AI & ML

dreydrey9000 Bundle

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations,...

jamestorrevillas Bundle

Prompt Engineering

xcrrr Skill

Use this skill when you need financial modeling, ratio analysis, or business financial health assessment — triggered by phrases like 'analyze my financials', 'calculate my burn rate', 'model this scenario', or 'is this business profitable'. Not for tax advice, bookkeeping, or regulated investment advisory services.

jamestorrevillas Skill

AI Prompting Patterns & Agent Communication

sipingme Bundle

通过 MCP 协议操作今日头条平台，支持内容发布、账号管理等功能

sipingme Bundle

通过 MCP 协议操作小红书平台，支持内容发布、搜索、互动等完整功能

xcrrr Skill

Use this skill when building evaluation frameworks to measure LLM quality, safety, accuracy, or alignment including test suites, human eval rubrics, automated evals, and metrics design. Not for training or fine-tuning models. Not for dataset curation or benchmark comparison across publicly available models.

moose-lab Skill

Send and receive emails, and intercept verification/OTP codes for AI agents using the mails.dev service. Use this skill whenever an agent needs to: claim an @mails.dev mailbox, send an email, wait for a verification or OTP code to arrive, search an inbox for a specific message, or embed email functionality inside a Claude artifact via the SDK or HTTP API. Trigger on phrases like "send an email", "wait for a verification code", "check my inbox", "OTP email", "email agent", "set up a mailbox", or any workflow that involves receiving a confirmation email and extracting a code from it. Also trigger when building an artifact that needs to call the mails API directly.

congcongfu Bundle

plurk-mcp skill pack 的仓库级说明文件。用于解释本仓库的结构、共享参考和统一入口 skill 的位置，而不是作为实际安装后的子 skill 使用。

congcongfu Bundle

plurk-mcp 的统一入口 skill。用于在多账号上下文中，在 Load Profile、Load Alerts、Load Mentions、Create Post、Create Reply 这些具体技能之间做选择，并在进入具体技能前先提醒当前工具边界和目标账号锁定要求。

congcongfu Bundle

在用户已经明确要为指定账号发布新 plurk，或需要先整理一条公开披露的 Laike 推广内容再执行发布时使用。通过 plurk_post 执行最终写操作，并遵守按账号隔离的每日新帖配额和当前不支持动作的边界。

congcongfu Bundle

在用户要求查看目标账号的近期提醒、识别需要关注的互动，或先做提醒层面的运营巡检时使用。通过 plurk_get_alerts 读取标准化 alerts，保持只读。

congcongfu Bundle

在用户要求用指定账号回复明确 mention 或其自有线程中的互动时使用。先读取 thread context，再通过 plurk_reply 执行最终写入，并遵守资格与冷却边界。

congcongfu Bundle

在用户要求查看某组 credentials 对应的 Plurk 账号资料、确认这次调用会落到哪个账号，或检查基础 profile 信息时使用。通过 plurk_get_me 读取标准化 profile，保持只读。

congcongfu Bundle

在用户要求查看目标账号的近期 mentions、梳理可回复互动，或为后续回复准备上下文时使用。通过 plurk_get_mentions_context 读取 mention 结果，并按需使用 plurk_get_thread_context 展开线程，但整体保持只读。

ztygod Skill

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

dragonestdwolf Bundle

提供基于本地 SVG 的图标 MCP 服务使用说明；支持图搜（输入为图片，返回最相似图标）。在需要列出/获取/搜索图标、按图片搜图标、或需要图标本地路径与 SVG 内容时使用。

dreydrey9000 Bundle

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

dreydrey9000 Bundle

Transform audio recordings into professional Markdown documentation with intelligent summaries using LLM integration

sean2411 Skill

Multi-Agent Development Workflow

liuyihey Skill

Guide for creating effective AI agent skills. Use this skill when creating a new personal skill from a completed task solution. Triggers when the user agrees to create a skill after task review, or explicitly asks to create a new skill.

liuyihey Skill

Guide for improving existing AI agent skills based on execution feedback. Use this skill when a skill didn't execute smoothly, when the user wants to improve a skill after using it, or when iterating on skill quality based on real usage.

dreydrey9000 Bundle

Master orchestrator, peer-to-peer, and hierarchical multi-agent architectures

dreydrey9000 Skill

9-step framework for building production-ready AI agents from scratch. Use when users want to create AI agents, automate with AI, or build multi-agent systems. Keywords: agent, ai, automation, llm, workflow, tool use, multi-agent

mlopscommunity Skill

Use when working on multi-step tasks, long conversations, or when agent output quality degrades mid-session. Techniques for keeping context lean so the model produces better results.

sssssssynqa Bundle

小红书操作指南（Chrome MCP）

bryanhull Bundle

MCP server for Tebra FHIR (Kareo EHR) with OAuth2 client-credentials auth and read-focused tools for patients and clinical resources.

bryanhull Bundle

MCP server for Tebra Web Services API 2.1 (SOAP) using CustomerKey, User, and Password for office administration workflows.

dreydrey9000 Bundle

The definitive Claude Code setup system. Use when onboarding anyone to Claude Code, setting up a new machine, auditing your configuration, or answering "what should I install?" Covers ALL 14 hook events, 3 hook types, agent teams, worktree isolation, MCP servers, skills, and proven patterns. Triggers on "starter pack", "setup Claude Code", "onboard", "what hooks do I need", "get started", "new machine setup", "Claude Code features".

dreydrey9000 Bundle

This skill should be used when the user asks to "add MCP server", "integrate MCP", "configure MCP in plugin", "use .mcp.json", "set up Model Context Protocol", "connect external service", mentions "${CLAUDE_PLUGIN_ROOT} with MCP", or discusses MCP server types (SSE, stdio, HTTP, WebSocket). Provides comprehensive guidance for integrating Model Context Protocol servers into Claude Code plugins for external tool and service integration.

claio0128 Skill

Specialized for deep-dive academic research in Machine Learning (RL, Diffusion, VLM, VLA). Use when you need to search ArXiv, trace historical milestones, analyze benchmark datasets/metrics, compare competing solutions, and generate practical 'try-out' instructions. Results are saved to the workspace 'research' folder.

dreydrey9000 Bundle

This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.

damiangao Bundle

Asynchronous Claude Code Agent Teams with session management and multi-channel notifications (Feishu, Discord, Telegram).

damiangao Bundle

Claude Code Agent Teams

anup4khandelwal Bundle

1. Skill Name

anup4khandelwal Bundle

1. Skill Name