Loading...
Loading...
Found 162 Skills
AI-powered autonomous penetration testing framework with multi-agent system, real security tool execution, and compliance reporting
This skill should be used when the user asks to "optimize prompts", "design prompt templates", "evaluate LLM outputs", "build agentic systems", "implement RAG", "create few-shot examples", "analyze token usage", or "design AI workflows". Use for prompt engineering patterns, LLM evaluation frameworks, agent architectures, and structured output design.
Deep Research Skill - Multi-source investigation across X (Twitter), the Web, and academic papers using team agents. Utilize this skill when users request deep research, comprehensive investigation, multi-perspective analysis, or hypothesis development on any topic. It is triggered by phrases such as "deep research", "investigate thoroughly", "research across sources", "ディープリサーチ", or requests for fact-based analysis with original hypotheses. It conducts a 6-phase research process: needs analysis, X preliminary research, parallel web deep-dive (3 agents), information integration, hypothesis construction, and final report delivery.
LangGraph workflow patterns for state management, routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming, subgraphs, and functional API. Use when building LangGraph pipelines, multi-agent systems, or AI workflows.
Agentic Workflow Pattern
Operates a shared identity graph that multiple AI agents resolve against. Ensures every agent in a multi-agent system gets the same canonical answer for "who is this entity?" - deterministically, even under concurrent writes.
Agent Workflow Designer
Letta framework for building stateful AI agents with long-term memory. Use for AI agent development, memory management, tool integration, and multi-agent systems.
AI agents: autonomous agents, multi-agent systems, LangChain, LlamaIndex, MCP.
Use when you need a complete research workflow from initial literature search to polished, fact-checked document. Chains researcher -> synthesizer -> devils-advocate -> fact-checker -> editor automatically.
Xiaohongshu Copy Optimization Agent System. Specialized in optimizing copy for eyewear products on Xiaohongshu, it supports reading content to be optimized and reference materials, and outputs high-conversion notes that comply with platform specifications. Usage scenarios: When users request to optimize Xiaohongshu eyewear copy, generate Xiaohongshu eyewear notes, or need to refer to platform hot words and writing specifications.
Manage agent fleet through CRUD operations and lifecycle patterns. Use when creating, commanding, monitoring, or deleting agents in multi-agent systems, or implementing proper resource cleanup.