Eve Agent Native Design

This is how you build apps where agents aren't bolted on as an afterthought. Four principles: parity (agents can do everything users can), granularity (atomic tools, not bundled logic), composability (new features via prompts, not code), and emergent capability (agents surprise you with combinations you didn't design). Load it when designing new apps on Eve, evaluating agent-friendliness, or deciding whether logic belongs in code or prompts. The real insight is that if adding a feature requires new API endpoints instead of new prompts, your primitives probably aren't atomic enough. Includes practical patterns like job attachments for context passing and explicit completion signals instead of heuristic detection.

skills.sh installs: 287
last updated: Aug 21, 2026

View on GitHub

Install

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

Installs into .claude/skills of the current project.

Files

Agent-Native Design for Eve Horizon

Build applications where agents are first-class citizens — not afterthoughts.

When to Use

Load this skill when:

Designing a new application or API on Eve
Evaluating whether an existing app is agent-friendly
Adding features that agents should be able to use
Deciding between putting logic in code vs. in prompts
Choosing how to handle inter-agent communication

The Four Principles

1. Parity — Agents Can Do Everything Users Can

Every user action must have an agent-equivalent path.

On Eve: The CLI IS the parity layer. If a user can do it through eve ..., an agent can too. When building your app, apply the same principle:

Check	How
Can agents create/read/update/delete every entity?	Map UI actions to CLI/API equivalents
Are there UI-only workflows?	Expose them as API endpoints or CLI commands
Can agents discover what's available?	Provide `list` operations for every entity type

CRUD Completeness: For every entity in your app, verify agents have Create, Read, Update, and Delete paths. Missing any one breaks parity.