agentleFS
viknesh20-20viknesh20-20/claude-code-tool-kit/.claude/skills/architecture-review/SKILL.md

architecture-review

Skill7 starsChanged 7 months agoMITView on GitHub

Reviews the system architecture for structural issues, dependency cycles, layer violations, scalability concerns, and single points of failure. Use for periodic health checks or before major new features.

78 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-stories, story-done and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • lilangMaxSkill

    create-stories

    Break a single epic into implementable story files. Reads the epic, its GDD, governing ADRs, and control manifest. Each story embeds its GDD requirement TR-ID, ADR guidance, acceptance criteria, story type, and test evidence path. Run after /create-epics for each epic.

    Also in 11 projects that use this

  • lilangMaxSkill

    story-done

    End-of-story completion review. Reads the story file, verifies each acceptance criterion against the implementation, checks for GDD/ADR deviations, prompts code review, updates story status to Complete, and surfaces the next ready story from the sprint.

    Also in 11 projects that use this

  • +10 more from lilangMax

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 70 edited versions we read keep these.

  • 2

    Distinctive

    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:

    Check for layer violations — e.g., presentation layer importing directly from data layer

    line 32
  2. Distinctive:

    Look for god modules — modules that everything depends on

    line 33

“Common” is measured: kept by at least 6 in 10 of the 70 edited versions of this file we could read. “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

Architecture Review

Project Structure

!find . -type f -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/vendor/*" -not -path "*/__pycache__/*" -not -path "*/target/*" -not -path "*/bin/*" -not -path "*/obj/*" -not -path "*/.next/*" -not -path "*/dist/*" -not -path "*/build/*" 2>/dev/null | head -80

Directory Layout

!tree -L 3 -I "node_modules|.git|vendor|__pycache__|target|bin|obj|.next|dist|build" 2>/dev/null || find . -type d -not -path "*/node_modules/*" -not -path "*/.git/*" -not -path "*/vendor/*" -maxdepth 3 2>/dev/null

Package/Module Config

!cat package.json go.mod Cargo.toml pyproject.toml requirements.txt *.csproj pom.xml 2>/dev/null | head -60


Review Areas

1. Project Structure & Organization

  • Is the directory layout clear and consistent?
  • Does it follow established conventions for the stack? (e.g., src/, app/, lib/, pkg/)
  • Are related files co-located or scattered?
  • Is there a clear entry point?

2. Dependency Architecture

  • Map the dependency graph between major modules/packages
  • Identify circular dependencies — modules that import each other
  • Check for layer violations — e.g., presentation layer importing directly from data layer
  • Look for god modules — modules that everything depends on
  • Assess coupling: can modules be changed independently?

3. Separation of Concerns

  • Is business logic separated from framework/transport code?
  • Are side effects (I/O, network, database) isolated at boundaries?
  • Is configuration separated from code?
  • Are there clear interfaces between layers?

4. Scalability Considerations

  • Stateless vs stateful components — which components hold state?
  • Are there bottlenecks that would fail under load?
  • Database query patterns — are they efficient at scale?
  • Caching strategy — what is cached, where, and when invalidated?
  • Background job handling — how are long-running tasks managed?

5. Reliability & Resilience

  • Single points of failure: What happens if any component goes down?
  • Error boundaries: Where do errors propagate, and are they caught?
  • Retry logic: For external service calls, is there retry with backoff?
  • Graceful degradation: Does the system handle partial failures?
  • Health checks: Are there endpoints or mechanisms to monitor health?

6. Security Architecture

  • Authentication and authorization boundaries
  • Where is input validation enforced?
  • How are secrets managed?
  • API rate limiting and abuse prevention

Output Format

Architecture Diagram (ASCII)

┌─────────┐     ┌─────────┐     ┌──────────┐
│ Frontend │────▶│   API   │────▶│ Database │
└─────────┘     └─────────┘     └──────────┘
                     │
                     ▼
               ┌───────────┐
               │  External  │
               │  Services  │
               └───────────┘

Findings Table

#AreaFindingSeverityRecommendation

Top Recommendations

Prioritized list of the most impactful architectural improvements.

Overall Health

Rate: Healthy / Needs Attention / At Risk — with reasoning.

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.