dark/thin type. Re-run APCA — body text on `bg-muted` fails Lc 68 (<75).
---
## Example 3 — State coverage gate
**Input:** Happy path looks polished
**Output:** FAIL — no loading skeleton on invoice table; no error state on payment failure.
---
## Example 4 — Direction fidelity
**Input:** Hero uses Inter; DIRECTION.md specifies GT Sectra display
**Finding:** "Swap `--font-display` per DIRECTION.md §Typography — current Inter 700 reads generic vs Ledger reference."
---
## Example 5 — Playwright capture path
**Input:** No screenshots pasted; repo has Playwright MCP
**Output:** Follow `references/playwright-flow.md` — capture login, settings, empty invoice list at 375px before scoring.
---
## Verification checklist (full session)
- [ ] Examples demonstrate SKILL.md hard rules, not generic chat
- [ ] Anti-skip or rationalization defense included where applicable
- [ ] Output artifacts or Impact Report shape is explicit
- [ ] Reader can trace input → concrete agent actions → outcome
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| rea-analysis-optimizationmorluto/reaOptimize REA providers and shared analysis workflows for agent context, latency, CPU, and memory while preserving correctness and Evidence. Use for analysis bottlenecks and cache or query design; CI/test-suite optimization belongs to rea-ci-tests-audit. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-ci-tests-auditmorluto/reaAudit REA CI and test suites for correctness, fixture drift, false passes, and measured performance; use for suite or workflow investigations and efficiency changes, rather than ordinary feature testing or a single test failure. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| rea-tool-designmorluto/reaAudit, investigate, design, or change REA investigation tools, CLI/MCP contracts, provider capabilities, and Evidence semantics. | Stars: 471k | Updated | Claude CodeCodex | Verified | Install |
| ponytail-auditDietrichGebert/ponytailQuality audit of the whole repo: bugs, security, real load, missing tests, speed, and what to delete. Most important first. | Stars: 194k | Updated | Claude CodeCodex | Verified | Install |