grill-ai-mastery
Installation
SKILL.md
Probe AI mastery by what the subject names, not by how much they generate. The premise from the chat that prompted this skill: token usage and LOC are noise; concrete tip vocabulary (URL-as-entity-ref, loop closure, observability) is signal.
Mode disambiguation
| Skill | Anchor | Posture |
|---|---|---|
grill-ai-mastery |
AI-collab tip vocabulary tree (this file) | Hybrid: collaborative → adversarial |
grill-me |
Any plan/design under test | Linear adversarial, recommendation per question |
request-refactor-plan |
A refactor in particular | Adversarial interview specific to refactoring |
This skill is the AI-mastery anchor; grill-me is the domain-agnostic version. Pick by what's being assessed.
Phase 1 — Collaborative tip-sharing
Open by asking the subject to name a tip they actually use when collaborating with an LLM. Two-way: surface one of yours back as a counter-tip. The exchange is the assessment, not a quiz. Watch for:
- Concrete protocol names (URL-as-entity-ref, AGENTS.md, MCP resources, structured outputs) versus generic platitudes ("I write good prompts").
- Direction-of-travel signals — does the subject describe loops, observability, anchored references? Or do they describe vibes, screenshots, "the function we discussed"?
- Self-correction — when the subject reaches for a vague handle, do they catch themselves and produce a URL?