MCP App StoreMCP App Store
from senpai-skill81
Distill a graduated lab senior into an AI Skill. Import chats, meeting notes, photos, and screenshots to build Group Memory + Persona with continuous...
Distill a graduated lab senior into an AI Skill. Import chats, meeting notes, photos, and screenshots to build Group Memory + Persona with continuous evolution. | 把毕业大师兄蒸馏成 AI Skill，导入聊天记录、组会纪要、照片和截图，生成 Group Memory + Persona，支持持续进化。
Use this when you need an agent to distill a graduated lab senior into an ai skill. import chats, meeting notes, photos, and screenshots to build group memory + persona with continuous evolution. | 把毕业大师兄蒸馏成 ai skill，导入聊天记录、组会纪要、照片和截图，生成 group memory + persona，支持持续进化。
General coding agents (Claude Code, Codex, Cursor)
A bilingual (Chinese/English) skill for distilling a graduated lab senior into an AI persona skill. Imports WeChat/QQ chat logs, meeting notes, and photos to build a 'Group Memory + Persona' model. No scripts were bundled for testing. The SKILL.md is extensive with clear steps but references multiple external tool scripts (wechat_parser.py, qq_parser.py, etc.) that are not included. The skill has thoughtful safety boundaries against impersonation and fabrication, but uses `rm -rf senpais/{slug}` for deletion without guards and references local file operations that could be misused.
Creative concept (digital senpai persona from chat history) but very niche — targets Chinese academic lab culture specifically. Heavy dependency on unprompted external scripts (6 Python tools referenced but none bundled). Safety rules are well-considered (anti-impersonation, anti-fabrication, privacy). The rm -rf deletion command is a minor security concern but not catastrophic since it's scoped to a subdirectory. Architecture is decent with clear step-by-step flow, prompt templates, and file structure, but the skill is essentially a long instruction set without executable scripts.
Marshal (Session Commander)
A single-session meta-orchestrator that parses a direction, chains existing skills, and executes multi-step tasks end-to-end without unnecessary user prompts.
Hermes Ops
运维 Hermes Agent 的实战 skill。适用于用户提到“运维 hermes”“排查 hermes 问题”“gateway 异常”“平台掉线”“cron 不执行”“profile 配置混乱”“skills 或 tools 不生效”“想让其他 agent 帮忙维护 hermes”时使用。基于 hermes...
Claw Release
Release automation for Claw skills and website. Guides through version bumping, tagging, and release verification.
libagent
Agent orchestration library for conversational AI — coordinates LLM completions, memory, tool execution, and multi-turn flows; useful for building chat agents a
Azure Blob Storage
Expert knowledge for Azure Blob Storage development including troubleshooting, best practices, decision making, limits & quotas, security, configuration, int
OfficeCLI — Agent-friendly Office tools
A comprehensive CLI for reading, editing, validating, and automating .docx, .xlsx, and .pptx files — designed for AI agents to inspect, modify, and generate Off
Parchi Relay — Browser Relay & Automation
Run a local relay daemon and browser extension to control real browsers via JSON-RPC/WebSocket; includes CLI for listing agents, calling tools, and running task
Claude CLI: Create Agent
Guidelines for creating and running Claude Code CLI agents: agent JSON format, storage conventions, and execution commands.