Is the Architecture Audit skill free?

Yes. The skill itself is free from helderberto/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.

What is the Architecture Audit SkillProof Score?

8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.

How do I install Architecture Audit?

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 Audit 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 Audit

Audits a codebase for shallow/coupled modules and writes a deep-module refactor PRD.

by helderberto · helderberto/agent-skills

Works with setup

Install — copy the command Download source ↗

Test report

Verdict: Works with setup
Score: 8.0/10
Tested: Jul 15, 2026
Environment: Claude Code 2.x (agent harness)
Upstream re-checked: Aug 10, 2026 · 17f16a5

SKILL.md leans on a sibling skill folder ('../codebase-design/SKILL.md' and its DEEPENING.md) for its core vocabulary and dependency-category logic -- copy just architecture-audit/ per the standard single-directory install and those links 404 locally. Ran a real audit against a 4-file throwaway app with a textbook pass-through service; the skill-guided run produced a genuinely more actionable deliverable than an unaided baseline -- a full improvement-template.md PRD (problem/interface/dependency-strategy/migration/risks) vs. the baseline's two throwaway sentences.

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

Installs cleanly 4/5
Triggers reliably 5/5
Output vs. baseline 7/10
Docs & honesty 4/5

What Architecture Audit does

Explores a codebase for architectural friction (pass-through wrappers, temporal decomposition, tight coupling at seams) and writes an improvement PRD proposing a refactor toward deep modules (small interface, large implementation), with alternative interface designs and a migration plan. Triggers on requests to audit architecture or find structural friction across a codebase; explicitly not for single-module interface design or diff-level code review.

How to install Architecture Audit

git clone https://github.com/helderberto/agent-skills
mkdir -p ~/.claude/skills
cp -r agent-skills/skills/architecture-audit ~/.claude/skills/architecture-audit
cp -r agent-skills/skills/codebase-design ~/.claude/skills/codebase-design   # required sibling dependency, see notes

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

Commands — how to trigger Architecture Audit

/architecture-audit Audits a codebase for shallow/coupled modules and writes a deep-module refactor PRD.

It also activates on plain-language prompts like these:

Audit this codebase for architectural friction and propose a refactor
Find the shallow, pass-through modules coupling this service together
Write a PRD proposing deeper module boundaries for this messy repo

Frequently asked questions

Is the Architecture Audit skill free?: Yes. The skill itself is free from helderberto/agent-skills. SkillProof publishes the install command and an independent test verdict at no cost.
Does Architecture Audit work with Claude Code?: We tested it with Claude Code 2.x (agent harness) on Jul 15, 2026. Verdict: Works with setup. SKILL.md leans on a sibling skill folder ('../codebase-design/SKILL.md' and its DEEPENING.md) for its core vocabulary and dependency-category logic -- copy just architecture-audit/ per the standard single-directory install and those links 404 locally. Ran a real audit against a 4-file throwaway app with a textbook pass-through service; the skill-guided run produced a genuinely more actionable deliverable than an unaided baseline -- a full improvement-template.md PRD (problem/interface/dependency-strategy/migration/risks) vs. the baseline's two throwaway sentences.
What is the Architecture Audit SkillProof Score?: 8.0/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 7/10, docs & honesty 4/5.
How do I install Architecture Audit?: 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 Audit 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.