MCP App StoreMCP App Store
from pig-skill62
Create a personalised conversational persona from QQ group chat records or manual inputs; generates a reusable Skill that speaks like that person and supports i
This skill converts QQ group chat records and simple intake prompts into a reusable ‘pig’ persona Skill that replies in the target user's voice. It analyses uploaded TXT/JSON or pasted chat logs, extracts communication style, common phrases, emoji habits, and a five-layer persona profile, then scaffolds persona files and a SKILL.md package. The skill supports English and Chinese and includes tools and commands for versioning, exporting persona metadata, and listing or updating generated pigs.
Use this when you want an assistant that mimics a specific group friend or chat persona — for simulations, roleplay, customer-style responses, or automated replies that preserve a distinct voice. Triggered by commands like /pig-skill, help me create a pig skill, or by update commands when adding new files or corrections.
Designed for Claude Code environments (uses Read, Write, Edit, Bash).
Pig-skill creates conversational personas from QQ group chat records for Claude Code. No bundled scripts were present — it references external tools (qq_chat_parser.py, version_manager.py, skill_writer.py) via CLAUDE_SKILL_DIR. The SKILL.md is well-documented and bilingual (Chinese/English) with clear step-by-step flows for creation, evolution, and correction modes. Delete command uses rm -rf but is gated behind user confirmation.
No scripts to execute or test. The skill is purely instructional with references to external Python tools not bundled in the skill itself. Architecture follows a reasonable pattern but doesn't strictly conform to the AgentSkills references/ directory convention.
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.
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.
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
draw.io Diagram Skill
Create, edit, lint, and export draw.io diagrams; includes export helpers, SVG linting, and repository QA for clean architecture and icon-based diagrams.
悟道真英雄
Create a personalized A-share trading persona that grows with your trade history: analyze screenshots, ingest chat posts, track watchlists and regrets, and enfo
Writer — Writing Style Guide
A practical writing style and persona guide for producing human-sounding docs, READMEs, commit messages, PR descriptions, blog posts, and UI copy.
API Development
Guidelines and patterns for building robust REST APIs: correct HTTP status codes, RFC 7807 error responses, validation, sanitization, rate limiting, and central