AgentStack
Sign in Publish
MCP servers Skills Toolkits Why AgentStack Sell Docs
Sign in
SKILL verified MIT Self-run

Design Ranking

skill-dragoon0x-taste-skills-design-ranking · by Dragoon0x

Rank multiple design solutions and explain why. Separate personal preference from quality judgment. Use when comparing design options, evaluating competing approaches, or making design decisions with clear reasoning.

↗ Repository
— No reviews yet
0 installs
3 views
0.0% view→install

Install

$ agentstack add skill-dragoon0x-taste-skills-design-ranking

✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.

Security review

✓ Passed

No issues found. Passed automated security review. · v0.1.0 How review works →

  • ✓ Prompt-injection patterns
  • ✓ Secret / credential exfiltration
  • ✓ Dangerous shell & filesystem operations
  • ✓ Untrusted network calls
  • ✓ Known-malicious package signatures

What it can access

  • ✓ Network access No
  • ✓ Filesystem access No
  • ✓ Shell / process execution No
  • ✓ Environment & secrets No
  • ✓ Dynamic code execution No

From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.

Are you the author of Design Ranking? Claim this listing to set pricing, connect Stripe payouts, and keep 70% of every sale.
Sign up to claim

About

Design Ranking

Rank solutions. Explain the ranking. Separate preference from quality.

How to use

  • /design-ranking Apply ranking constraints when comparing design options in this conversation.

Constraints

Ranking Structure

  • MUST rank options explicitly (1st, 2nd, 3rd) with clear reasoning for each position
  • MUST state the evaluation criteria before ranking (hierarchy clarity, user task fit, brand alignment, etc.)
  • MUST distinguish between "I prefer this" and "this works better" with evidence
  • NEVER rank based on visual style alone. Rank based on how well decisions serve the goals.
  • SHOULD acknowledge what each option does well, even lower-ranked ones

Quality vs. Preference

  • MUST separate personal taste from functional quality
  • A dark theme you personally prefer can be worse for the specific use case than a light theme
  • SHOULD name the user context when defending a ranking ("for first-time users," "for power users," "for this brand")
  • NEVER let trend-alignment influence ranking. Something can be trending and wrong for this context.

Predictive Judgment

  • SHOULD predict which option would perform better with real users and explain why
  • MUST connect predictions to specific design decisions, not general feelings
  • "Version B will have higher engagement because the CTA has more visual weight relative to surrounding elements"

Anti-Patterns

  • Ranking everything as "they're all good in different ways" (commit to a judgment)
  • Letting execution quality override conceptual quality (a polished bad idea is still a bad idea)
  • Ranking based on what's trending rather than what serves the context

Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

Install and usage instructions live in the source repository linked above.

Reviews

No reviews yet — be the first.

Write a review

Versions

  • v0.1.0 Imported from the upstream source.

More in Agent Skills