ingestion

Name: ingestion
Availability: InStock
Author: Transluce

Convert raw agent transcripts and evaluation logs into Docent-ready agent runs.

6|Updated Jan 31, 2026

Search Tags:#workflow #validation #ingestion #transcripts #docent #data-processing #agent_runs

Ready to run

npx skills add https://github.com/TransluceAI/claude-code-plugins --skill ingestion-transluceai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ingestion
Source: https://github.com/TransluceAI/claude-code-plugins/tree/main/plugins/docent/skills/ingestion
Command: npx skills add https://github.com/TransluceAI/claude-code-plugins --skill ingestion-transluceai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Docent ingestion skill provides a structured workflow to transform raw agent transcripts and evaluation logs into Docent-ready agent runs, enabling reproducible organization and analysis.

Core Features & Use Cases

End-to-end ingestion planning, schema inference, and validation to ensure data quality before import
Flexible mapping of transcript data and metadata to Docent's AgentRun, Transcript, and TranscriptGroup structures
Guided workflow stages (context gathering, planning, conversion, and testing) that help analysts organize data for multi-agent and single-agent scenarios

Quick Start

Provide your data path and target Docent collection to begin the ingestion workflow.

Frequently Asked Questions about ingestion

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

FAQPage Schema

How do I convert raw agent transcripts into Docent agent runs?▼

To convert raw agent transcripts into Docent agent runs, use a guided workflow that handles end-to-end planning, schema inference, and validation. This process maps transcript data and metadata to Docent's AgentRun, Transcript, and TranscriptGroup structures for reproducible analysis.

What is the best way to validate evaluation logs before uploading to Docent?▼

The best way to validate evaluation logs before uploading to Docent is to use a structured ingestion workflow that performs schema inference and data verification. This ensures configuration and mapping are correct, maintaining data integrity and reproducibility before the upload.

Can I use this ingestion workflow for both single-agent and multi-agent scenarios?▼

Yes, you can use this ingestion workflow for both single-agent and multi-agent scenarios. The guided workflow stages, including context gathering and planning, help analysts organize data flexibly for different agent configurations before conversion and testing.

How do I map transcript metadata to Docent structures during data processing?▼

To map transcript metadata to Docent structures, the ingestion workflow provides flexible mapping configurations that align raw data fields with Docent's AgentRun, Transcript, and TranscriptGroup schemas. This ensures accurate data conversion and verification before upload.

What do I need to start importing agent evaluation data into a Docent collection?▼

To start importing agent evaluation data, you need to provide your raw data path and specify the target Docent collection. The workflow then guides you through context gathering, planning, conversion, and testing to ensure successful ingestion.