rampstackco/claude-skills / skills/comparison-tool-design
comparison-tool-design
VerifiedDesigning side-by-side comparison tools (plan-compare, product-compare, alternative-compare) that help users decide rather than just listing features. Axis selection, default-comparison logic, recommendation discipline. Honest about feature-list-dump (every feature in a row, no decision support), hidden-recommendation (biased comparison pretending to be neutral), and honest-comparison-with-guidance (genuine comparison plus opinionated recommendation) patterns. Triggers on comparison tool, plan compare, product compare, alternative compare, vs page, decision support tool. Also triggers when conversion through comparison stages is poor, when users are abandoning at the comparison step, or when a comparison tool is being scoped for the first time.
| File | Kind | Size |
|---|---|---|
| README.md | markdown | 363 B |
| SKILL.md | skill md | 16.4 KB |
| references/axis-selection-patterns.md | markdown | 4.6 KB |
| references/common-comparison-failures.md | markdown | 5.6 KB |
| references/comparison-anti-patterns.md | markdown | 5.9 KB |
| references/comparison-fatigue-patterns.md | markdown | 5.8 KB |
| references/comparison-tool-decision-criteria.md | markdown | 4.5 KB |
| references/default-comparison-logic.md | markdown | 5.6 KB |
| references/filter-and-toggle-patterns.md | markdown | 6.1 KB |
| references/honest-recommendation-discipline.md | markdown | 6.7 KB |
| references/recommendation-engine-design.md | markdown | 5.0 KB |
references/axis-selection-patterns.md
View on GitHub# Axis selection patterns
Strong axes, weak axes, the 8-12 rule.
Axes (the rows of the comparison) should be the dimensions that genuinely affect the decision. Done well, axes produce decisions; done poorly, they produce overwhelm.
---
## The decision-relevance principle
Each axis should affect the audience's decision. Axes that do not are decoration.
**The win.** A comparison tool with 10 axes covering capability, pricing, integration, support quality. Each axis materially affects whether the audience would choose.
**The fail.** Same tool with 35 axes including marketing-checkbox features. User overwhelmed; many cells provide no signal.
The discipline. Axes earn placement through decision relevance.
---
## Strong axes
Patterns that earn placement.
**Decision-relevant capabilities.** The 5-7 capabilities the audience explicitly evaluates.
**Cost dimensions.** Price, total cost of ownership, hidden costs.
**Constraint dimensions.** Capacity, scale ceilings, integrations, geography.
**Service dimensions.** Support quality, onboarding, SLA.
**Risk dimensions.** Vendor stability, security, compliance.
**Time dimensions.** Time to value, implementation timeline.
**The selection discipline.** Each axis answers "will this matter to the audience?" If no, cut.
---
## Weak axes
Patterns that fail.
**Marketing checkboxes.** Features on every option; checkmarks across the row. No signal.
**Nice-to-haves.** Features the audience does not weigh.
**Vendor-specific terminology.** Features named differently by each vendor; label confusion.
**Decoration features.** Added because brand has them.
**Generic checkmarks.** "Customer support: yes/yes/yes." Not differentiating.
---
## The 8-12 axis rule
Most production comparison tools work well with 8-12 axes.
**Why 8-12.**
- Below 8: comparison thin.
- Above 12: cognitive overload.
**Exceptions.**
- Highly technical audiences may absorb 15-20.
- Consumer audiences may tolerate 6-8.
**The over-12 trap.** Each axis beyond 12 reduces engagement.
---
## Axis ordering
Within the comparison, order matters.
**Strong order.** Most decision-relevant first.
**Weak order.** Random; alphabetical; feature-category without importance weighting.
**The first-axis discipline.** First axis should be one of the most important; users may skim past later axes.
---
## Axis grouping
When axes group naturally.
**Grouping patterns.** Capability axes together; cost together; service together; risk together.
**Strengths.** Easier to scan.
**Weaknesses.** Group dividers add visual complexity.
**When to use.** When axis count justifies (10+ axes).
---
## Axis content per cell
What each cell shows.
**Beyond checkmarks.** "Yes/no" rarely produces decisions. Numbers, descriptions, comparisons add depth.
**Examples.**
- Cost: "$X/month" not just "Yes" to "has pricing."
- Capacity: "Up to 1000 users" not just "Yes" to "scales."
- Support: "24/7 chat plus phone" not just "Yes" to "support."
The cell content discipline. Depth where decisions need it.
---
## Axis defaults
Which axes show by default; which behind toggle.
**Default-shown axes.** The 8-12 most decision-relevant.
**Toggle-shown axes.** Less critical; audience can expand.
**The hide-bias trap.** Hiding axes where brand loses; detection eventual.
**The honest-default principle.** Defaults reflect audience importance; not brand strength.
---
## Axis updates
Axes decay.
**What decays.**
- Axes that lost relevance.
- Axes that gained relevance.
- Axis content stale.
**Maintenance cadence.** Quarterly review.
---
## Axis testing
Validate axes with the audience.
**Methods.**
- User research: which axes do they consider?
- A/B test: different axis sets.
- Sales-call mining: which axes do prospects ask about?
The validation discipline. Axes are hypotheses; validate.
---
## Common axis failures
**Too many axes.** Cognitive overload.
**Too few axes.** Comparison thin.
**Wrong axes.** Audience does not weigh them.
**Marketing-checkbox axes.** No signal.
**Vendor-specific terminology.** Label confusion.
**Hidden axes where brand loses.** Bias detected.
**Stale axis content.** Pricing or features outdated.
**Axis ordering ignores importance.** First axes are not most critical.
---
## Methodology-level choices that stay in the public skill
The decision-relevance principle. Strong axes (6 patterns). Weak axes (5 patterns). The 8-12 rule. Axis ordering. Axis grouping. Cell content. Axis defaults. Updates. Testing. Common failures.
## Implementation choices that stay internal
Specific axes for specific tools. Specific cell content. Specific tooling. The team's audit calendar. These vary by team.
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: 197k | 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: 197k | 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: 197k | Updated | Claude CodeCodex | Verified | Install |