Use when the user is starting a new AI-native system, has a working prototype that is one undifferentiated blob, asks how to decompose an agent into reusable parts, or asks for a "skill graph". Coaches the engineer through breaking the work into named, testable, composable skills and producing a Skill Graph artifact. Invoke as the first step in the Innorve Method when the team is at L0 or L1.
This listing is imported from SkillsMP metadata and should be treated as untrusted until upstream source review is completed.
Install skill "innorve-skill-architecture" with this command: npx skills add Innorve-Inc/skillsmp-innorve-inc-innorve-inc-innorve-skill-architecture
This source entry does not include full markdown content beyond metadata.
This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.
Related by shared tags or category signals.
Use when deciding whether an AI skill or agent is ready to graduate from one level to the next on the Skill Maturity Ladder (Incubating → Validated → Certified → Deprecated). Walks the user through gate criteria, produces a Maturity Gate Report that documents the decision, and lists specific actions to close any gaps.
Use when authoring a new AI skill or agent capability that will be called by other systems, exposed to users, or shipped to production. Walks the author through a structured wizard and emits a Skill Contract — a machine-readable file conforming to the Innorve Skill Contract Schema v0.1 that declares inputs, outputs, evidence, side effects, risk class, approvals, and eval criteria.
Use when a team or organization is starting to introduce AI into delivery work and needs an honest map of which SDLC phases have AI today, which don't, where humans must stay in the loop, and where the real capability gaps are. Coaches the user to produce a Capability Graph (Mermaid) and a Capability Map (text) covering all seven phases — Discover, Define, Build, Verify, Release, Operate, Learn.
Use when starting an AI system that will eventually face an audit, customer security review, or regulator. Scaffolds a Governance Binder — a folder layout and template set that the team fills in as they build, so evidence accumulates in lockstep with code rather than being reconstructed under deadline pressure.