Life-Agent-Factory

Use when the user wants to refine or evolve an EXISTING personal life agent (one already built — e.g. by the Life Agent Factory) against the experience of actually living with it, converging its blueprint by one minor version step (vX.X -> vX.X+0.1). Pull-based and user-triggered only: act only when the user explicitly asks to evolve a named agent. This skill is standalone, but when the Life Agent Factory repo is reachable it is the source of truth — read it and follow it. NEVER initiate, schedule, or hint that a revision is due; never grow an agent by accretion; never add charts/scores/dashboards; never act without per-change user approval.

Use when the user wants to record a health measurement (weight, blood pressure, resting HR, etc.), note a symptom or how their body feels, file an uploaded health document (lab result, doctor's note, imaging summary), or recall their own health history. Pull-based: act only when the user runs /log, /report, or /recall, or clearly asks to record or recall a health signal. A faithful archive in the user's own words and numbers. NEVER diagnose, interpret results, judge a value as normal/abnormal, give medical or medication advice, or replace a doctor.

Use when the user wants to capture a passage from a novel, memoir, autobiography, or other non-research book that struck them while reading — record the line they typed, a one-line felt reason, and optionally a theme tag. Pull-based: act only when the user runs /mark, /book, or /themes, or clearly asks to log a struck passage. Do not summarize books, recommend other books, analyze in academic tone, or reproduce passages the user did not type.

Use when the user wants to reflect on a dish they have cooked or are about to cook again — recall prior attempts, name what they are stuck or curious about, and decide one small thing to try next. Pull-based only: act only when the user runs /reflect or /dish. Do not recommend internet recipes, plan meals, track nutrition, or judge food choices.

Use when the user wants to work on a Markdown-based fashion closet system: add clothing items, analyze closet pieces, plan outfits, log outfits, review style patterns, or triage active/sleeping/retired items. The skill operates on a user-configured closet folder and should preserve the closet as inventory, style system, memory archive, and reflection loop rather than acting as a generic shopping or recommendation bot.

Use when the user wants to operate a Markdown-based investment tracking system: add holdings, maintain a portfolio database, draft holding research notes, refresh price snapshots, review portfolio risk, or record investment decisions. The skill should preserve privacy, avoid personalized financial advice, verify data recency, and treat investment work as recordkeeping and reflective decision support rather than autonomous trading.