Skills for Real Engineers. Straight from my .agents directory.
brooks-audit
Agent skill fromhyhmrright/brooks-lint
Architecture audit that maps module dependencies, checks layering integrity, and flags structural decay across a codebase, drawing on twelve classic engineering books. Triggers when: user asks to audit architecture, review folder/module structure, check for circular imports, understand how the codebase is organized, or asks "does this follow clean architecture?" or "why does everything depend on everything?". Also triggers for onboarding requests: "explain this codebase to a new developer" or "give me a codebase tour" (use onboarding mode). Do NOT trigger for: PR-level code review (use brooks-review) or line-level refactoring questions — this skill analyzes structural/module-level concerns, not individual functions.
How to install brooks-audit
npx skills add hyhmrright/brooks-lint# or add only this skill to Claude Code: copy the folder
skills/brooks-audit/
# into
~/.claude/skills/brooks-audit/ (all projects)
.claude/skills/brooks-audit/ (one project)
1# Brooks-Lint — Architecture Audit23## Setup45Read in order:671. `../_shared/common.md` — Iron Law, Project Config, Report Template, Health Score82. `../_shared/source-coverage.md` — book coverage, exceptions, tradeoffs93. `../_shared/decay-risks.md` — symptom definitions and source attributions104. `architecture-guide.md` (this directory) — the audit framework1112## Process1314**Onboarding mode:** If the user asks for an onboarding report, codebase tour, or15"explain this codebase to a new developer", read `onboarding-guide.md` from this16directory and follow it instead of `architecture-guide.md`. This mode explains rather17than diagnoses — no Health Score, no Iron Law findings.1819**Scope:** if the user did not specify files or a directory, apply Auto Scope Detection20(`../_shared/common.md`) first.21221. Gather codebase context and draw the module dependency graph as Mermaid (Steps 0–1 of the guide)232. Scan for each decay risk in the order specified (Steps 2–4 of the guide)243. Assign node colors in the Mermaid diagram based on findings (red/yellow/green) — after Step 4254. Run the Testability Seam Assessment (Step 5 of the guide)265. Run the Conway's Law check (Step 6 of the guide)276. Output using the Report Template from common.md — Mermaid graph FIRST, then Findings2829**Mode line in report:** `Architecture Audit`
Excerpt shown under the repository's MIT license.
More skills in brooks-lint
Similar skill repositories
An agentic skills framework & software development methodology that works.
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Public repository for Agent Skills
Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
