Does this skill work on Windows or Linux?

This skill is primarily optimized for macOS as it leverages the built-in Vision framework for high-accuracy OCR. However, it can be adapted for Linux or Windows by using Tesseract OCR.

Can it handle screenshots containing sensitive information?

The OCR process is performed locally. Additionally, the skill's workflow includes a final check phase to remind users to desensitize or mask tokens and passwords.

What image formats are supported?

The skill supports most common image formats, including PNG, JPG, JPEG, GIF, and WebP.

Do I need to name my screenshots before using this skill?

No. One of the primary features of this skill is its ability to take unnamed, timestamp-based files and rename them semantically (e.g., '01-install-plugin.png') based on their content.

How does it determine where to insert images in the document?

The skill analyzes the OCR text results from the screenshots and matches them against the logical flow and keywords found in your rough Markdown outline.

Screenshot-to-Tutorial Generator

Name: Screenshot-to-Tutorial Generator
Author: opensourceways

byopensourceways

0•

Learning & Documentation

Transforms folders of raw screenshots and rough notes into professionally formatted, illustrated step-by-step documentation.

This skill streamlines the tedious process of manual documentation by automating screenshot processing and content structure. It utilizes macOS-native OCR via the Vision framework to identify UI elements within images, renames files semantically for better organization, and intelligently inserts them into a polished Markdown tutorial. Whether you're documenting a new feature or creating a setup guide, it handles the heavy lifting of image mapping and formatting, ensuring consistent, professional, and accessible technical documentation with minimal manual effort.

Key Features

01Intelligent Markdown structure generation with hierarchical headings

02Seamless alignment of step-by-step text with corresponding images

03Semantic file renaming based on identified UI actions and objects

04Comprehensive final document verification for broken links and formatting

050 GitHub stars

06Automated image content recognition using macOS Vision OCR technology

Use Cases

01Rapidly generating illustrated README files for software repositories

02Converting quick snip-and-save sessions into customer-facing help guides

03Standardizing internal technical documentation and onboarding materials

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add opensourceways/agent-skills operation

For use in Claude.ai and ChatGPT

Key Features

01Intelligent Markdown structure generation with hierarchical headings

02Seamless alignment of step-by-step text with corresponding images

03Semantic file renaming based on identified UI actions and objects

04Comprehensive final document verification for broken links and formatting

050 GitHub stars

06Automated image content recognition using macOS Vision OCR technology

Use Cases

01Rapidly generating illustrated README files for software repositories

02Converting quick snip-and-save sessions into customer-facing help guides

03Standardizing internal technical documentation and onboarding materials

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add opensourceways/agent-skills operation

For use in Claude.ai and ChatGPT