Generate idiom drills grounded in specific lines of a source file. Seeded patterns first, model eyeball fallback on no match. Grades user attempts /10 and writes outcomes to ~/.chiron/profile.json.
Set or show chiron's voice level (gentle, default, or strict). Zero-arg invocation prints the full config snapshot — voice level plus drill sizing and teaching dials — doubling as a health check. Persists to ~/.chiron/config.json across sessions.
Session-end review of recent chiron activity. Scores across 5 axes (design thinking, code quality, idioms, testing, engineering maturity) and names one concrete thing to practice next time. Read-only in v0.3.0 — does not persist scores.
Architecture Decision Records with trade-off analysis. Guides through decision context, quality-attribute scoring, and ADR generation via a domain-adapted hint ladder. Defers to CLAUDE.md or AGENTS.md.
Generate idiom drills grounded in specific lines of a source file. Seeded patterns first, model eyeball fallback on no match. Grades user attempts /10 and writes outcomes to ~/.chiron/profile.json.
Apply teach-first Socratic mentor treatment to a coding request. Questions before code, graduated hints via an L0-L4 ladder, idiom callouts. Defers to CLAUDE.md or AGENTS.md when they conflict.
Structured debugging with hypothesis testing. Observe, hypothesize, verify, fix, explain — teaches debugging methodology via a domain-adapted hint ladder. Defers to CLAUDE.md or AGENTS.md.
Compare 2-3 approaches to a coding or design decision with trade-offs and a recommendation. Teach-first framing — surfaces decision complexity rather than picking for you. For "which way should I..." questions (complements /chiron which handles "how do I..." questions). Defers to CLAUDE.md or AGENTS.md.