agentleFS
saemihemmasaemihemma/lead-producer-oss/.claude/skills/team-architecture-review/SKILL.md

team-architecture-review

Skill2 starsChanged 3 months agoMITView on GitHub

Architecture review team: system design, migrations, hard-to-reverse decisions, with required Mermaid diagram. Use for new systems, major refactors, or technology choices.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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:

    Every review must ship with a verified Mermaid diagram:

    line 33
  2. Distinctive:

    Run specialist perspectives in parallel.

    line 41
  3. Distinctive:

    Call out what is not in scope and the top failure modes.

    line 43
  4. Distinctive:

    When specialists disagree, rank by reversibility: hardest-to-change decision gets priority attention.

    line 61
  5. Distinctive:

    Do not expand scope to adjacent systems unless the boundary question depends on it.

    line 64
  6. Distinctive:

    Do not average conflicting specialist opinions.

    line 66

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

Architecture Review Team

Purpose

Evaluate whether system shape is structurally sound, scalable, secure, strategically sensible, and realistic to ship. Prioritize by reversibility.

Composition

  • role-software-architect: structure, boundaries, contracts, decomposition
  • role-cto: strategic fit, long-term cost, organizational implications
  • role-scalability-engineer: load paths, bottlenecks, scaling risk
  • role-security-engineer: threat surface, security constraints, blast radius
  • role-technical-product-manager: delivery feasibility, dependencies, migration risk
  • Synthesis: conflict handling, acceptance

Use When

  • Designing new system or major subsystem
  • Evaluating migration, decomposition, hard-to-reverse contract
  • Reviewing API/service boundaries or major data-model choices
  • Post-incident architecture review

Do NOT Use When

  • Small implementation review or routine refactor
  • Product prioritization or roadmap value
  • Deployment-only with no architecture decision
  • Narrow interface shape fitting workflow-design-interface-options

Required Diagram

Every review must ship with a verified Mermaid diagram:

  • Diagram what IS, not aspirational
  • Label services, stores, external dependencies, data flows
  • Distinguish sync/async paths when it matters
  • Validate against code or evidence before accepting

Workflow

  1. Load truth sources: architecture docs, code reality, constraints, and what already exists.
  2. Run specialist perspectives in parallel; sequence only when dependent.
  3. Rank findings by reversibility: hardest-to-change first.
  4. Call out what is not in scope and the top failure modes.
  5. Resolve conflicts explicitly.
  6. Synthesize for acceptance.

Default Output

ARCHITECTURE REVIEW
===================
System Shape: existing components, boundaries, ownership, major contracts
Risk Review: scalability, security, migration/rollback risks
Failure Modes: top failure modes, out-of-scope work
Reversibility: hardest-to-change decisions, attention order
Artifact: verified Mermaid diagram
Verdict: Accept / Rework / Escalate, open questions

Conflict Resolution

  • Architect owns structural decisions. CTO has veto on strategic misalignment. Security can block on exploitability.
  • When specialists disagree, rank by reversibility: hardest-to-change decision gets priority attention.

Anti-Drift Rules

  • Do not expand scope to adjacent systems unless the boundary question depends on it.
  • State what already exists before recommending new structure.
  • Do not average conflicting specialist opinions; resolve them explicitly.
  • Diagram must match code reality, not aspirational architecture.

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.