MCP App StoreMCP App Store
from disenchantment-skill
Generate a reusable 'disenchantment' agent that helps users stop idealizing a person by extracting facts, analyzing attachment mechanisms, and producing actiona
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.
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.
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).
A meta-skill that generates personalized 'disenchantment agents' to help users stop idealizing someone (ex, crush, AI companion). SKILL.md is detailed and well-structured with clear 5-step workflow and ethical guardrails. However, all referenced scripts (case_writer.py, folder_ingest.py, version_manager.py) and prompt templates (prompts/*.md) are missing from the bundle, making it non-functional as-is. No security concerns — no scripts to audit, no network calls, no destructive commands.
Novel concept for a meta-skill that creates other skills. SKILL.md content is primarily in Chinese with English tags and some mixed-language sections. The skill has thoughtful ethical constraints (no attacking immutable characteristics, distinguish facts from inference, AI companion warning). Missing all referenced implementation files.
Retriever (Membrane CLI)
Integrate Retriever search and discovery via the Membrane CLI — manage connections and run queries across Retriever data sources.
Bash Pro
Defensive, production-grade Bash scripting patterns and CI/CD best practices: strict mode, safe argument parsing, testing with Bats, and tooling (ShellCheck/shf
Skill Retro
Analyze a session's skill invocations to surface performance issues and recommend or apply improvements using the skill-creator workflow.
AI News Daily
Generate a structured, bilingual daily briefing of the latest AI industry news, model updates, papers, and open-source tools with in-depth technical analysis an
Analyzing Ransomware Leak Site Intelligence
Collect and analyze ransomware data-leak site (DLS) posts to extract victim, group, sector and geographic trends for threat intelligence and proactive defense.
Analyzing Ransomware Leak Site Intelligence
Collect and analyze ransomware data-leak site (DLS) postings to extract victim, group, sector, and timeline intelligence for threat hunting and risk assessment.
Code Mode for MCP Servers
Add a sandboxed code mode tool to an MCP server so LLMs run small processing scripts against large API responses and only the script output enters the model con
Arcana (Technical Mechanism Analysis)
Explain how systems, protocols, or architectures actually work under the hood and surface non-obvious implications and failure modes.