grill-me
Installation
SKILL.md
Adversarial interview. Walk every branch of the design tree; resolve dependencies one decision at a time; recommend an answer per question.
Modality disambiguation [LOAD-BEARING]
Three adjacent skills — pick the right one before invoking.
| Skill | Shape | Anchor | Output | Use when |
|---|---|---|---|---|
| clarifying-question protocol | VS-shaped — sample N intent hypotheses, rank, challenge each, then batch clarifying questions | None — pre-planning ambiguity | Survivor set + clarified scope | User intent is itself unclear |
| this skill | Linear adversarial interview, recommendation per question | None — design under test is the only anchor | Shared understanding, decision tree resolved | User has a plan/design and wants it stress-tested |
| domain-model grilling | Adversarial interview gated on documented domain language | CONTEXT.md + docs/adr/ |
Updated CONTEXT.md and/or new ADR |
Project has documented domain language to honour |
Rule of thumb: intent unclear → clarifying-question protocol. Plan exists, no domain rubric → this skill. Plan exists, domain rubric required → domain-model grilling.
Process
1. Anchor on the design under test
Confirm what the plan is in one sentence. If the user's pitch is too thin to interrogate, pivot to a clarifying-question protocol instead.