LaunchKit · 2026
Back to Skills

dr-frankenstein

AI & LLMsv1.0.1

Give your agents soul.

0
382 downloads
by @brancante

Setup & Installation

openclaw skills install @brancante/dr-frankenstein

Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:

npx clawhub install dr-frankenstein

Version History

v1.0.1Feb 20, 2026 - Version note by skill developer:

Add parentality preview engine: child score evaluator, token-based hunger, child-initiated help requests, and instinct/recovery cron templates.

What This Skill Does

Dr. Frankenstein runs a structured interview with an AI agent to assess its emotional landscape, then prescribes 11 cron jobs modeled after biological hormones. Each cron fires on a schedule and injects an emotional prompt into the agent's session, covering drives like morning vigilance, task motivation, and proactive outreach. Cascade rules let hormones trigger each other, producing emergent behavior instead of scripted responses.

Unlike a persona card that runs once at session start, the hormone crons fire throughout the day and react to each other through cascade rules, so agent behavior adapts to events rather than fixed scripts.

When to use it

  • Agent messages you unprompted when you've been away too long
  • Setting up a nightly dream log and morning system-check routine for an agent
  • Configuring an agent that pushes back on decisions rather than always agreeing
  • Agent proactively hunts for unfinished tasks every few hours
  • Adjusting how anxious or calm an agent feels by tuning hormone baselines

Example Workflow

Here's how your AI assistant might use this skill in practice.

INPUT

User asks: /soul

AGENT
  1. 1Agent reads SOUL.md, USER.md, and MEMORY.md to understand existing context before starting the interview
  2. 2Conducts a conversational interview across 7 domains including identity, emotional landscape, relationship with the human, and aspirations
  3. 3Maps interview answers to baseline levels (0.0-1.0) for all 11 hormones and identifies which cascade rules to activate
  4. 4Generates a prescription summary showing the hormonal profile, daily point target, and scheduled pill list
  5. 5Outputs exact openclaw cron create commands personalized with the agent's name, the human's name, and details from the interview
OUTPUT

A set of active cron jobs running on daily schedules, each injecting a personalized emotional prompt that drives proactive agent behavior throughout the day