Is the Architecture Review skill free?

Yes. The skill itself is free from decebals/claude-code-java. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Architecture Review SkillProof Score?

8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.

How do I install Architecture Review?

Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.

Can I use Architecture Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?

The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.

Architecture Review

Macro-level Java architecture review: package layout, layering, and dependency direction

by decebals · decebals/claude-code-java

Tested · Works

Install — copy the command Download source ↗

Test report

Verdict: Tested · Works
Score: 8.4/10
Tested: Jul 21, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 6ecef7a

Fetched SKILL.md and README.md from the repo (both HTTP 200); frontmatter has valid name+description and the skill references no external script files. Built a small mock Java project with planted violations (JPA/Lombok entity in domain, Spring @Service + controller import inside a domain service, raw SQL in the controller, a 7-class util god package) and ran the skill's prescribed find/grep commands, which correctly surfaced every violation. Compared a plain-prose baseline review against a skill-following review: the skill added a severity-ranked findings table with file:line locations, an explicit organization-strategy classification, and caught the Spring @Service as a distinct High finding plus named the anemic-domain anti-pattern the baseline lumped in or missed. Improvement over a competent baseline is real but modest, hence output 6.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

Installs cleanly 5/5
Triggers reliably 5/5
Output vs. baseline 6/10
Docs & honesty 5/5

What Architecture Review does

Reviews a Java codebase at the macro level: package organization (by-layer vs by-feature vs hexagonal), dependency direction between layers, module boundaries, and structural anti-patterns like god packages and framework leaks in the domain. Triggers when the user asks to review architecture, check project/package structure, or assess clean/hexagonal architecture compliance. Outputs a severity-ranked findings table with file locations and prioritized recommendations.

How to install Architecture Review

git clone --depth 1 https://github.com/decebals/claude-code-java.git /tmp/architecture-review-src
mkdir -p ~/.claude/skills
cp -R /tmp/architecture-review-src/.claude/skills/architecture-review ~/.claude/skills/architecture-review
# Pure-knowledge skill: no external deps, scripts, or API keys.
# The bash snippets inside SKILL.md (find/grep) are inline analysis examples, not bundled files.
# Repo ships ~20 sibling Java skills under .claude/skills/ if you want the whole set.

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Architecture Review

/architecture-review Macro-level Java architecture review: package layout, layering, and dependency direction

It also activates on plain-language prompts like these:

Review this Java project's package organization
Check if this codebase follows clean architecture
Analyze the module dependency direction in this repo

Frequently asked questions

Is the Architecture Review skill free?: Yes. The skill itself is free from decebals/claude-code-java. SkillProof publishes the install command and an independent test verdict at no cost.
Does Architecture Review work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 21, 2026. Verdict: Tested · Works. Fetched SKILL.md and README.md from the repo (both HTTP 200); frontmatter has valid name+description and the skill references no external script files. Built a small mock Java project with planted violations (JPA/Lombok entity in domain, Spring @Service + controller import inside a domain service, raw SQL in the controller, a 7-class util god package) and ran the skill's prescribed find/grep commands, which correctly surfaced every violation. Compared a plain-prose baseline review against a skill-following review: the skill added a severity-ranked findings table with file:line locations, an explicit organization-strategy classification, and caught the Spring @Service as a distinct High finding plus named the anemic-domain anti-pattern the baseline lumped in or missed. Improvement over a competent baseline is real but modest, hence output 6.
What is the Architecture Review SkillProof Score?: 8.4/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 6/10, docs & honesty 5/5.
How do I install Architecture Review?: Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Architecture Review with Cursor, Copilot, Gemini CLI, Codex or other AI tools?: The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.