Best use case
kpi-aggregator is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Aggregates KPIs from portfolio companies, normalizes metrics
Teams using kpi-aggregator should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/kpi-aggregator/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How kpi-aggregator Compares
| Feature / Agent | kpi-aggregator | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Aggregates KPIs from portfolio companies, normalizes metrics
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# KPI Aggregator ## Overview The KPI Aggregator skill collects and normalizes key performance indicators from portfolio companies for consolidated reporting. It enables standardized portfolio analysis despite varying reporting formats and metrics definitions across companies. ## Capabilities ### Data Collection - Collect KPIs from multiple sources - Support various input formats (spreadsheets, APIs, emails) - Handle periodic collection schedules - Track submission compliance ### Metric Normalization - Standardize metric definitions - Normalize time periods and currencies - Handle different accounting treatments - Reconcile varying calculation methods ### Portfolio Aggregation - Aggregate across portfolio companies - Calculate portfolio-level metrics - Track sector and stage segments - Compare to benchmarks ### Trend Analysis - Track metrics over time - Calculate growth rates and trends - Identify anomalies and concerns - Generate trend visualizations ## Usage ### Collect Portfolio KPIs ``` Input: Collection period, company list Process: Gather data from sources Output: Raw KPI data, submission status ``` ### Normalize Metrics ``` Input: Raw KPI data, normalization rules Process: Standardize definitions and formats Output: Normalized metric dataset ``` ### Aggregate Portfolio View ``` Input: Normalized data, aggregation parameters Process: Calculate portfolio metrics Output: Portfolio summary, segment analysis ``` ### Analyze Trends ``` Input: Historical KPI data Process: Calculate trends, identify patterns Output: Trend analysis, anomaly flags ``` ## Core KPI Categories | Category | Key Metrics | |----------|-------------| | Revenue | ARR, MRR, revenue growth, NRR | | Unit Economics | LTV, CAC, LTV/CAC, payback | | Growth | Logo growth, expansion rate | | Engagement | DAU/MAU, retention, NPS | | Financial | Burn rate, runway, gross margin | ## Integration Points - **Quarterly Portfolio Reporting**: Core data collection - **Portfolio Dashboard Builder**: Feed dashboard data - **Cohort Analyzer**: Connect to cohort analysis - **Portfolio Reporter (Agent)**: Support reporting ## Data Sources - Portfolio company reporting systems - Email-based report collection - Carta and cap table systems - Accounting system integrations - Manual data entry portals ## Best Practices 1. Establish clear metric definitions 2. Enforce consistent reporting periods 3. Validate data before aggregation 4. Track reporting compliance 5. Document normalization adjustments
Related Skills
market-research-aggregator
Market intelligence aggregation skill for synthesizing market data from multiple sources
process-builder
Scaffold new babysitter process definitions following SDK patterns, proper structure, and best practices. Guides the 3-phase workflow from research to implementation.
babysitter
Orchestrate via @babysitter. Use this skill when asked to babysit a run, orchestrate a process or whenever it is called explicitly. (babysit, babysitter, orchestrate, orchestrate a run, workflow, etc.)
yolo
Run Babysitter autonomously with minimal manual interruption.
user-install
Install the user-level Babysitter Codex setup.
team-install
Install the team-pinned Babysitter Codex workspace setup.
retrospect
Summarize or retrospect on a completed Babysitter run.
resume
Resume an existing Babysitter run from Codex.
project-install
Install the Babysitter Codex workspace integration into the current project.
plan
Plan a Babysitter workflow without executing the run.
observe
Observe, inspect, or monitor a Babysitter run.
model
Inspect or change Babysitter model-routing policy by phase.