Designing 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.
53
60%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/comparison-tool-design/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong, well-crafted skill description that clearly defines a specific niche (comparison tool design), lists concrete capabilities and design patterns, and provides explicit trigger guidance covering both keyword-based and situational triggers. The description is detailed without being padded, uses third-person voice appropriately, and would be easily distinguishable from other skills in a large skill library.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions and concepts: 'side-by-side comparison tools', 'axis selection', 'default-comparison logic', 'recommendation discipline', and names three distinct patterns (feature-list-dump, hidden-recommendation, honest-comparison-with-guidance). Very concrete and actionable. | 3 / 3 |
Completeness | Clearly answers both what (designing comparison tools with axis selection, default-comparison logic, recommendation discipline, and awareness of honest/dishonest patterns) and when (explicit 'Triggers on...' clause with specific trigger terms plus situational triggers like poor conversion or first-time scoping). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'comparison tool', 'plan compare', 'product compare', 'alternative compare', 'vs page', 'decision support tool', plus situational triggers like 'users are abandoning at the comparison step' and 'conversion through comparison stages is poor'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive niche focused specifically on comparison/decision-support UX tools. The combination of plan-compare, product-compare, vs page, and conversion-at-comparison-step triggers creates a clear, unique domain unlikely to conflict with general UI or product design skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
20%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill reads more like a thought-leadership essay or strategic framework document than an actionable skill file for Claude. It is extremely verbose, repeating its core thesis (honest-comparison-with-guidance > feature-list-dump/hidden-recommendation) multiple times across sections. The biggest weakness is the complete absence of concrete, executable guidance—no example comparison tables, no template copy, no sample recommendation text, no wireframes or structural examples that Claude could actually use to produce output.
Suggestions
Add concrete examples: include a sample 8-12 axis comparison table, example recommendation copy ('For teams under 50 people, choose X because...'), and a sample filter configuration to make the skill actionable rather than purely conceptual.
Cut redundancy aggressively: the feature-list-dump vs hidden-recommendation vs honest-comparison-with-guidance distinction is explained at minimum 4 times; state it once clearly and reference it thereafter. Remove the preamble about 'the voice' and the closing section that restates everything.
Add a concrete workflow with validation: instead of 12 abstract considerations, provide a step-by-step process like '1. List candidate axes → 2. Score each axis on decision-relevance (template below) → 3. Cut to 8-12 → 4. Test with 3 user scenarios → 5. Validate no all-checkmark rows remain.'
Provide the referenced bundle files or inline the most critical reference content; currently 9 reference files are cited but none exist, making the progressive disclosure structure hollow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Extremely verbose for a skill file. The content repeatedly restates the same concepts (feature-list-dump vs hidden-recommendation vs honest-comparison-with-guidance is explained at least 4 times across sections). Extensive preamble about 'the voice' and audience, explanations of concepts Claude already understands (what cognitive overload is, what trust means), and a closing section that rehashes everything. This could be cut by 60%+ without losing actionable content. | 1 / 3 |
Actionability | The skill is entirely conceptual with no concrete, executable guidance. There are no code examples, no templates, no specific commands, no sample outputs, no wireframe descriptions, no copy examples. It describes principles and patterns at a high level but never shows what a comparison tool's actual output should look like—no example axis table, no example recommendation copy, no example filter configuration. | 1 / 3 |
Workflow Clarity | The 12-consideration framework provides a reasonable checklist sequence for designing or auditing a comparison tool. However, there are no validation checkpoints, no feedback loops, and no clear 'if X then Y' decision points within the workflow. The steps are more of a consideration list than a sequenced process with verification. | 2 / 3 |
Progressive Disclosure | The skill references 9 separate reference files with clear links and descriptions, which is good structure. However, no bundle files are provided, so these references are dead links. Additionally, the main SKILL.md itself contains too much inline content that could be in reference files—the detailed sections on axis selection, default logic, recommendation engine, etc. are all expanded inline AND referenced externally, creating redundancy. | 2 / 3 |
Total | 6 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
8e70d03
Table of Contents
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.