deep-kiss

Use when the user invokes /aftercare to capture lessons from a just-fixed mistake or to retrospectively review a session for skill/memory candidates. Dispatches two stages of subagents — Stage 1 judges candidates against 4 criteria (recurrence/generalizability/proceduralization/trigger-clarity), Stage 2 drafts the artifact (skill bundle or memory-file entry). User-explicit invocation only; do NOT trigger automatically. Do NOT use for in-progress debugging — only after a mistake is fixed.

Use when the user invokes /afterglow to retrospectively scan the current project's past Claude Code sessions for repeated user corrections or workflow patterns. afterglow is an analyst: it surfaces patterns with verbatim evidence and offers to hand selected candidates to aftercare for capture. afterglow itself does NOT decide bucket, draft skills, or write files. Project-scoped. User-explicit invocation only; do NOT trigger automatically.

You MUST use this before any creative work — creating features, building components, adding functionality, or modifying behavior. Explores intent and presents YAGNI/KISS-locked options (4 axes, 5-slot structure) optimized for low-parameter models. F.L.I.R.T. = Find intent, List axes, Iterate options, Refine slots, Test-spec — the non-committal exploration phase before deep-kiss.