skills.rest
cdeistopened
cdeistopenedCOMMUNITY
Explore all skills by this author →
GitHub

wiki-extract-entities

Extract named entities from transcripts into JSON inventories with counts and sentiment.

2|1|Updated Mar 18, 2026
Search Tags:#gemini#inventory#entities#transcripts#extract#sentiment#co-occurrence
One-click install
npx skills add https://github.com/cdeistopened/skill-stack-skills --skill wiki-extract-entities
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: wiki-extract-entities
Source: https://github.com/cdeistopened/skill-stack-skills/tree/main/wiki-pipeline/wiki-extract-entities
Command: npx skills add https://github.com/cdeistopened/skill-stack-skills --skill wiki-extract-entities

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Transcripts are rich in content but hard to search and analyze; this skill creates a structured entity inventory with counts, sentiments, and co-occurrence data to enable quick topic discovery and indexing.

Core Features & Use Cases

  • Extract named entities from transcripts and build a running inventory with per-episode sources.
  • Track mention counts, sentiment tallies, and entity co-occurrences for SEO briefs and wiki navigation.
  • Use cases include topic discovery, article briefing, and cross-episode analytics.

Quick Start

Run the entity extractor on data/transcripts to generate data/entities/entity-inventory.json and data/entities/top-entities.json.

Frequently Asked Questions about wiki-extract-entities

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

FAQPage Schema
How do I extract named entities from transcripts to build a structured inventory?▼

You can extract named entities from transcripts by running an extraction process on a transcripts directory to generate a structured JSON inventory containing mention counts, co-occurrences, and sentiment tallies.

How does entity co-occurrence tracking work for cross-episode transcript analytics?▼

Entity co-occurrence tracking identifies named entities appearing together within transcripts to map relationships, enabling cross-episode analytics, topic discovery, and structured wiki navigation for downstream SEO briefs.

Can I use Gemini to categorize entities and track sentiment in text transcripts?▼

Yes, you can use Gemini to categorize extracted entities and track sentiment, producing a structured entity inventory file and a top entities listing for downstream analysis.

What is the best way to index topics across multiple episode transcripts?▼

The best way to index topics across multiple transcripts is to extract named entities into a structured inventory, tracking per-episode sources, mention counts, and sentiment tallies for quick discovery.

Do I need a specific directory structure to generate an entity inventory?▼

Yes, you need transcripts stored in a data/transcripts/ directory to produce the inventory file and top entities listing in data/entities/, enabling structured downstream analysis.

Related Skills

Explore More Data & Analytics Skills→
PostergullyPostergully

media-ingest

Ingest video, audio, PDF, book, screenshot, and repository content into structured brain pages.

Community
Advanced
PolealphaPolealpha

feishu-wiki

List Feishu wiki spaces and nodes, retrieve details, and create, move, or rename pages.

Community
Intermediate
OpenSuckerOpenSucker
15

sentiment-analysis

Calculate market sentiment indices from financial and social indicators.

Official
Intermediate
akrindevakrindev

sentiment-analyzer

Analyze video sentiment and emotion to produce sentiment scores, peaks, and timelines.

Community
Advanced