Standardmäßig ist der Prompt ausgewählt, der zuerst die Quelle prüft. Sie können zu einem direkten Befehl wechseln oder eine lokale Kopie herunterladen.
Quelldateien prüfen
Lesen Sie SKILL.md und alle von SkillsMP angezeigten Begleitdateien, bevor Sie sich für eine Installation entscheiden.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Ein direkter Befehl überspringt den Prüf-Prompt. Prüfen Sie die Quelle, bevor Sie ihn ausführen.
Design and build AI agents with tools, memory, and multi-step reasoning capabilities. Covers ChatGPT, Claude, Gemini integration patterns based on n8n's 5,000+ AI workflow templates.
agent_types:reactive_agent:description:"Single-turn response, no memory"use_case:simple_qa,classificationcomplexity:lowconversational_agent:description:"Multi-turn with conversation memory"use_case:chatbots,supportcomplexity:mediumtool_using_agent:description:
"Can call external tools/APIs"
use_case:
data_lookup,
actions
complexity:
medium
reasoning_agent:
description:
"Multi-step planning and execution"
use_case:
complex_tasks,
research
complexity:
high
multi_agent:
description:
"Multiple specialized agents collaborating"
use_case:
complex_workflows
complexity:
very_high
Tool Calling Pattern
Tool Definition
tool_definition:name:"get_weather"description:"Get current weather for a location"parameters:type:objectproperties:location:type:stringdescription:"City name or coordinates"units:type:stringenum: ["celsius", "fahrenheit"]
default:"celsius"required: ["location"]
implementation:type:api_callendpoint:"https://api.weather.com/v1/current"method:GETparams:q:"{location}"units:"{units}"
n8n_agent_workflow:nodes:-trigger:type:webhookpath:"/ai-agent"-ai_agent:type:"@n8n/n8n-nodes-langchain.agent"model:openai_gpt4system_prompt:|
You are a helpful assistant that can:
1. Search the web for information
2. Query our customer database
3. Send emails on behalf of the user
tools:-web_search-database_query-send_email-respond:type:respond_to_webhookdata:"{{ $json.output }}"
Memory Patterns
Memory Types
memory_types:buffer_memory:description:"Store last N messages"implementation:|
messages = []
def add_message(role, content):
messages.append({"role": role, "content": content})
if len(messages) > MAX_MESSAGES:
messages.pop(0)
use_case:simple_chatbotssummary_memory:description:"Summarize conversation periodically"implementation:|
When messages > threshold:
summary = llm.summarize(messages[:-5])
messages = [summary_message] + messages[-5:]
use_case:long_conversationsvector_memory:description:"Store in vector DB for semantic retrieval"implementation:|
# Store
embedding = embed(message)
vector_db.insert(embedding, message)
# Retrieverelevant=vector_db.search(query_embedding,k=5)use_case:knowledge_retrievalentity_memory:description:"Track entities mentioned in conversation"implementation:|
entities = {}
def update_entities(message):
extracted = llm.extract_entities(message)
entities.update(extracted)
use_case:personalized_assistants
Thought: I need to find information about X
Action: web_search("X")
Observation: [search results]
Thought: Based on the results, I should also check Y
Action: database_query("SELECT * FROM Y")
Observation: [database results]
Thought: Now I have enough information to answer
Action: respond("Final answer based on X and Y")
support_agent:name:"Customer Support AI"model:gpt-4system_prompt:|
You are a customer support agent for {company}.
Guidelines:-Behelpful,professional,andempathetic-Usetheknowledgebasetoanswerquestions-Escalatetohumanifyoucannothelp-NevermakeupinformationAvailable actions:-Searchknowledgebase-Lookupcustomeraccount-Createsupportticket-Escalatetohumanagenttools:-knowledge_search:description:"Search help articles"-customer_lookup:description:"Get customer account info"-create_ticket:description:"Create support ticket"-escalate:description:"Transfer to human agent"escalation_triggers:-sentiment:very_negative-keywords: ["speak to human", "manager", "complaint"]
-failed_resolution:after_3_attempts
Research Agent
research_agent:name:"Research Assistant"model:claude-opussystem_prompt:|
You are a research assistant that helps users find
and synthesize information on any topic.
Process:1.Understandtheresearchquestion2.Plansearchstrategy3.Executesearchesacrossmultiplesources4.Synthesizefindings5.Presentwithcitationstools:-web_search-academic_search-news_search-wikipedia_lookupoutput_format:-executive_summary-key_findings-detailed_analysis-sources_cited
Output Example
Request: "Design an AI agent for appointment scheduling"
User: "I'd like to book an appointment"
Agent: [Thought: Need to know service type and preferred time]
Agent: "I'd be happy to help! What service are you looking for,
and do you have a preferred date/time?"
User: "Haircut, next Tuesday afternoon"
Agent: [Action: calendar_check(date="next Tuesday", time="afternoon")]
Agent: "I have availability at 2pm, 3pm, and 4:30pm next Tuesday.
Which works best for you?"
User: "3pm please"
Agent: [Action: book_appointment(datetime="Tuesday 3pm", service="haircut")]
Agent: [Action: send_notification(type="confirmation", ...)]
Agent: "You're all set for a haircut at 3pm next Tuesday.
I've sent a confirmation to your email. See you then!"
