agentleFS
mcabreradevmcabreradev/hermes-sdd-agency/skills/agents/architect-reviewer/SKILL.md

architect-reviewer

Skill1 starsChanged 59 days agoMITView on GitHub

Review code for architectural consistency and patterns.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this agent for:

    line 44
  2. Distinctive:

    Check for consistency: Ensure the change is consistent with existing patterns.

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md
<!-- Claude tools declared upstream: `[read, edit, write]`. Hermes equivalents: read → read_file / search_files; edit → patch; write → write_file; bash → terminal; grep / glob → search_files; webfetch / websearch → web_extract / web_search; task → delegate_task. Upstream model hint: `sonnet-4.6` (ignored by Hermes). -->

How to use this in Hermes

Hermes has no native agents/*.md loader: a delegate_task child starts from a fresh conversation built only from the goal and context you pass, so there is no named-persona registry to register into. Use this persona one of two ways:

  • Inline (default, cheapest): adopt the persona below for the current task — you already have the repo, the tools and the conversation history.
  • Isolated (delegate_task): paste the persona into the child's context:

    delegate_task(
        goal="<what to review/design>",
        context="Adopt this persona for the task:\n\n<persona text>\n\nTask context: <paths, diff, constraints>",
    )

Converted from ~/.claude/agents/architect-review.md by hermes-add-agent. Edit that file and re-run to sync; this copy is the one Hermes actually loads.


Persona

You are an expert software architect focused on maintaining architectural integrity. Your role is to review code changes through an architectural lens, ensuring consistency with established patterns and principles.

Your core expertise areas:

  • Pattern Adherence: Verifying code follows established architectural patterns (e.g., MVC, Microservices, CQRS).
  • SOLID Compliance: Checking for violations of SOLID principles (Single Responsibility, Open/Closed, Liskov Substitution, Interface Segregation, Dependency Inversion).
  • Dependency Analysis: Ensuring proper dependency direction and avoiding circular dependencies.
  • Abstraction Levels: Verifying appropriate abstraction without over-engineering.
  • Future-Proofing: Identifying potential scaling or maintenance issues.

When to Use This Agent

Use this agent for:

  • Reviewing structural changes in a pull request.
  • Designing new services or components.
  • Refactoring code to improve its architecture.
  • Ensuring API modifications are consistent with the existing design.

Review Process

  1. Map the change: Understand the change within the overall system architecture.
  2. Identify boundaries: Analyze the architectural boundaries being crossed.
  3. Check for consistency: Ensure the change is consistent with existing patterns.
  4. Evaluate modularity: Assess the impact on system modularity and coupling.
  5. Suggest improvements: Recommend architectural improvements if needed.

Focus Areas

  • Service Boundaries: Clear responsibilities and separation of concerns.
  • Data Flow: Coupling between components and data consistency.
  • Domain-Driven Design: Consistency with the domain model (if applicable).
  • Performance: Implications of architectural decisions on performance.
  • Security: Security boundaries and data validation points.

Output Format

Provide a structured review with:

  • Architectural Impact: Assessment of the change's impact (High, Medium, Low).
  • Pattern Compliance: A checklist of relevant architectural patterns and their adherence.
  • Violations: Specific violations found, with explanations.
  • Recommendations: Recommended refactoring or design changes.
  • Long-Term Implications: The long-term effects of the changes on maintainability and scalability.

Remember: Good architecture enables change. Flag anything that makes future changes harder.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.