research-manager

Name: research-manager
Availability: InStock
Author: ARA-Labs

Record research events with classification and provenance tags.

594|52|Updated Mar 27, 2026

Search Tags:#knowledge management #research automation #provenance tracking #structured knowledge #research documentation

Ready to run

npx skills add https://github.com/ARA-Labs/Agent-Native-Research-Artifact --skill research-manager-ara-labs

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-manager
Source: https://github.com/ARA-Labs/Agent-Native-Research-Artifact/tree/main/skills/research-manager
Command: npx skills add https://github.com/ARA-Labs/Agent-Native-Research-Artifact --skill research-manager-ara-labs

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the recording of research processes and the crystallization of knowledge, enabling researchers to maintain structured, verifiable, and traceable research records.

Core Features & Use Cases

End-of-Turn Research Recording: Automatically captures research activities at the end of each turn, ensuring all significant events are documented.
Progressive Crystallization: Stages research observations and knowledge events, allowing them to mature into formal entries based on external signals.
Provenance Tracking: Maintains detailed provenance tags for all entries, indicating whether they were user-input, AI-suggested, or AI-executed.
Use Case: For AI researchers who need to document their research process, ensure reproducibility, and maintain a structured knowledge base.

Quick Start

Use the research-manager skill at the end of each research turn to record and crystallize your findings.

Frequently Asked Questions about research-manager

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

FAQPage Schema

How do I automate research documentation and track provenance in AI workflows?▼

Research documentation automation captures significant events at the end of each turn, classifies them, and applies provenance tagging to maintain structured, verifiable records. This ensures reproducibility by indicating whether entries were user-input, AI-suggested, or AI-executed.

What is progressive crystallization for structured knowledge management?▼

Progressive crystallization stages research observations and knowledge events to mature into formal entries based on external signals. It allows researchers to gradually structure raw findings into a verified knowledge base without immediate finalization.

How do I record research processes automatically at the end of each turn?▼

You record research processes by running the automation at the end of each research turn. It automatically extracts significant events, classifies the activity, and documents the findings with provenance tags for immediate structured knowledge capture.

Do I need structured input for event classification and provenance tracking?▼

Yes, structured input is required for event classification and provenance tracking. The automation relies on structured inputs to accurately categorize research activities and assign correct provenance tags indicating user-input, AI-suggested, or AI-executed origins.

What's the best way to ensure reproducibility in AI research workflows?▼

The best way to ensure reproducibility is to automate end-of-turn research recording with provenance tracking. This maintains detailed tags for all entries, classifies significant events, and builds a structured knowledge base that verifies research activities.

When should I not use automated research process recording?▼

You should avoid automated research process recording when you lack structured input for event classification, or when your research workflow does not require structured documentation, provenance tracking, or strict reproducibility standards.