agentsclimarketplace

Architecture review

Skill JoaoAlavarse/cursor-config/skills/architecture-review

Configuração global do Cursor: user rules, agent skills, slash commands e hooks com scripts de instalação.

Install
npx -y skills add JoaoAlavarse/cursor-config --skill architecture-review

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

2 things to look at

  • 15 days oldThe repository was created 15 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 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

Evaluates system architecture, module boundaries and design decisions to identify structural risks and improvement opportunities. Use when reviewing architecture, system design, or module structure.

SKILL.md

3.0 KB, as published. Nobody here has run it

Objective

Evaluate the system architecture to identify structural strengths, weaknesses, risks and improvement opportunities.

Focus on long-term maintainability, scalability, modularity and system evolution rather than implementation details.

Context

Before reviewing:

  1. If project rules are available, read and follow them.
  2. Otherwise, infer the project's architectural conventions from the existing codebase.
  3. Respect the project's design decisions unless there is clear evidence they create significant problems.
  4. Do not assume the project follows current architectural best practices.
  5. Evaluate the architecture within the project's business and technical constraints.

Review Process

  1. Understand the system's purpose and requirements.
  2. Identify the major components and their responsibilities.
  3. Analyze module boundaries and dependencies.
  4. Evaluate cohesion and coupling.
  5. Review data flow and communication patterns.
  6. Assess maintainability, scalability, extensibility, reliability and resilience.
  7. Identify architectural risks, technical debt and unnecessary complexity.
  8. Recommend improvements only when the expected long-term benefits justify the associated changes.

Review Guidelines

Base conclusions on observable evidence.

Clearly distinguish facts, assumptions and recommendations.

Avoid recommending architectural changes without a clear justification.

Prefer incremental architectural improvements over large redesigns.

Respect intentional architectural decisions unless they introduce significant long-term costs.

Evaluate trade-offs rather than seeking an ideal architecture.

Avoid describing architectural decisions as universally good or bad.

Evaluate the trade-offs each decision introduces.

Evaluate whether the current architecture is appropriate for the system's current scale and complexity.

Evaluate whether the architecture enforces clear responsibility boundaries between components.

Consider business constraints alongside technical concerns.

Identify opportunities to simplify the architecture without reducing flexibility.

Avoid optimizing for hypothetical future requirements without evidence.

Avoid suggesting new technologies unless they clearly solve an existing problem.

Output

Summary

Provide a high-level assessment of the architecture.

Strengths

Identify architectural decisions that work well.

Issues Identified

Describe structural weaknesses, architectural risks and unnecessary complexity.

Risks

Explain the long-term impact of the identified issues.

Recommendations

Recommend only improvements that provide meaningful long-term value and explain their trade-offs.

Priority

Prioritize the recommendations based on expected impact, implementation effort and risk reduction.

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.