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/default-comparison-logic.md
View on GitHub# Default-comparison logic
Honest defaults vs bias-flattering defaults.
Defaults shape the user's first impression. Honest defaults reflect the audience's likely starting point; bias-flattering defaults shape conclusions in ways that erode trust when caught.
---
## The honest-default principle
Defaults should serve the audience, not the brand. When defaults must reflect brand strength, do so honestly with disclosure.
**The win.** Default comparison shows the brand alongside 2-3 commonly-considered competitors. Default axes are the 8-12 most decision-relevant. Default audience profile (if pre-selected) reflects the visitor's likely segment.
**The fail.** Default comparison shows the brand alongside the 2 weakest competitors. Default axes are the ones where the brand wins. Audience defaults assume the brand's ideal customer.
The discipline. Defaults make the comparison fair as a starting point; users can adjust.
---
## Default options
Which options compare by default.
**Audience-fit defaults.** The options the audience most commonly considers.
How to determine. Sales-call mining (which competitors do prospects mention?), referral analysis, user research.
**Stage-fit defaults.** The options that match the audience's stage.
How. Awareness audiences may compare against generic categories; decision audiences against specific products.
**Inferred defaults.** Based on referral source or query.
How. Visitor from "X vs Y" search query gets X and Y as defaults; visitor from generic landing gets default comparison set.
---
## Default axes
Which axes show by default.
**The most-critical-axes default.** Top 8-12 axes by decision relevance.
**Audience-relevant axes.** Default to axes most relevant to the inferred or stated audience.
**The hide-where-we-lose anti-pattern.** Defaulting to axes where the brand wins; hiding where it loses. Detection by analytical audiences eventual; trust damage permanent.
The cure. Defaults reflect audience importance, not brand strength. Honest about competitor strengths.
---
## Default audience or use case
When the tool asks (or infers) the audience.
**Pattern A: Pre-selected.** Tool selects an audience based on referrer or query.
Strengths. Lower friction; tool seems intelligent.
Weaknesses. Inference can be wrong.
**Pattern B: Asked upfront.** Tool asks "what is your role?" or "what is your team size?"
Strengths. Accurate; user controls.
Weaknesses. Adds friction; some audiences skip.
**Pattern C: No audience selection.** Tool shows comparison; user can filter.
Strengths. Lowest friction; works for all audiences.
Weaknesses. Generic; no per-audience recommendation.
The choice depends on the tool's complexity and the audience's diversity.
---
## Default recommendation
What the tool recommends by default.
**Pattern A: Single default recommendation.** "For most teams, [option] is the best choice."
Strengths. Clear; opinionated.
Weaknesses. May not fit all visitors.
**Pattern B: Audience-conditional default.** Recommendation changes based on audience selection.
Strengths. Fits different audiences.
Weaknesses. More complex.
**Pattern C: No default recommendation.** Tool requires user to specify before recommending.
Strengths. User commits; recommendation is matched.
Weaknesses. Higher friction.
The discipline. Whatever default, the recommendation is honest about who it is for.
---
## Bias-flattering defaults: the failure
Patterns that destroy trust.
**Defaults set for brand victory.** Comparison tool defaults to axes where the brand wins, hides where it loses.
**Defaults that frame in brand's terminology.** Other options compared in vocabulary that favors the brand's positioning.
**Defaults that misrepresent competitor pricing.** Showing competitor's most expensive plan vs brand's mid-tier.
**Defaults that show outdated competitor info.** Listing features competitors have updated.
**The audience reaction.** Sophisticated audiences notice; trust collapses; brand earns "manipulative" reputation.
---
## Honest defaults with disclosure
When the brand legitimately stands out, honest framing matters.
**The pattern.** "Default view shows the comparison most relevant to teams of [size]. Your situation may differ; use filters to adjust."
**Disclosure where defaults are brand-favorable.** "We are highlighting [axis] because we think it matters most for [audience]. Let us know if you weigh things differently."
The honest framing earns trust where bias-flattering loses it.
---
## Default maintenance
Defaults decay.
**What decays.**
- Default options no longer match audience consideration.
- Default axes no longer the most relevant.
- Default audiences shifted.
**Maintenance cadence.** Quarterly review. Update as competitive landscape and audience composition shift.
---
## Common default failures
**Hide-where-we-lose.** Bias detected; trust collapses.
**Stale defaults.** Competitor info outdated.
**Wrong default audience.** Inference produces unfit comparison for visitor.
**No default at all.** Tool requires extensive setup before showing comparison.
**Default obscures methodology.** Defaults look like neutral; methodology is biased.
**Default ignores recent competitor changes.** Defaults from 6 months ago.
---
## Methodology-level choices that stay in the public skill
The honest-default principle. Default options. Default axes. Default audience or use case. Default recommendation. The bias-flattering failure pattern. Honest defaults with disclosure. Default maintenance. Common failures.
## Implementation choices that stay internal
Specific defaults for specific comparison tools. Specific audience inference logic. 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: 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 |