borghei/Claude-Skills / engineering/interface-refinement
interface-refinement
VerifiedRefine an existing interface with named commands (critique, polish, distill, typeset, colorize ...), a product and design context file, and a static detector of generic UI patterns. Use when UI looks generic, cluttered or unfinished.
assets/refinement-report-template.md
View on GitHubMethod: (two assessments (A: design review, B: detector) | single context: reason)
# Critique: (surface) — (date)
Target: (file path or route) · Mode: (persuade | operate | read | showcase) · Context file: (path | none)
## Specificity verdict
**Design review (A):** (could another product ship this unchanged? which choices are interchangeable,
which belong only to this product)
**Detector (B):** (N findings: X high, Y medium, Z advisory; top rules with file:line; false positives
named with the reason)
## Heuristic scores
| # | Heuristic | Score | Evidence |
|---|-----------|-------|----------|
| 1 | Visibility of state | | |
| 2 | Match with the real world | | |
| 3 | Control and freedom | | |
| 4 | Consistency | | |
| 5 | Error prevention | | |
| 6 | Recognition over recall | | |
| 7 | Flexibility | | |
| 8 | Minimal design | | |
| 9 | Error recovery | | |
| 10 | Help | | |
| | **Total** | **(sum) / (4 x scored)** | |
## What works
1. (specific element and why it works)
2.
## Priority issues
| P | Issue | Why it matters | Fix | Command | Evidence |
|---|-------|----------------|-----|---------|----------|
| P1 | | | | | file:line |
## Persona red flags
- **(Persona):** (what broke for them, by element)
## Minor observations
-
## Plan
Validated with `command_router.py --plan plan.json`: (PASS/FAIL)
1. (command) — (target) — changes: (...) — keep: (...) — verify: (...)
2. polish — (target)
## Question for the owner
(Which issue should be fixed first, or the one decision only the owner can make.)
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| brainstormingobra/superpowersYou MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation). | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| brand-guidelinesanthropics/skillsApplies Anthropic's official brand colors and typography to any sort of artifact that may benefit from having Anthropic's look-and-feel. Use it when brand colors or style guidelines, visual formatting, or company design standards apply. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| frontend-designanthropics/skillsGuidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |
| mcp-builderanthropics/skillsGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK). | Stars: 198k | Updated | Claude CodeCodex | Verified | Install |