ai-readiness-rollup

/ai-readiness-rollup

Summarise AI readiness across several subjects, using assessments that already exist.

This command is fully self-contained — it does not depend on any plugin skills, agents, sub-commands, or external services. Everything it needs is below.

Run /ai-readiness-assess first in any subject that has no assessment yet: a roll-up reads reports, it does not produce them.

---

What a roll-up is

A roll-up reads the machine-readable assessment-summary block from reports that already exist and assembles them into one portfolio view. It runs no scan, asks no behavioural questions, and writes no per-subject report.

That restraint is the design. Twelve repositories at ten minutes each, with the behavioural questions asked twelve times, is not a session anyone sits through, and a single pass over twelve repositories exhausts context long before it finishes. Reading artefacts instead of re-assessing also separates who runs the assessment from who reads the summary, which is what a consultancy engagement actually needs: each team keeps and owns its own report, and the portfolio view is assembled from what they produced.

The unit

The assessment unit is subject × governing habitat, with the cognitive read scoped to the team:

• Subject — the code artefacts under examination: a repository, a submodule, or a directory inside a monorepo.
• Habitat — the harness and control surfaces governing that subject.
• Team — the people whose behaviour produces the cognitive read. Never a repository.

What the roll-up is for

One cognitive read measured against N different habitats produces N different gaps, and the spread of those gaps is the headline finding. A team can sit Coherent in the greenfield service and deep in Ambition-outpaces-enablement in the legacy one. The enablement work those two facts imply is completely different, and a single-repository assessment cannot surface the difference because it only ever has one reading to compare.