incept5 avatar

Eve Agentic App Design

This is the layer you add once your Eve app's PaaS foundation is solid. It walks you through defining agents in agents.yaml (slug, skill, harness profile, access scope, git policies), organizing them into teams with fanout, council, or relay dispatch modes, and designing memory architecture so agents know what to remember and where. The harness profiles section is smart: agents reference named profiles instead of hardcoded models, so you can swap brains without rewriting agent configs. The honest take is that this assumes you've already loaded eve-fullstack-app-design and understand the prerequisite layers. If you're building an app where agents coordinate, make decisions, and remember context across sessions, this gives you the architectural skeleton.

skills.sh installs
279
last updated
Aug 21, 2026

Install

$ npx -y skills add incept5/eve-skillpacks --skill eve-agentic-app-design --agent claude-code

Installs into .claude/skills of the current project.

Files

Agentic App Design on Eve Horizon

Transform a full-stack app into one where agents are primary actors — reasoning, coordinating, remembering, and communicating alongside humans.

When to Use

Load this skill when:

  • Designing an app where agents are primary users alongside (or instead of) humans
  • Adding agent capabilities to an existing Eve app
  • Choosing between human-first and agent-first architecture
  • Deciding how agents should coordinate, remember, and communicate

Prerequisite: Start with the Foundation

Load eve-fullstack-app-design first. The agentic layer builds on a solid PaaS foundation. Without a well-designed manifest, service topology, database, pipeline, and deployment strategy, agentic capabilities collapse into chaos.

The progression:

  1. eve-agent-native-design — Principles (parity, granularity, composability, emergent capability)
  2. eve-fullstack-app-design — PaaS foundation (manifest, services, DB, pipelines, deploys)
  3. This skill — Agentic layer (agents, teams, memory, events, chat, coordination)

Each layer assumes the previous. Skip none.

Agent Architecture

Defining Agents

Sponsors

Details

Repository
github.com/incept5/eve-skillpacks
Categories
AI & Agent Building, Design & UI/UX
First seen
Jun 3, 2026

More from incept5/eve-skillpacks

All 26
1andreadellacorte avataragent-browserandreadellacorte/grooveBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking scr273skills.sh installs
2cinience avataralicloud-ai-audio-tts-realtimecinience/alicloud-skillsReal-time speech synthesis with Alibaba Cloud Model Studio Qwen TTS Realtime models. Use when low-latency interactive speech is required, including instruction-272skills.sh installs
3oimiragieo avatarcontext-compressoroimiragieo/agent-studioCompress large context before reasoning to reduce token usage while preserving evidence. Use this whenever the user mentions huge files, long prompts, RAG paylo271skills.sh installs
4cinience avataralicloud-ai-recommend-aireccinience/alicloud-skillsManage Alibaba Cloud AIRec (Airec) via OpenAPI/SDK. Use whenever the user needs recommendation-engine resource operations in Alibaba Cloud, including list/creat265skills.sh installs
5kimyx0207 avataragent-teams-playbookkimyx0207/agent-teams-playbookagent teams playbook265skills.sh installs
6cinience avataralicloud-ai-pai-aiworkspacecinience/alicloud-skillsManage Alibaba Cloud PAI AIWorkspace (AIWorkSpace) via OpenAPI/SDK. Use whenever the user is operating AIWorkspace resources such as workspace/project inventory264skills.sh installs