agentleFS
srikanth-manivannansrikanth-manivannan/claude-agent-factory/skills/architecture/system-design-reviewer/SKILL.md

system-design-reviewer

Skill1 starsChanged 5 months agoMITView on GitHub

Use this to review a system or software design against scalability, reliability, security, and cost.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Note strengths: Call out what is sound and should be preserved.

    line 61

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

System Design Reviewer

Use this to review a system or software design against scalability, reliability, security, and cost.

Tech profile — Technology: any · Language: n/a · Stack: n/a · Toolchain: n/a · Domain: architecture (Pure-reasoning skill — reviews any design, from a microservice to a data platform.)

When to use this skill

  • Reviewing a proposed design/RFC before implementation begins.
  • Auditing an existing system for quality-attribute risks.
  • Preparing input for an architecture decision or ADR.

When NOT to use this skill

  • Choosing between design options — use architecture/tradeoff-analyzer.
  • Planning a migration of an existing system — use architecture/migration-planner.
  • Line-by-line code review — use a code-review workflow.

Prerequisites

  • A described design (diagram, doc, or narrative) and its goals/constraints.
  • The expected scale/load and any compliance requirements, if known.

Inputs

InputRequiredDescription
designyesThe design to review (doc, diagram, or description)
goalsyesWhat the system must achieve
expected_scalenoLoad/growth expectations (assumed + stated if absent)
constraintsnoBudget, compliance, team, deadline constraints

Instructions

  1. Restate the design + goals. Summarize the design in your own words and the goals it serves. If the design is ambiguous, list the clarifying questions rather than guessing.
  2. Map the critical path. Identify the request/data flow that matters most and its dependencies.
  3. Review against quality attributes, each producing findings:
    • Scalability — bottlenecks, statefulness, horizontal-scaling path.
    • Reliability — single points of failure, failure modes, graceful degradation.
    • Security — trust boundaries, authz, data protection (defer depth to security-review, but flag here).
    • Cost & operability — cost drivers, observability, maintenance burden.
    • Data — consistency model, growth, integrity.
  4. Severity-tag every finding 🔴 blocker / 🟠 major / 🟡 minor, each with a concrete recommendation (see /standards/review-process.md).
  5. Note strengths. Call out what is sound and should be preserved.
  6. Give a verdict — approve / approve-with-changes / needs-rework — driven by the highest open severity.
  7. List assumptions. Especially any assumed scale/constraints.

Output

A structured design review: restated design, critical-path map, severity-tagged findings per quality attribute (with recommendations), strengths, a verdict, and assumptions. Maps directly onto the architecture-review checklist.

Constraints & safety

  • Evidence-based. Each finding cites a part of the design; no vague criticism.
  • No rewrite. Recommend; do not silently redesign the system.
  • Defer deep security to security-audit/security-review but never skip flagging.
  • Conforms to /standards/prompt-engineering.md.

Examples

Minimal below; full reviews in EXAMPLES.md.

Given: a single-instance API + single-DB design expecting 50× growth. Produces: findings incl. 🔴 single point of failure (DB), 🟠 stateful API blocks horizontal scaling, with recommendations, plus a verdict of needs-rework.

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.