Run any Skill in Manus with one click

architecture-knowledge

Stars21

Forks5

UpdatedApril 14, 2026 at 10:34

Deep knowledge about AI agent architectures, AWS services, memory patterns, and best practices. Use as reference when answering technical questions.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

aws-samples

aws-samples/sample-agent-greenhouse

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	architecture-knowledge
description	Deep knowledge about AI agent architectures, AWS services, memory patterns, and best practices. Use as reference when answering technical questions.

Architecture Knowledge

AgentCore Runtime

Managed container runtime for AI agents
Supports Strands SDK, LangChain, and custom frameworks
Request-driven model (invoke_agent_runtime API)
Session-based with automatic scaling (including scale-to-zero)
Memory integration (STM events + LTM strategy extraction)

Memory Architecture (Plato Design)

Platform files (SOUL.md, IDENTITY.md) → baked into container image
User memory → AgentCore Memory with namespace isolation
STM: Conversation events per session (list_events / create_event)
LTM: Extracted records from 4 strategies (Semantic, UserPreference, Summary, Episodic)
Namespace isolation: /actors/{actorId}/ for server-side filtering
Explicit memory: save_memory / recall_memory tools for high-value facts

Slack Integration Pattern

API Gateway → Lambda (3s ack) → SQS → Worker Lambda (15min) → AgentCore
Session ID: thread-based for shared context, channel+user for non-thread
Actor ID: Slack user ID for memory isolation

More from this repository

same repository

aidlc-inception

aws-samples/sample-agent-greenhouse

Guide developer teams through AIDLC Inception — structured requirements gathering, design, and artifact generation

2026-05-1721

code-review

aws-samples/sample-agent-greenhouse

Reviews agent code for security vulnerabilities, quality issues, and agent-specific best practices. Checks for prompt injection, credential exposure, unsafe execution, error handling, and testing.

2026-05-1721

debug

aws-samples/sample-agent-greenhouse

Debugging specialist for AgentCore deployments: container failures, IAM permission errors, runtime exceptions, networking issues, and performance problems. Use when developers report errors, crashes, deployment failures, or need help troubleshooting their agent applications.

2026-05-1721

deployment-config

aws-samples/sample-agent-greenhouse

Generates deployment configurations for Amazon Bedrock AgentCore. Produces Dockerfiles, IAM policies, CDK stacks, buildspec files, runtime configs, and environment variable templates following AWS security best practices and least-privilege principles.

2026-05-1721

design-advisor

aws-samples/sample-agent-greenhouse

Reviews agent applications for platform deployment readiness. Checks containerization, secrets, config, health endpoints, statefulness, error handling, dependencies, and security.

2026-05-1721

fleet-ops

aws-samples/sample-agent-greenhouse

Fleet operations specialist for agent restart, scaling, graceful draining, and capacity planning. Use when teams need to restart agents, scale the fleet up or down, drain agents for maintenance, or plan capacity.

2026-05-1721

name	architecture-knowledge
description	Deep knowledge about AI agent architectures, AWS services, memory patterns, and best practices. Use as reference when answering technical questions.

Architecture Knowledge

AgentCore Runtime

Managed container runtime for AI agents
Supports Strands SDK, LangChain, and custom frameworks
Request-driven model (invoke_agent_runtime API)
Session-based with automatic scaling (including scale-to-zero)
Memory integration (STM events + LTM strategy extraction)

Memory Architecture (Plato Design)

Platform files (SOUL.md, IDENTITY.md) → baked into container image
User memory → AgentCore Memory with namespace isolation
STM: Conversation events per session (list_events / create_event)
LTM: Extracted records from 4 strategies (Semantic, UserPreference, Summary, Episodic)
Namespace isolation: /actors/{actorId}/ for server-side filtering
Explicit memory: save_memory / recall_memory tools for high-value facts

Slack Integration Pattern

API Gateway → Lambda (3s ack) → SQS → Worker Lambda (15min) → AgentCore
Session ID: thread-based for shared context, channel+user for non-thread
Actor ID: Slack user ID for memory isolation