Can I use this skill with unstructured text?

Yes, the skill analyzes the structure and content of raw text to suggest the most likely source type and extract a relevant topic ID automatically.

How does it handle the date format in IDs?

It uses the current date in YYYY-MM-DD format or extracts an original date from the content context to ensure chronological organization.

Why use semantic IDs instead of random UUIDs?

Semantic IDs provide immediate human context, making it easier to debug workflows and browse through database entries or file systems without opening every record.

What source types does the ID Generator support?

It identifies and formats IDs for podcasts, transcripts, articles, YouTube videos, Twitter posts, raw text, and general content based on input characteristics.

Is the output format compatible with other tools?

Yes, it returns a structured JSON object including the contentId, detectedSource, and confidence score, making it easy to parse in any programming language.

Semantic ID Generator

Name: Semantic ID Generator
Author: memorysaver

bymemorysaver

•

Content Management

Generates human-readable, context-aware session IDs by analyzing content source types and extracting key themes.

About

The ID Generator skill provides a standardized way to organize agentic workflows by creating meaningful identifiers for processed content. By analyzing source metadata—such as whether a file is a podcast transcript, a YouTube description, or a news article—and extracting the core subject matter, it replaces generic random strings with descriptive IDs like 'podcast-2024-12-08-ai-healthcare'. This skill is essential for developers and teams managing large volumes of AI-generated content who need to ensure data traceability, reusability, and clear organization across their automated pipelines.

Key Features

Standardized date-based versioning in YYYY-MM-DD format
Strict JSON output for seamless integration into automated workflows
Confidence scoring and rationale for every source detection
Intelligent keyword extraction for descriptive, human-readable naming
2 GitHub stars
Automated source type classification for podcasts, articles, and transcripts

Use Cases

Enhancing traceability in agentic workflows by tagging sessions with semantic metadata
Organizing large datasets of processed transcripts for easier retrieval and indexing
Creating consistent file naming conventions for automated AI content pipelines

About

Key Features

Standardized date-based versioning in YYYY-MM-DD format
Strict JSON output for seamless integration into automated workflows
Confidence scoring and rationale for every source detection
Intelligent keyword extraction for descriptive, human-readable naming
2 GitHub stars
Automated source type classification for podcasts, articles, and transcripts

Use Cases

Enhancing traceability in agentic workflows by tagging sessions with semantic metadata
Organizing large datasets of processed transcripts for easier retrieval and indexing
Creating consistent file naming conventions for automated AI content pipelines