Menu
Build applications where agents are first-class citizens. Use when designing tools, APIs, or features that agents will interact with.
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.
Based on SOC occupation classification
Browser automation for AI agents. Use when agents need to navigate pages, fill forms, take screenshots, or verify UI.
Explore requirements and approaches through collaborative dialogue before planning. Use before ce-plan for new features.
Document solved problems to compound team knowledge. Use after completing any non-trivial feature or bug fix.
Transform feature descriptions into structured implementation plans grounded in repo patterns and research. Use when starting any non-trivial work.
Structured multi-agent code review with tiered personas, confidence-gated findings, and merge/dedup pipeline. Use during the Review phase.
Execute work plans efficiently with atomic commits, verification checkpoints, and state tracking. Use during the Work phase.
| name | agent-native-architecture |
| description | Build applications where agents are first-class citizens. Use when designing tools, APIs, or features that agents will interact with. |
| slug | agent-native-architecture |
| tags | ["architecture","agent-native"] |
| metadata | {"sources":[{"kind":"github-dir","repo":"EveryInc/compound-engineering-plugin","path":"plugins/compound-engineering/skills/agent-native-architecture","commit":"main","url":"https://github.com/EveryInc/compound-engineering-plugin"}]} |
Referenced from compound-engineering plugin. Guides design of agent-native systems with parity, granularity, composability, and emergent capability principles.
