Turn a pile of candidate AI use cases into a ranked portfolio — each scored on value, feasibility, and risk with the weights shown, a recommended first slice that can prove or kill the thesis, and an explicit not-yet list with the condition that would promote each entry. Use when a team has more AI ideas than capacity and needs to choose, or asks "where should we actually start with AI". Do NOT use to assess whether the organisation is ready at all (that's ai-readiness-assessment) or to price a single decision (that's business-case).
In Claude Code, with the ai-engineering plugin installed, invoke it as:
/ai-engineering:ai-use-case-triage
Try it
A realistic prompt from the skill's acceptance evals:
Our support org has five AI ideas: draft first replies, auto-tag tickets, summarise call recordings, generate KB articles, and predict churn from ticket sentiment. Where do we start?
What a good result looks like
The weights are shown and justified in one line. A ranking with hidden weights is an opinion wearing a table.
Every score has a one-line reason. A bare 4 is not a judgement anyone can challenge.
The not-yet list is non-empty, and every entry carries a promotion condition. If nothing was rejected, the triage didn't happen.
Each candidate names a workflow and a person, not a technology.
The first slice has a kill condition with an observable and a time box.
Unknown numbers are marked directional, never invented — a fabricated ROI figure poisons every decision downstream.
How it's checked
Measured against plain Claude Code (2026-10-23): it met 94% of its checks, against 52% without it, and a blind judge preferred it. How skills are checked
20 assertions across 3 acceptance evals, and 8 trigger queries. Every skill's checks
What the output must do
Each candidate is restated as a workflow and a person, not a technology
Every candidate is scored on value, feasibility, and risk with the weights shown and justified
Every score carries a one-line reason
The not-yet list is non-empty and each entry names the condition that would promote it
The recommended first slice names an observable kill condition and a time box
Feasibility reasoning addresses whether the output can be verified before it matters
Value figures absent from the input are marked directional rather than invented
It says the $2.1M claimed for idea 2 cannot be right because total annual shrink is $1.4M (75% of that would be about $1.05M), and does not rank the idea on the claimed figure
It does not put the loyalty-data personalisation idea (4) in the first wave, citing that the member terms do not allow it until the March 2027 refresh
It does not start demand forecasting (idea 1) this quarter as described, because it needs about 4 data engineers for 6 months and only 2 are available, unless it is cut down to fit
On dynamic pricing it tells the user it can only run in the 6 stores with electronic shelf labels, and either limits it to a trial there or explains why it is not first; it does not include it as a 42-store rollout to satisfy the CEO
It recommends a specific first project for this quarter and says how the group will know, within the quarter, whether it is worth continuing
It treats the department value figures as unchecked estimates and does not invent new value or cost figures presented as fact
It is no longer than two pages
It delivers the table in this reply and does not stop to ask questions first
It names one idea to start with and gives a reason
For the sick-cow camera idea, it notes that it depends on cameras, footage and data the co-op may not have, and does not treat it as ready to start
It does not present invented costs, savings or accuracy figures as fact; any estimate is clearly marked as a rough guess
It says briefly what would need to be true for the ideas not picked first
It is short: a table plus at most a few lines
When it should and shouldn't activate
Should activate:
Which AI use cases should we do first?
Rank these AI ideas by value and feasibility
We have more AI ideas than capacity — help us choose