Install
$ agentstack add skill-ericwang915-data-scientist-skills-kpi-framework ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
About
KPI Framework
Purpose
Design a metrics hierarchy that aligns teams and drives the right behavior.
Frameworks
North Star Metric
- Single metric that captures core value delivered to customers
- Input metrics that drive the North Star (2-5 levers)
- Example: Spotify = "Time spent listening"
AARRR (Pirate Metrics)
| Stage | Metric | |-------|--------| | Acquisition | New signups, cost per acquisition | | Activation | Completed onboarding, "aha moment" | | Retention | DAU/MAU, D7/D30 retention | | Revenue | ARPU, MRR, conversion to paid | | Referral | Viral coefficient, referral rate |
HEART (Google)
- Happiness, Engagement, Adoption, Retention, Task success
Leading vs. Lagging
- Leading: Predict future outcomes (weekly active users → future revenue)
- Lagging: Confirm past results (monthly revenue, churn rate)
Usage Examples
"Define the KPI framework for our B2B SaaS product with North Star and input metrics"
Output Format
- Metrics Hierarchy: North Star → input metrics → supporting metrics
- Definitions: Precise calculation for each metric
- Dashboard Design: How to visualize the framework
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: ericwang915
- Source: ericwang915/data-scientist-skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.