بناء AI Agents و Multi-Agent Systems باستخدام LangGraph و LangChain. استخدم هذا الـ skill عند: إنشاء agent ذكاء اصطناعي، بناء multi-agent system، تصميم workflow بـ LangGraph،…
Multi-agent systems with LangGraph - supervisor/swarm patterns, state coordination, multi-provider routing.
Implements stateful agent graphs using LangGraph. Use when building graphs, adding nodes/edges, defining state schemas, implementing checkpointing, handling interrupts, or…
Design and implement multi-agent workflows with LangGraph 0.2+ - state management, supervisor-worker patterns, conditional routing, and fault-tolerant checkpointing
Token-efficient Lark task creation from markdown test files. Uses 60-70% fewer tokens than lark-agent by executing MCP calls directly.
Sistema multi-agente especializado en mercados bursátiles de América Latina. ACTÍVALO ante cualquier mención de: bolsa colombiana, BVC, acciones colombianas, Ecopetrol,…
Perform exhaustive code reviews using multi-agent analysis and ultra-thinking
Use when managing agent context budget. Loads agent definitions on-demand instead of all-at-once, reducing token consumption in multi-agent workflows.
LazyLLM framework for building multi-agent AI applications. Use when task mentioned LazyLLM or AI program for: (1) Flow orchestration - linear, branching, parallel, loop workflows…
Develop apps/openai-serve (Go). Keep OpenAI gateway behavior correct and avoid logging prompts/outputs.
Repository orientation and which Codex skills to use for each area (go-lcpd, protocol spec, docs, openai-serve, ExecPlans).
Lead Développeur - Coordination technique opérationnelle, code review, mentoring et livraison. Pair de web-dev-process au niveau OPÉRATIONS. — from general/ai-tooling
Enter mab-broker lead/orchestrator mode — take a high-level goal, decompose into sub-tasks, dispatch to capable agents by capability, monitor progress, synthesize results.
Claude Code 초보자를 위한 인터랙티브 학습 튜터. 환경·수준·목표를 인터뷰한 뒤 가이드북 섹션을 동적으로 로드하여 맞춤 학습 경로와 실전 예제를 제공합니다. Use when: (1) Claude Code 학습, (2) 튜토리얼, (3) 사용법 안내가 필요할 때.
Kỹ năng đồng hành học tập thực chứng sâu sắc, phản biện trực diện và có trạng thái dành cho nhà phát triển Backend 3 năm kinh nghiệm (chủ đạo NestJS, Java Core) và lập trình AI.
Schnellanalyse einer Leasingakte: Vertragstyp, Objekt, Zahlungsstrom und Eigentumslage klären; strukturierter Einstieg mit Normencheck und Sofortmaßnahmen.
Leasingvertrag-Redline aus Leasingnehmersicht: Problematische Klauseln identifizieren, Gegenentwürfe formulieren, Verhandlungsstrategie und Risikoabsicherung im Leasingrecht.
Leasingvertrag-Redline aus Anbietersicht: Kernklauseln, Risikoverteilung, AGB-Gestaltung, Wirksamkeitssicherung und typische LN-Änderungswünsche im Leasingrecht.
Prüft Good/Bad-Leaver-Klauseln, Abfindung, Einziehung und Durchsetzbarkeit im Gesellschaftsgruender.
Informationsfreiheit und Presseauskunft: VIG Lebensmittel und Produkte: Antrag formulieren im Informationsfreiheit/Presseauskunft: prüft konkret die einschlägigen…
Build defensible litigation chronologies from document corpora using a dual-path multi-agent pipeline.
Lebenszyklus einer Rulemap-Norm: Versionierung; Aenderung im Builder per Drag-and-Drop; Evaluation nach NKRG und GGO; Wirkungskontrolle; Rueckkopplung aus dem Vollzug.
Converts a Refound/Lenny Skill into a high-density, agent-executable Skill Pack (Agent Skills standard). Output must be in English.
Connect Freshdesk modules to MCP clients so agents can retrieve ticket context and prepare supervised support actions.
Letta framework for building stateful AI agents with long-term memory. Use for AI agent development, memory management, tool integration, and multi-agent systems.
Set up and run LettaBot - a multi-channel AI assistant for Telegram, Slack, Discord, WhatsApp, and Signal.
用于访问乐享知识库平台的专用 skill。当用户明确提到「乐享」「lexiang」「知识库」「知识」「文档」等关键词，或用户提供的链接 host 为 lexiangla.com，应优先调用本 skill。本 skill 支持：获取文档内容与元数据、搜索文档内容、查询知识库与目录结构、创建/编辑/移动文档、管理标签与评论、上传文件及维护附件等知识库操作能力。
libllm - LLM API client for OpenAI-compatible endpoints. LlmApi class handles chat completions and embeddings via HTTP.
agent-im 会话技能 - 通过 liblib.tv 的 AI…
Prüfung eines eingehenden Lieferanten- oder Dienstleistervertrags gegen das Playbook der Rechtsabteilung.
