Skip to content
Agentmart
Submit a tool

architecture-review

Review an existing or proposed architecture against requirements, boundaries, risks, operability, and tradeoffs.

Skill by Mr-Wolv

IndexedMIT
Write a review

Chalk Labs

Need help deploying architecture-review?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/mr-wolv-architecture-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review an existing or proposed architecture against requirements, boundaries, risks, operability, and tradeoffs. Use when assessing architecture quality, reviewing design proposals, or checking whether a system structure fits its constraints.

Use cases: design

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/architecture-review

What's inside

Skill name
architecture-review
Description
Review an existing or proposed architecture against requirements, boundaries, risks, operability, and tradeoffs. Use when assessing architecture quality, reviewing design proposals, or checking whether a system structure fits its constraints.
License
MIT
Instructions
211 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Architecture Review

Review an architecture as a system of decisions, boundaries, and tradeoffs.

Use this skill to evaluate whether an existing or proposed architecture is a good fit for the problem it is supposed to solve. The goal is not to redesign everything. The goal is to identify the most important structural strengths, weaknesses, risks, and mismatches.

## When to use

- Reviewing a proposed system design before implementation
- Assessing whether an existing architecture still fits current requirements
- Evaluating module boundaries, dependency direction, and responsibility allocation
- Reviewing a service decomposition, integration model, or deployment shape
- Comparing architecture options against constraints like scale, reliability, cost, security, or team capacity
- Preparing architecture feedback for a document, ADR, proposal, or technical review

## Boundary

Use this skill to evaluate an existing or proposed architecture as a whole-system or multi-boundary structure.

Use `design-review` instead when the artifact under review is a more local solution shape such as a module design, workflow, interface, or feature proposal rather than the architecture of the wider system.

Use synthesis skills such as `architecture-patterns`, `api-and-interface-design`, `design-an-interface`, or `codebase-design` when the primary need is to create or reshape a design rather than to review one.

## When not to use

- Pure code-quality review of a diff; use code review skills instead
- Writing the initial architecture from scratch; use architecture/design skills for synthesis
- Producing a formal ADR only; use ADR-focused skills for decision recording

## Review dimensions

Evaluate the architecture across these dimensions.

### 1. Problem fit

Check whether the structure matches the actual problem.

Questions:

- What requirements is this architecture trying to satisfy?
- Which constraints appear to be primary: scale, latency, reliability, compliance, cost, delivery speed, team familiarity?
- Is the architecture proportionate to the problem, or is it underpowered or overengineered?
- Does it solve today's problem only, or is it making justified bets on future needs?

### 2. Boundaries and cohesion

Check whether responsibilities are placed sensibly.

Questions:

- Are modules/services/components organized around cohesive responsibilities?
- Are boundaries explicit, or are concepts leaking across layers?
- Do modules change for one reason, or many unrelated reasons?
- Is shared logic truly shared, or duplicated with slight drift?

### 3. Dependencies and coupling

Check whether dependency flow supports maintainability.

Questions:

- Do dependencies point in the expected direction?
- Are there circular or backchannel dependencies?
- Are shared modules becoming dumping grounds?
- Does any area create excessive coordination cost because too many parts depend on it?

### 4. Operability

Check whether the system can be run and supported in practice.

Questions:

- Can the architecture be monitored, debugged, and operated by the actual team?
- Are failure modes visible and diagnosable?
- Are deployment, rollback, and recovery paths practical?
- Does the design introduce operational burden disproportionate to its value?

### 5. Reliability and failure handling

Check how the design behaves under stress and failure.

Questions:

- What are the critical dependencies and single points of failure?
- How does the system degrade when dependent components fail?
- Are retry, timeout, idempotency, fallback, or backpressure concerns handled where needed?
- Are consistency expectations explicit and realistic?

### 6. Security and trust boundaries

Check whether trust boundaries are visible and defended.

Questions:

- Where does untrusted input enter the system?
- Are authentication, authorization, and secrets-handling concerns placed in the right layers?
- Are data flows across trust boundaries explicit?
- Does the architecture centralize too much privilege in one place?

### 7. Delivery and evolution

Check whether the architecture can change safely.

Questions:

- Can teams modify one area without destabilizing unrelated areas?
- Does the architecture support incremental delivery?
- Are there clear seams for refactoring or replacement?
- Will future changes require broad cross-cutting edits?

## Review workflow

### Step 1: Establish context

Before judging the architecture, gather the minimum context:

- system purpose
- main requirements and constraints
- scale assumptions

From Mr-Wolv/Skill_Playground_Bakr101_2026, MIT.

More from Mr-Wolv/Skill_Playground_Bakr101_2026

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jul 7, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from Mr-Wolv

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get architecture-review running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying architecture-review?

CallGet help
Cite this page

architecture-review skill. Agent Mart. https://agentmart.dev/skills/mr-wolv-architecture-review (last updated 2026-10-24)