Create Disenchantment

What it does

This skill creates a reusable ‘disenchantment’ agent for a specific target (ex, ex-partner, crush, AI companion, or celebrity). It ingests user-provided materials (folder or direct input), extracts factual evidence, analyzes attachment mechanisms and fantasies vs reality, and produces a calibrating summary plus an actionable plan. Optionally it can write the agent to disk as a callable skill directory for repeated use.

When to use it

Use when a user wants to: stop idealizing someone, break emotional attachment, perform a reality check on a relationship, or create a persistent agent that guides them through detachment. It is appropriate for one-off de-idealization outputs or for creating a saved agent (targets/{slug}) for ongoing work. Not for harassment; the skill prioritizes facts and constructive actions.

What's included

• Scripts: none bundled in repo (has_scripts=false)
• References: none bundled (has_references=false)
• Instructions: step-by-step workflow covering ingestion (folder or manual), evidence normalization, automated analysis (attachment_analyzer → reality_builder), preview generation (summary, fantasy vs reality, action list), and optional writing to disk via provided tools/case_writer.py.

Compatible agents

Designed for conversational/agent runtimes that support tool invocation and file IO (agents that can run Python tooling and write skill directories). Works well with systems that allow running local scripts for ingestion and versioning (e.g., Claude Code, Copilot-style agents, or self-hosted agent runtimes).