agentsclimarketplace

Boundary review

Skill jukrap/ai-agent-playbook/skills/architecture/boundary-review

Reusable AI agent skills, project templates, and guardrails for safer software maintenance and delivery.

Install
npx -y skills add jukrap/ai-agent-playbook --skill boundary-review

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when reviewing architecture boundaries, FSD layers, DDD modules, monorepo package ownership, dependency direction, or cross-module coupling.

SKILL.md

1.3 KB, as published. Nobody here has run it

Boundary Review

Use this as the primary architecture skill for module and layer boundaries.

Workflow

  1. Identify the intended architecture boundary from code, docs, package layout, and imports.
  2. Check dependency direction, public APIs, shared utilities, feature ownership, and data flow.
  3. Prefer local conventions over forcing a new architecture.
  4. Recommend small boundary repairs before broad restructuring unless the user asks for redesign.

Reference

Read references/boundary-redesign-protocol.md when deciding whether to keep local conventions, apply FSD/DDD/layered rules, split packages, or propose a broader restructure.

Read references/fsd-ddd-fit-matrix.md when deciding between feature-sliced, layered, domain-driven, modular monolith, or legacy seam approaches.

Read references/modular-boundary-migration.md when a boundary repair needs staged moves, adapters, compatibility shims, or import/dependency checks.

Read references/deep-module-design-review.md when evaluating whether a module should become deeper, when comparing alternative interfaces, or when a shallow extraction may only move complexity around.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.