| name | portfolio-aggregator |
| description | Roll up findings across many subjects into one organization-level view — top waste patterns by frequency, teams/services ranked by open high-severity findings, SCI-term distribution, and portfolio-wide quick wins. Use this skill whenever the user has findings files from multiple audits/repos/teams and asks for the big picture, an engineering-org sustainability posture, a CTO/leadership rollup, or "where should we focus first across everything". Part of Lean Agentic AI Skills; a transformer emitting a portfolio findings summary. |
Portfolio Aggregator
Transformer skill — the CTO consumer. Input: many findings files (different subjects, producers, dates). Output: a portfolio summary (structured JSON + prose) that lean-report-writer, lean-deck-builder, or lean-dashboard can render at org level.
Single audits answer "what's wrong here"; the portfolio answers "what's wrong everywhere, and what one fix pays off most times". Frequency across subjects is the signal no single audit can see.
Subject type: emit subject.type: "organization" in findings.
Aggregation procedure
- Normalize and inventory — subjects, producers, audit dates; flag stale audits (older than a stated freshness window) so the rollup doesn't present last year's posture as current.
- Pattern frequency — group findings by pattern URL / finding id family across subjects: "images without modern formats: present in 14 of 20 audited sites" is the portfolio's headline material. Counts are real; report them with the denominator always attached.
- Posture table — per subject/team: open findings by severity, quick-win count, last-audit date. Ranked by open high-severity count — with the fairness rule below.
- SCI-term distribution — where the portfolio's levers sit (mostly E? no one touching I?) — this often reveals that nobody owns scheduling/region decisions.
- Leverage list — fixes that recur across many subjects (a shared platform fix, a paved-road change, one CI template) ranked by (frequency × severity ÷ effort). The portfolio's job is finding the one change that closes twenty findings.
- Trend layer (when findings-diff outputs or dated audit pairs exist) — org-level resolved/new counts per period.
Fairness & honesty rules
More audits ⇒ more findings: never rank teams without normalizing for audit coverage and subject count, and say so on the ranking itself — otherwise the team that audited most looks worst, which teaches teams to stop auditing. Different producers have different signature densities; cross-domain comparisons (a web team vs a data team) are noted as apples-to-oranges. No composite org score — the module's no-single-number rule holds hardest exactly here, where the temptation is greatest. Methodologies are heterogeneous by nature at portfolio level: the summary carries a methodology appendix listing each source audit's scope.
Not this skill's job
Producing audits, rendering the deck/report/dashboard (consumers take this skill's output), assigning the work (findings-to-tickets per subject).
