Three-layer verification architecture (CoVe, HSP, RAG) for self-verification, fact-checking, and hallucination prevention
EXPLAIN ANALYZE分析、クエリ実行計画最適化、インデックス推奨、スロークエリ検出・修正。DBパフォーマンス改善、クエリ最適化が必要な時に使用。Schemaのスキーマ設計を補完。
>
Build neuro-symbolic LLM applications with Synalinks framework. Use when working with DataModel, Program, Generator, Module, training LLM pipelines, in-context learning, structured output, JSON...
|
Orchestrate comprehensive planning phase from ideation to development-ready specifications using 4 specialized agents
Orchestrate comprehensive planning phase from ideation to development-ready specifications using 3 specialized agents (Full workflow documentation at docs/workflows/planning-workflow.md)
>
WooYun漏洞分析专家系统。基于88,636个真实漏洞案例提炼的元思考方法论、测试流程、利用技巧、绕过方法。覆盖SQL注入、XSS、命令执行、逻辑漏洞、文件上传、未授权访问等主要漏洞类型。当用户进行漏洞挖掘、渗透测试、安全审计、代码审计时触发。
A comprehensive skill for interacting with Dremio Data Lakehouse via CLI, Python SDK, SQL, and REST API. Use this skill when the user asks for Dremio-related coding tasks, data manipulation, or...
>
|
Build LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval,...
Build LLM applications with LangChain and LangGraph. Use when creating RAG pipelines, agent workflows, chains, or complex LLM orchestration. Triggers on LangChain, LangGraph, LCEL, RAG, retrieval,...
|
Cohere LangGraph agents reference for building ReAct agents, multi-tool workflows, agents with memory, and human-in-the-loop patterns. Covers both prebuilt and custom agent architectures.
Guides architectural decisions for LangGraph applications. Use when deciding between LangGraph vs alternatives, choosing state management strategies, designing multi-agent systems, or selecting...
Extracts expertise from domain experts and transforms it into working Claude skills. Guides through structured conversations to capture mental models, workflows, principles, and best practices.
|
>