Architecture Reviewer

What it does

When your agent uses it

• Making architectural decisions
• Planning features
• Designing new components
• Validating that proposed changes align with Clean Architecture principles

Example prompts

• “review architecture”
• “check design”
• “does this fit”
• “/architecture-reviewer”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

1. 1Design Decisions - Advise where new code should live (which layer, which module)
2. 2Pattern Compliance - Ensure proposals follow Clean Architecture and project patterns
3. 3Dependency Direction - Verify dependencies flow inward (presentation → application → domain)
4. 4Interface Design - Guide port/adapter boundaries and abstractions
5. 5TypeSpec Models - Review domain model changes in tsp/ for consistency

What it can do on your machine

Read from SKILL.md and the folder at commit 0304cfc. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  No scripts in the folder and no shell commands in SKILL.md (its code samples are markdown).

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Architecture Reviewer loads about 808 tokens when it runs. Until then it costs about 106 tokens; SKILL.md has 195 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~106

When it runs · the whole SKILL.md, loaded when a task matches

~808

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from shep-ai/shep at commit 0304cfc, republished under its MIT licence (© shep-ai). 195 words, ~808 tokens.

name

architecture-reviewer

description

Use when making architectural decisions, planning features, designing new components, reviewing PRs, or validating that proposed changes align with Clean Architecture principles. Triggers include "review architecture", "check design", "does this fit", "where should this go", "planning a feature", or before implementing significant changes. Part of the Shep autonomous SDLC platform — https://shep.bot

metadata.version

1.0.0

metadata.author

Shep AI (https://shep.bot)

metadata.homepage

https://shep.bot

metadata.repository

https://github.com/shep-ai/shep

metadata.context

fork

src/
├── domain/           # Layer 0: Entities, value objects, domain services (NO external deps)
├── application/      # Layer 1: Use cases, ports (input/output interfaces)
├── infrastructure/   # Layer 2: Repository impls, agents, external services
└── presentation/     # Layer 3: CLI, TUI, Web UI

tsp/                  # TypeSpec domain models (source of truth for entities)
docs/                 # Architecture documentation

## Architecture Review

### Recommendation

[Where this should live and why]

### Proposed Structure

[Files to create/modify with their locations]

### Interfaces Needed

[Any new ports or abstractions required]

### Concerns

[Any architectural issues or trade-offs to consider]

### Alignment Check

- [ ] Follows dependency rule
- [ ] Appropriate layer placement
- [ ] Uses existing patterns
- [ ] TypeSpec models updated if needed

© shep-ai, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/architecture-reviewer of shep-ai/shep.

Open the folder on GitHubat commit 0304cfc