metric-tree-builder-38818a — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited metric-tree-builder-38818a (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
A north-star metric you can't decompose is a number you can't move. This skill breaks it into the multiplicative/additive drivers beneath it, down to metrics a team can actually act on — and points at the highest-leverage levers.
Given a top metric and a rough business model, build the full tree anyway, inferring the standard driver structure for that model and marking assumptions. Never stop at one level; push down to input metrics someone owns.
Ask for (if not already provided):
Express the top metric as an equation of its drivers, e.g.: Revenue = New customers × Avg first order + Retained customers × Repeat rate × AOV Then break each driver down a level or two, until you reach input metrics a team can directly influence (e.g. signup conversion, activation rate, email open→click, time-to-value).
Show it as an indented tree or a table:
| Level | Metric | Driven by | Owner / lever |
|---|---|---|---|
| 0 | North star | — | |
| 1 | Driver | sub-inputs | |
| 2 | Input metric | actions | team |
Note where drivers are multiplicative (a small % gain compounds) vs additive, and any that trade off against each other.
The 2–3 input metrics where a realistic improvement moves the north star most — and why (sensitivity × how movable it is).
Which input metrics aren't being measured yet but should be, to make the tree usable.
Also render the decomposition as a Mermaid flowchart so the structure is visible at a glance (it renders live in the playground and exports as PNG/SVG). North star at the top, drivers below, input metrics as leaves; keep labels short.
flowchart TD
NS[North star] --> D1[Driver A]
NS --> D2[Driver B]
D1 --> I1[Input metric]
D1 --> I2[Input metric]
D2 --> I3[Input metric]~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.