# Validate

> Run architecture model validation and interpret results. Checks registry entries against diagrams, reports orphans and errors.

- **Type:** Skill
- **Install:** `agentstack add skill-ea-toolkit-architecture-catalog-validate`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [ea-toolkit](https://agentstack.voostack.com/s/ea-toolkit)
- **Installs:** 0
- **Category:** [Agent Skills](https://agentstack.voostack.com/c/agent-skills)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [ea-toolkit](https://github.com/ea-toolkit)
- **Source:** https://github.com/ea-toolkit/architecture-catalog/tree/main/.claude/skills/validate
- **Website:** https://architecture-catalog.web.app

## Install

```sh
agentstack add skill-ea-toolkit-architecture-catalog-validate
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# Validate Architecture Model

Run the validation script and interpret results for the user.

## Workflow

1. Run: `python scripts/validate.py`
2. Parse the output
3. Summarize for the user:
   - Total elements in registry
   - Validation errors (elements in diagrams but not registered)
   - Orphan elements (registered but not in any diagram)
   - Domain maturity scores

## Response Format

```
**Validation Results**

| Metric | Count |
|--------|-------|
| Registry entries | X |
| Validation errors | X |
| Orphan elements | X |

**Errors (if any):**
[List each error with file location]

**Orphans by layer:**
[Group orphans by ArchiMate layer]

**Recommendations:**
[Suggest fixes for errors, note that orphans are expected for incomplete models]
```

## Notes

- Orphan elements are normal for incomplete models - don't alarm the user
- Validation errors are more serious - these indicate diagrams reference unregistered elements
- If user asks for JSON output, run: `python scripts/validate.py --format json`

## Source & license

This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [ea-toolkit](https://github.com/ea-toolkit)
- **Source:** [ea-toolkit/architecture-catalog](https://github.com/ea-toolkit/architecture-catalog)
- **License:** MIT
- **Homepage:** https://architecture-catalog.web.app

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/skill-ea-toolkit-architecture-catalog-validate
- Seller: https://agentstack.voostack.com/s/ea-toolkit
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.