agentleFS
wolulabswolulabs/hermes-founder-os/skills/architecture-reviewer/SKILL.md

architecture-reviewer

Skill18 starsChanged 6 months agoMITView on GitHub

Specialist skill for reviewing system architecture, database design, security concerns, scaling risks, maintainability, integration risk, and technical debt. Primary output: ARCHITECTURE_REVIEW.md.

9 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

3 rules. 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 8 edited versions we read keep these.

  • 3

    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:

    Use this skill to review technical design before or during implementation.

    line 8
  2. Distinctive:

    Prefer a modular monolith for MVP unless evidence says otherwise.

    line 58
  3. Distinctive:

    Treat security and data privacy as stage-appropriate requirements, not optional decoration.

    line 60

“Common” is measured: kept by at least 6 in 10 of the 8 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 Reviewer

Use this skill to review technical design before or during implementation. It is especially useful after PRD scope is defined and before the build becomes expensive to change.

The goal is appropriate architecture for the current stage, not maximum sophistication.

Primary Output

  • ARCHITECTURE_REVIEW.md

Use This Skill For

  • System architecture review.
  • Database schema review.
  • Security and privacy concerns.
  • Scaling risk.
  • Maintainability.
  • Integration risk.
  • Technical debt assessment.

Do Not Use This Skill For

  • Market validation.
  • Writing PRDs.
  • Implementing code directly.
  • UX review.
  • Growth planning.

Default Review Structure

# ARCHITECTURE_REVIEW.md

## Executive Summary
## Current Stage
## Proposed Architecture
## Fit For MVP Scope
## Database Review
## API / Integration Review
## Mobile Store Payment Review
## Security And Privacy Review
## Scaling Risks
## Maintainability Risks
## Technical Debt
## What To Build Now
## What To Defer
## Recommendations

Principles

  • Match architecture to validated stage.
  • Prefer a modular monolith for MVP unless evidence says otherwise.
  • Defer scaling work until bottlenecks are real.
  • Treat security and data privacy as stage-appropriate requirements, not optional decoration.
  • Flag AI, data, and integration risks early.
  • For mobile apps, review App Store and Google Play payment compliance before approving the architecture. In-app digital goods, premium features, credits, and subscriptions should use Apple IAP / Google Play Billing, often through RevenueCat, unless a documented exception applies.

References

  • references/architecture-review-framework.md for general review.
  • references/database-review.md for schema and data modeling.
  • references/security-review.md for security/privacy.
  • references/scaling-review.md for scaling and reliability.
  • references/mobile-payment-review.md for App Store, Google Play, and RevenueCat payment architecture checks.

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.