memory/voice_transcript_ingestion

Classify voice transcript content into observations, assertions, claims, hypotheses, and actions.

Updated Apr 4, 2026

Search Tags:#voice #memory #ingestion #transcripts #claims #hypotheses #non-sovereign

Ready to run

npx skills add https://github.com/JMTassy/helen-conquest --skill memory-voice-transcript-ingestion

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory/voice_transcript_ingestion
Source: https://github.com/JMTassy/helen-conquest/tree/main/oracle_town/skills/memory/voice_transcript_ingestion
Command: npx skills add https://github.com/JMTassy/helen-conquest --skill memory-voice-transcript-ingestion

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Raw voice transcripts are noisy, unstructured data that hinder memory capture and later recall. This skill provides a safe, non-sovereign pathway to structure transcripts into reusable memory candidates (observations, assertions, claims, hypotheses, and actions) without elevating items to doctrine.

Core Features & Use Cases

Non-sovereign intake: captures data without writing into the ledger or constitution.
Observation vs assertion separation: clearly marks what was observed versus what is claimed.
Structured output: produces categorized candidate items ready for review or promotion through formal channels.

Quick Start

Ingest a raw voice transcript and generate a non-doctrinal candidate set.

Frequently Asked Questions about memory/voice_transcript_ingestion

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

FAQPage Schema

How do I structure raw voice transcripts into usable memory candidates?▼

Voice transcript ingestion parses raw transcripts from meetings or recordings to classify observations, assertions, claims, hypotheses, and actions into a standardized output template for later review.

What is non-sovereign intake for voice transcript processing?▼

Non-sovereign intake captures transcript data and structures it into memory candidates without writing into the ledger or constitution, ensuring nothing is promoted to doctrine automatically.

Can I separate observations from assertions when ingesting meeting transcripts?▼

Yes, transcript ingestion explicitly separates observations from assertions, clearly marking what was directly observed versus what is claimed to ensure accurate memory candidate classification.

How do I capture hypotheses and actions from voice recordings without altering doctrine?▼

The ingestion skill extracts hypotheses and actions from voice recordings into a non-doctrinal candidate set, satisfying non-sovereign intake constraints while preparing items for formal review.

Does voice transcript ingestion require any specific dependencies or components?▼

No, voice transcript ingestion operates with zero dependencies and components, processing raw transcripts directly to generate categorized memory candidates ready for downstream review.

What is the best way to prepare unstructured meeting transcripts for memory recall?▼

Ingesting unstructured meeting transcripts through a non-sovereign pathway structures the noisy data into categorized candidate items, preventing premature doctrinal promotion while enabling later recall and review.