From lets-engineer
Build applications where agents are first-class citizens. Use this skill when designing autonomous agents, creating MCP tools, implementing self-modifying systems, or building apps where features are outcomes achieved by agents operating in a loop.
How this skill is triggered — by the user, by Claude, or both
Slash command
/lets-engineer:lets-agent-native-architectureThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
<overview>
references/action-parity-discipline.mdreferences/agent-execution-patterns.mdreferences/agent-native-testing.mdreferences/architecture-patterns.mdreferences/checklists.mdreferences/dynamic-context-injection.mdreferences/files-universal-interface.mdreferences/from-primitives-to-domain-tools.mdreferences/mcp-tool-design.mdreferences/mobile-patterns.mdreferences/product-implications.mdreferences/refactoring-to-prompt-native.mdreferences/self-modification.mdreferences/shared-workspace-architecture.mdreferences/system-prompt-design.mdAgent-native applications treat agents as first-class citizens. Features are outcomes achieved by an agent with tools operating in a loop, not functions written in code. The same architecture that powers Claude Code can power apps far beyond coding.
Five core principles:
context.md file) and prompt refinement, without shipping code.For deep coverage of how these principles translate into architectural patterns, read references/architecture-patterns.md.
Pick a number or describe what you want. Wait for the response before proceeding.
| Response | Read | |----------|------| | 1, "design", "architecture", "plan" | `references/architecture-patterns.md`, then apply the checklist in `references/checklists.md` | | 2, "files", "workspace", "filesystem" | `references/files-universal-interface.md` and `references/shared-workspace-architecture.md` | | 3, "tool", "mcp", "primitive", "crud" | `references/mcp-tool-design.md` | | 4, "domain tool", "when to add" | `references/from-primitives-to-domain-tools.md` | | 5, "execution", "completion", "loop" | `references/agent-execution-patterns.md` | | 6, "prompt", "system prompt", "behavior" | `references/system-prompt-design.md` | | 7, "context", "inject", "runtime", "dynamic" | `references/dynamic-context-injection.md` | | 8, "parity", "ui action", "capability map" | `references/action-parity-discipline.md` | | 9, "self-modify", "evolve", "git" | `references/self-modification.md` | | 10, "product", "progressive", "approval", "latent demand" | `references/product-implications.md` | | 11, "mobile", "ios", "android", "background", "checkpoint" | `references/mobile-patterns.md` | | 12, "test", "testing", "verify", "validate" | `references/agent-native-testing.md` | | 13, "refactor", "existing", "migrate" | `references/refactoring-to-prompt-native.md` | | 14, "review", "audit", "anti-pattern", "checklist", "success criteria" | `references/checklists.md` |After reading the reference, apply those patterns to the user's specific context.
<reference_index>
Core patterns:
references/architecture-patterns.md — Event-driven, unified orchestrator, agent-to-UI; full coverage of the five principlesreferences/files-universal-interface.md — Why files, organization, context.mdreferences/mcp-tool-design.md — Tool design, dynamic capability discovery, CRUDreferences/from-primitives-to-domain-tools.md — When to graduate primitives to domain toolsreferences/agent-execution-patterns.md — Completion signals, partial completion, context limitsreferences/system-prompt-design.md — Features as prompts, judgment criteriaDisciplines:
references/dynamic-context-injection.md — Runtime context injectionreferences/action-parity-discipline.md — Capability mapping, parity workflowreferences/shared-workspace-architecture.md — Shared data space, UI integrationreferences/product-implications.md — Progressive disclosure, latent demand, approvalreferences/agent-native-testing.md — Testing outcomes, parity testsreferences/checklists.md — Architecture checklist, anti-patterns, success criteriaPlatform-specific:
references/mobile-patterns.md — iOS storage, checkpoint/resume, cost awarenessreferences/self-modification.md — Git-based evolution, guardrailsreferences/refactoring-to-prompt-native.md — Migrating existing code
</reference_index>npx claudepluginhub williamzelesny/lets-engineer --plugin lets-engineerGuides creation, editing, and verification of skills for AI coding agents using test-driven development with subagent scenarios. Use when authoring or debugging skills.