# Image Analyzer

> Inspect local or supplied images with available Codex or Hermes vision capabilities. Use for OCR, visual description, object inspection, layout review, comparison, and structured extraction.

- **Type:** Skill
- **Install:** `agentstack add skill-rylaispirit-rylai-codex-hermes-skills-image-analyzer`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [Rylaispirit](https://agentstack.voostack.com/s/rylaispirit)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [Rylaispirit](https://github.com/Rylaispirit)
- **Source:** https://github.com/Rylaispirit/rylai-codex-hermes-skills/tree/main/skills/image-analyzer

## Install

```sh
agentstack add skill-rylaispirit-rylai-codex-hermes-skills-image-analyzer
```

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

## About

> Rylai Codex-Hermes Edition | Original portable workflow by Rylai

# Image Analyzer

Analyze the supplied image itself before making claims.

## Workflow

1. Resolve the exact local file, attachment, or user-approved URL.
2. Inspect the original resolution when small text, fine detail, or cropping matters.
3. Match the analysis to the request: description, OCR, layout, objects, comparison, or extraction.
4. Separate direct observations from interpretation and uncertainty.
5. Preserve reading order for OCR and mark unreadable regions instead of guessing.
6. For structured extraction, define the schema first and use `null` for unavailable fields.
7. When comparing images, use the same checklist for every image.
8. Return concise evidence and note any resolution or visibility limits.

## Runtime Routes

- Codex: use the available image viewer or native vision capability.
- Hermes: use its configured vision tool.
- Use an external OCR or vision service only when the user approves it and the
  required credentials are already configured.

## Safety

- Do not infer sensitive identity, health, ethnicity, or exact location withou
  reliable evidence and a legitimate user request.
- Do not claim that an object, logo, person, or place is certain when the image
  only supports a tentative match.
- Never upload a private image to an external service without user approval.

## Source & license

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

- **Author:** [Rylaispirit](https://github.com/Rylaispirit)
- **Source:** [Rylaispirit/rylai-codex-hermes-skills](https://github.com/Rylaispirit/rylai-codex-hermes-skills)
- **License:** MIT

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-rylaispirit-rylai-codex-hermes-skills-image-analyzer
- Seller: https://agentstack.voostack.com/s/rylaispirit
- 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%.