canon-architecture

Generate architecture decision and context artifacts from supplied risk, zone, and system context.

1|Updated Mar 26, 2026
One-click install
npx skills add https://github.com/apply-the/canon --skill canon-architecture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: canon-architecture
Source: https://github.com/apply-the/canon/tree/main/.agents/skills/canon-architecture
Command: npx skills add https://github.com/apply-the/canon --skill canon-architecture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Canon architecture skill enables you to start a governed architecture run that records decisions, tradeoffs, risk considerations, and approvals, ensuring a traceable, auditable artifact bundle.

Core Features & Use Cases

  • Start architecture-bound packets and create ADR-style architecture artifacts (architecture-decisions.md, context-map.md, system-context.md, container-view.md, component-view.md) under a real run.
  • Enforce required authored sections and preflight checks before invocation to ensure consistent, reviewable outputs.
  • Use cases include planning architectural decisions for new features, migrations, or system rewrites with risk-aware constraints.

Quick Start

Invoke Canon in architecture mode using your SYSTEM_CONTEXT and risk/zone values with an authored architecture brief.

Frequently Asked Questions about canon-architecture

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I capture architecture decisions and risk constraints for a system rewrite?

To capture architecture decisions and risk constraints, you supply RISK, ZONE, SYSTEM_CONTEXT, and at least one input to generate a reviewable packet of architecture-decisions.md, system-context.md, and context-map.md artifacts.

What is a governed architecture run and when do I need one for migrations?

A governed architecture run records decisions, tradeoffs, risk considerations, and approvals, ensuring a traceable, auditable artifact bundle. You need one when planning architectural decisions for migrations or system rewrites with risk-aware constraints.

How do I generate ADR-style architecture artifacts like context maps and container views?

Generate ADR-style architecture artifacts by invoking architecture mode with your SYSTEM_CONTEXT and risk/zone values using an authored architecture brief, producing context-map.md, container-view.md, and component-view.md files.

Do I need to prefill required authored sections before starting an architecture decision run?

Yes, you must include required authored sections and pass preflight checks before invocation to ensure the generated architecture packet is complete, consistent, and reviewable.

Can I use inline notes as inputs for architecture decision records and system context mapping?

Yes, you can use inline notes, files, or folders as inputs for architecture decision records and system context mapping alongside your RISK, ZONE, and SYSTEM_CONTEXT values.

What are the limitations of starting a Canon architecture run without ownership boundaries?

Without ownership boundaries, the architecture run cannot properly capture constraints and ownership, risking incomplete or unreviewable architecture-decisions.md and context-map.md artifacts.