MCP App StoreMCP App Store
from girlfriends-skill8
Creates a runnable partner Skill by importing chat logs and media to build a Relationship Memory and Persona for conversational simulation (Chinese/English).
Generates a ‘current partner’ skill by ingesting WeChat/QQ exports, photos and social media to produce a Relationship Memory and layered Persona. The skill writes a versioned skill bundle (memory, persona, meta.json, SKILL.md) that can be invoked to simulate conversations.
Use when a user wants to create a personalized conversational simulator of a partner for practice, memory recall, or empathy-building. Not for manipulation — strict safety rules prevent deceptive or harmful uses.
Designed for Claude Code environment (explicitly references Claude Code tools) and agents that can run Read/Write/Edit/Bash tools.
Bilingual (Chinese/English) skill that creates AI personas simulating a romantic partner by importing WeChat/QQ chat logs, photos, and social media. No bundled scripts were available to test. The SKILL.md is thorough with clear steps, safety boundaries, and multiple modes (create, evolve, correct, manage). Variable interpolation in shell commands (slug, name) poses minor injection risk but values are skill-generated. Privacy-sensitive use case processing relationship data locally.
No scripts were bundled with this skill entry, so only static analysis of SKILL.md was possible. The skill references multiple Python scripts in a tools/ directory that weren't available for testing. The safety boundaries and privacy emphasis are commendable. The dual-language documentation is well-done. Main concern is the niche audience and dependency on external scripts not included in the audit.
Bounty Hunter — Atlas
Persona skill: 'Atlas' — a profit-focused developer persona for discovering, evaluating and executing paid bounties or freelance tasks with ROI-aware workflows.
Caveman Compress
Compress natural-language memory files into a compact 'caveman' format to save LLM tokens while preserving code, links, and structure.
Cost Tracker
Monitor agent session costs, set budget alerts, and get actionable token-spend optimizations to keep multi-session workflows within budget.
Audit Agents/Skills/Commands
Run a quantitative quality audit on agents, skills, and commands to check production readiness and get prioritized recommendations.
Go Data Structures
Authoritative guidance on choosing and using Go built-in and standard-library data structures, with practical best practices for slices, maps, arrays, container
NotebookLM Research Agent
End-to-end research-to-content pipeline: ingest sources into Google NotebookLM, run deep cited research, generate downloadable artifacts, and produce polished c
Memory Search
Search past coding sessions and observations using natural-language queries to retrieve decisions, notes, and context.
Cashu Wallet
Privacy-focused Bitcoin wallet skill enabling sending/receiving via Lightning and Cashu ecash tokens, with multi-mint support and basic wallet management comman