Turn words with two readings into one confirmed ask. Use when the user's words admit two readings that would build different things.
82%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Passed
No findings from the security scan
Name the readings apart, each ending in what it would build or do differently. As short as they go with nothing that tells them apart lost — plain words. Drop each reading a source in reach rules out, and name the source. Then ask the user to pick from those left; one left is the confirmed ask.
One exchange: readings out, pick back. If the user cannot pick, the words are not the problem — stop.
Take the pick as the confirmed ask and restate it. As short as it goes with nothing in the ask lost.
The ask is already concrete and the pull is to keep questioning its decisions → use interrogate skill. The user holds something no reading of their words captures → use elicit skill.
saadshahd/moo.md
c263dea
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.