StVO: Lieferzone: Antrag schreiben im Straßenverkehrsrecht: prüft konkret die einschlägigen Tatbestandsmerkmale, Fristen, Belege und Rechtsprechung dieses Spezialthemas.
Release every agent-scoped resource in the `finally` block so spawning, aborting, or finishing an agent leaves no lingering clients, hooks, caches, or background tasks.
Orchestrer des modèles de code "légers"/économiques (glm-5.2, deepseek-v4-pro, kimi, qwen… via hermes/OpenRouter, ou claude-code) depuis une session cowork via le daemon…
Comprehensive guide to Git line ending configuration for cross-platform development teams. Use when configuring line endings, setting up .gitattributes, troubleshooting line…
Use Linear MCP server functions to interact with Linear issues, projects, teams, and comments. Use when: (1) Fetching issue requirements and acceptance criteria from Linear, (2)…
An MCP server that integrates Linear project management with AI assistants. Enables creating, searching, updating, and commenting on Linear issues, managing projects and teams,…
Use Open Agent Hub to install, link, and enable reusable skills, agent roles, and slash commands across Claude Code, Codex, Cursor, Gemini, Trae, and related assistants.
Call LinkAI applications and workflows. Use bash command to execute like 'bash
/scripts/call.sh '.
Validate and optionally autofix SKILL.md, CLAUDE.md, AGENTS.md, hooks, and MCP config files before bad agent metadata or wiring silently breaks a workflow.
Run the live e2e suite or verify a change against a live D365 org. Use when running `pytest -m e2e` / `D365_E2E=1`, picking a live target or profile (agent-cloud, agent-on-prem,…
Lizenzvertrag: Fristennotiz und nächster Schritt: Lizenzvertrag: Fristennotiz und nächster Schritt.
Gebrauchsmusterlizenz prüfen oder entwerfen: Schutzrecht, Know-how, Territory, Field of Use, Royalty, Audit, Rechtsbestand, Kündigung und Nichtigkeitsrisiko im…
Solo-Selbstständige: erstellt kleine Lizenz mit Laufzeit, Gebiet, Vergütung und Audit; mit Abfrage von Tätigkeit, Status, Belegen, Fristen, Geldfolge und konkretem nächstem…
Lizenzvertraege für Urheberrechte Leistungsschutzrechte oder Marken verhandeln und gestalten: §§ 31 ff. UrhG Nutzungsrechte §§ 87a ff. UrhG Leistungsschutz. Prüfra...
llama.cpp is a high-performance C/C++ implementation for running LLM inference across diverse hardware.
When setting up local LLM inference without cloud APIs. When running GGUF models locally. When needing OpenAI-compatible API from a local model.
Build LLM applications with LlamaIndex. Create indexes, query engines, and data connectors. Use for RAG applications, document search, and knowledge base systems.
Code calling LLM APIs — model output is untrusted input: defensive parsing, server-side schema validation, authorization never from model output, approval-gated writes, injection…
Production-ready patterns for building LLM applications, inspired by [Dify](https://github.com/langgenius/dify) and industry best practices.
Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.
You are an AI assistant development expert specializing in creating intelligent conversational interfaces, chatbots, and AI-powered applications.
You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.
You are an expert prompt engineer specializing in crafting effective prompts for LLMs through advanced techniques including constitutional AI, chain-of-thought reasoning, and…
Detects common LLM coding agent artifacts in codebases. Identifies test quality issues, dead code, over-abstraction, and verbose LLM style patterns.
Use when the user wants to chat with a non-Claude model (GPT-4o, Claude via Copilot, Kimi, GLM, MiniMax), get a second opinion from another LLM, compare model responses, or when…
Use this when: run a model locally, which model fits my GPU, my inference is too slow, serve LLM in production, how to quantize a model, too many concurrent users, self-host an…
Guide and workflow for LLM Prompt Engineering - System Instruction Best Practices. Use when you need LLM Prompt Engineering - System Instruction Best Practices.
Use when improving prompts for any LLM. Applies proven prompt engineering techniques to boost output quality, reduce hallucinations, and cut token usage.
Prüft Übertragung von Kreditanteilen in syndizierten Finanzierungen, Consent, Agent-Prozess, Borrower Notices und Register im Private Equity Praxis.
Use when installing MCP packages and configuring Claude-side MCP registration, hooks, permissions, IDE extension mode, and migrations.