build
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
Sharpen a fuzzy idea into §G/§C before spec. Calibrated interrogation, one question at a time.
> /plugin marketplace add JuliusBrussee/cavekit > /plugin install ck@cavekit-marketplace
How it fires
How this command gets triggered: by you, by Claude, or both.
/grillContext preview
What this command does when you run it.
Sharpen a fuzzy idea into §G/§C before spec. Calibrated interrogation, one question at a time.
description: Sharpen a fuzzy idea into §G/§C before spec. Calibrated interrogation, one question at a time. argument-hint: [idea | "grill me"]
Invoke the **grill** skill (`skills/grill/SKILL.md`). Treat `$ARGUMENTS` as the idea to interrogate. Calibrate pressure, climb the question ladder one question at a time with a recommended answer each rung, and hand the sharpened §G/§C to the spec skill. Park unresolved unknowns as `?` items — never guess a constraint.
Frozen — compressed spec-driven development plugin for Claude Code. Still works; active development moved to JuliusBrussee/caveman.
Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.
Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.
Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.
Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.