Defines right metrics using North Star framework, AARRR, and leading vs lagging indicators. Use when choosing metrics, instrumenting products, creating dashboards, or distinguishing vanity metrics from actionable ones.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 well-crafted skill description that excels across all dimensions. It uses third person voice, names specific frameworks (North Star, AARRR), includes an explicit 'Use when...' clause with multiple natural trigger scenarios, and carves out a distinct niche in product metrics methodology that won't conflict with general data or analytics skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'Defines right metrics', 'using North Star framework, AARRR, and leading vs lagging indicators' - names specific methodologies and frameworks rather than vague language. | 3 / 3 |
Completeness | Clearly answers both what (defines metrics using specific frameworks) AND when with explicit 'Use when...' clause covering multiple trigger scenarios: choosing metrics, instrumenting products, creating dashboards, distinguishing metric types. | 3 / 3 |
Trigger Term Quality | Includes natural keywords users would say: 'metrics', 'dashboards', 'vanity metrics', 'actionable', 'instrumenting products', 'North Star', 'AARRR' - good coverage of both common terms and domain-specific vocabulary. | 3 / 3 |
Distinctiveness Conflict Risk | Clear niche focused on product metrics and measurement frameworks - distinct triggers like 'North Star', 'AARRR', 'vanity metrics', 'leading vs lagging indicators' are unlikely to conflict with general analytics or dashboard skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured, concise skill that effectively presents metrics frameworks without over-explaining concepts Claude already knows. The main weakness is that it's more of a reference template than actionable guidance—it tells Claude what good metrics look like but doesn't provide concrete decision-making processes or validation steps for choosing and iterating on metrics.
Suggestions
Add a concrete decision tree or process for selecting a North Star metric (e.g., 'Ask: Does this metric X? If no, consider Y')
Include a validation step: how to verify chosen metrics are actually measuring what matters (e.g., 'After 2 weeks, check if North Star movement correlates with business outcomes')
Add a brief example showing the difference between a vanity metric and an actionable one in a specific scenario, not just definitions
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and efficient, presenting frameworks and templates without unnecessary explanation. Claude already knows what metrics are; this skill focuses on the specific frameworks and actionable templates. | 3 / 3 |
Actionability | Provides a useful dashboard template and checklist, but the guidance is more structural than executable. The examples are illustrative rather than showing how to actually implement tracking or make metric decisions in specific scenarios. | 2 / 3 |
Workflow Clarity | The checklist provides a sequence (Choose Metrics → Implement), but lacks explicit validation steps or feedback loops. No guidance on what to do if metrics aren't working or how to iterate on metric selection. | 2 / 3 |
Progressive Disclosure | For a skill of this scope (~80 lines), the content is well-organized with clear sections. No external references needed; the structure with frameworks, templates, and quick reference is appropriate and navigable. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
53530ef
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.