ワンクリックで
design-review
Post-deploy visual review of the live application. Catalog UX issues, run contrast checks, and log findings to the spec.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
メニュー
Post-deploy visual review of the live application. Catalog UX issues, run contrast checks, and log findings to the spec.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Safe, project-wide remediation of a dangerous or incorrect code pattern using structured search and replace.
Run a multi-faceted code review on uncommitted changes using specialized review subagents.
Create an Architectural Decision Record (ADR) to document a design choice or technical strategy.
Run a multi-faceted code review on uncommitted changes using specialized review subagents.
Commit (if needed), push the current branch to origin, and generate a pull request description in the chat.
Generate a session handoff document capturing the current working state for the next session.
| name | design-review |
| description | Post-deploy visual review of the live application. Catalog UX issues, run contrast checks, and log findings to the spec. |
| metadata | {"author":"cascadian-gamers","version":"1.0"} |
Post-deploy visual review of the live application. Catalog UX issues, run contrast checks, and log findings to the spec.
After any deploy that changes UI — CSS, templates, layout, components. Especially after CSS framework migrations.
Check each major page/route in the deployed app:
For each page, evaluate:
For any color pairing that looks questionable, run the contrast calculation:
python3 -c "
def luminance(h):
r,g,b = int(h[1:3],16)/255, int(h[3:5],16)/255, int(h[5:7],16)/255
def a(c): return c/12.92 if c<=0.03928 else ((c+0.055)/1.055)**2.4
return 0.2126*a(r)+0.7152*a(g)+0.0722*a(b)
def contrast(c1,c2):
l1,l2=luminance(c1),luminance(c2)
if l1<l2: l1,l2=l2,l1
return (l1+0.05)/(l2+0.05)
print(f'{contrast(\"#TEXT\", \"#BG\"):.1f}:1')
"
WCAG AA minimums: 4.5:1 for normal text, 3:1 for large text and icons.
Log each issue to the spec under a "Post-Deploy UX Issues" section:
### Issue PN: {Short description}
**Severity**: 🔴 Must Fix / 🟡 Should Fix / 🟢 Nit
**Problem**: {What's wrong and why}
**Design**: {Proposed fix with specific CSS/HTML changes}
**Files**: {Which files to modify}
Create a summary table sorted by severity:
| Issue | Description | Effort | Priority |
|---|
Group related issues (e.g., "all tables need cards" is one issue, not 5). Identify root causes — one fix may resolve multiple symptoms.
After identifying all issues, reassess with the design-frontend skill: