Decompose a top-line metric into a quantified metric tree with mathematical relationships, size each node, and identify where the real leverage is. Use when a PM needs to understand what drives a metric, where to focus, or where NOT to focus.
67
60%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./growth-skills/skills/build-metric-tree/SKILL.mdQuality
Discovery
85%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 description that clearly articulates specific actions (decompose, size, identify leverage) and provides explicit 'Use when' guidance tied to a PM persona. Its main weakness is that trigger term coverage could be broader to capture alternative phrasings users might employ, such as 'KPI tree', 'driver analysis', or 'north star metric'.
Suggestions
Add common alternative trigger terms users might say, such as 'KPI', 'driver tree', 'north star metric', 'impact analysis', or 'prioritization framework'.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'decompose a top-line metric into a quantified metric tree', 'size each node', 'identify where the real leverage is'. These are distinct, actionable steps. | 3 / 3 |
Completeness | Clearly answers both what ('decompose a top-line metric into a quantified metric tree with mathematical relationships, size each node, identify leverage') and when ('Use when a PM needs to understand what drives a metric, where to focus, or where NOT to focus') with explicit trigger guidance. | 3 / 3 |
Trigger Term Quality | Includes some natural terms like 'metric', 'metric tree', 'leverage', 'drives a metric', 'where to focus', and 'PM'. However, it misses common variations users might say such as 'KPI', 'driver tree', 'impact analysis', 'prioritization', 'decomposition', or 'north star metric'. | 2 / 3 |
Distinctiveness Conflict Risk | The description carves out a clear niche around metric decomposition trees with mathematical relationships and leverage identification. This is specific enough to be unlikely to conflict with general analytics, dashboarding, or other PM-related skills. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
35%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 PM strategy guide than a concise skill file for Claude. It over-explains concepts Claude already understands (North Star Metrics, metric quality criteria, leverage analysis) and wraps them in a verbose prompt template. The example tree format is the strongest element, providing a concrete output pattern, but the surrounding content could be cut by 60%+ without losing actionable information.
Suggestions
Cut all explanatory text about what NSMs, OMTMs, and metric quality criteria are — Claude knows these concepts. Reduce to just the tree format example, the mathematical relationship notation ([+] and [x]), and the output format.
Add a validation step: 'Verify all child nodes sum/multiply to their parent value. If they don't, flag the discrepancy before proceeding.'
Replace the motivational language ('Be direct. Be quantitative. Challenge the user.') with a concrete example of a completed leverage analysis showing the actual math comparison between two nodes.
Consider extracting the metric quality criteria checklist into a separate reference file to keep the main skill lean and focused on the tree-building workflow.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose, explaining concepts Claude already knows well (what a North Star Metric is, what metric quality criteria mean, what leverage analysis is). The prompt template alone is ~500 words of instruction that largely describes PM strategy concepts Claude is already fluent in. Phrases like 'This is non-negotiable' and 'Be direct. Be quantitative.' are motivational padding, not actionable guidance. | 1 / 3 |
Actionability | The skill provides a structured prompt template with a concrete example tree format and specific steps, which is somewhat actionable. However, it's essentially a prompt to paste rather than executable code or commands. The example tree is helpful but the overall guidance is more descriptive than prescriptive — it tells Claude what to think about rather than giving copy-paste-ready artifacts or tooling. | 2 / 3 |
Workflow Clarity | The five steps are clearly sequenced and logically ordered (establish hierarchy → decompose → size → validate → identify levers). However, there are no validation checkpoints or feedback loops — no guidance on what to do if the math doesn't add up, if nodes don't sum to parents, or how to handle missing data beyond 'estimate.' The output format section lists deliverables but doesn't include verification steps. | 2 / 3 |
Progressive Disclosure | The content is a monolithic wall of text with no references to supporting files. The Tips section mentions 'craft-experiment-design' as a related skill, which is a useful cross-reference. However, the lengthy prompt template could benefit from being separated or the detailed metric quality criteria could be in a reference file. For a skill with no bundle, the inline content is overly long. | 2 / 3 |
Total | 7 / 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 | |
221ffaa
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.