Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsCommunityBlog
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Verify Architecture

ASecurity

Verify ClaudeVille follows its architectural rules - layer structure, adapter pattern, CLAUDE.md conventions, and file organization. Trigger after adding new files, refactoring, or modifying project structure.

16 stars
0 votes
0 copies
0 views
Added 9/28/2026
ai-agentsswiftbashnoderefactoring

Works with

cli

Security Analysis

A100/100

Scanned 9/28/2026

Install to Claude Code

$npx -y skills add honorstudio/claude-ville --skill verify-architecture --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Verify Architecture?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Verify Architecture
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/honorstudio-verify-architecture/badge)](https://www.skillsdirectory.com/skills/honorstudio-verify-architecture)

More formats (shields.io, HTML) on the badges page.

Files
SKILL.md
---
name: verify-architecture
description: Verify ClaudeVille follows its architectural rules - layer structure, adapter pattern, CLAUDE.md conventions, and file organization. Trigger after adding new files, refactoring, or modifying project structure.
---

# Architecture Verification

Verify the ClaudeVille project adheres to its documented architecture and conventions defined in CLAUDE.md.

## Check Items

### 1. Layer Structure

Verify `claudeville/src/` follows the defined layers:

```
src/
├── domain/          (entities, value-objects, events)
├── application/     (managers, services)
├── infrastructure/  (WebSocketClient, data sources)
├── presentation/    (renderers, UI components)
│   ├── character-mode/
│   ├── dashboard-mode/
│   └── shared/
└── config/          (constants, theme, i18n, buildings)
```

- **PASS**: All directories exist with appropriate files
- **WARN**: Empty directories or misplaced files
- **FAIL**: Missing core directories (domain, application, presentation)

### 2. No Framework Dependencies

Verify the project uses pure HTML/CSS/JS with no npm dependencies:

- `package.json` should only have `scripts`, no `dependencies` or `devDependencies`
- No `node_modules/` directory
- All imports use relative paths or ES modules

- **PASS**: No external dependencies
- **FAIL**: npm dependencies found

### 3. Adapter Pattern Compliance

Verify `claudeville/adapters/` follows the multi-provider pattern:

- `index.js` exists and acts as registry
- Each adapter (`claude.js`, `codex.js`, `gemini.js`) exports consistent interface
- Adapters detect installed CLIs, not hard-require them

- **PASS**: All adapters present with consistent exports
- **WARN**: Adapter missing but referenced in index.js
- **FAIL**: index.js missing or broken adapter interface

### 4. CSS Convention

Verify no `position: fixed` in CSS files (except modal/toast as per CLAUDE.md rules):

```bash
grep -rn "position.*fixed" claudeville/css/ --include="*.css"
```

Allowed exceptions: `modal.css`, toast-related code

- **PASS**: No violations or only in allowed files
- **FAIL**: `position: fixed` in layout/sidebar/topbar CSS files

### 5. ES Module Consistency

Verify all JS files in `src/` use ES module syntax:

- Files should use `import`/`export`, not `require()`/`module.exports`
- Exception: `server.js` and `adapters/` (Node.js CommonJS)

- **PASS**: All src/ files use ES modules
- **FAIL**: Mixed module systems in src/

### 6. Port Configuration

Verify server port is 4000 as documented in CLAUDE.md:

- `claudeville/CLAUDE.md` mentions port 4000
- `claudeville/server.js` uses `const PORT = 4000`

- **PASS**: Port 4000 documented and configured
- **FAIL**: Port mismatch or not documented

### 7. Widget Integration

Verify widget directory follows the documented structure:

```
widget/
├── Sources/main.swift
├── Resources/
│   ├── widget.html
│   └── widget.css
├── Info.plist
└── build.sh          (must be executable)
```

- **PASS**: All files present, build.sh executable
- **WARN**: widget.html/css exist but are stale (widget uses Swift-generated HTML now)
- **FAIL**: Missing main.swift or build.sh

Attribution

honorstudiohonorstudio
View sourceMore from honorstudio →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Ultra-compressed communication mode that cuts output tokens while keeping technical accuracy. Levels: lite, full, ultra and the wenyan variants. Use for /caveman, "caveman mode", "talk like caveman", "be brief" or "less tokens".

1074701 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

695601 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3351 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

691 votes

math-skill

A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling

381 votes
View all in ai-agents →