image-analyzer

Inspect images for OCR, visual description, object detection, and structured extraction.

55|41|Updated Aug 9, 2026
One-click install
npx skills add https://github.com/Rylaispirit/rylai-codex-hermes-skills --skill image-analyzer-rylaispirit
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-analyzer
Source: https://github.com/Rylaispirit/rylai-codex-hermes-skills/tree/main/skills/image-analyzer
Command: npx skills add https://github.com/Rylaispirit/rylai-codex-hermes-skills --skill image-analyzer-rylaispirit

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Analyzing images manually is slow and error-prone when you need to extract text, describe visual content, or compare multiple images. This Skill provides a structured workflow for inspecting supplied images using available vision tools, ensuring observations are separated from interpretation and uncertainty is clearly marked. ## Core Features & Use Cases - OCR and Text Extraction: Read text from images while preserving reading order and marking unreadable regions instead of guessing. - Visual Description and Object Inspection: Describe image content, identify objects, review layouts, and compare multiple images using a consistent checklist. - Structured Data Extraction: Define a schema first and extract fields with null values for unavailable data, producing machine-readable output. - Use Case: Imagine you receive a photo of a receipt and need the vendor name, date, and total amount. Use this Skill to extract those fields into a structured format, with unreadable characters explicitly flagged rather than guessed. ## Quick Start Use the image-analyzer skill to describe this attached image and extract any visible text into a structured format.

Frequently Asked Questions about image-analyzer

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract text from an image using AI vision tools?▼

Provide the image file or approved URL to the vision-capable agent, which reads text while preserving reading order. Unreadable regions are marked explicitly rather than guessed, and results note any resolution limits affecting accuracy.

How to compare multiple images for differences?▼

Supply all images and request a comparison using the same checklist applied to every image. The workflow inspects each image at original resolution when fine detail matters and reports observations separately from interpretation.

Can I use external OCR services with image analysis?▼

External OCR or vision services are used only when the user approves and required credentials are already configured. Private images are never uploaded to external services without explicit user approval.

What image formats and sources does vision analysis support?▼

The workflow accepts local files, attachments, or user-approved URLs. It inspects original resolution when small text or fine detail matters, and notes visibility limits in the returned evidence.

What are the limitations of AI image analysis?▼

Analysis cannot reliably infer sensitive identity, health, ethnicity, or exact location without strong evidence. Tentative matches for objects, logos, or places are flagged as uncertain rather than stated as fact.