research-memory-cleanup

Name: research-memory-cleanup
Availability: InStock
Author: acertainknight

Consolidate duplicate papers, organize research domains, and clean outdated discovery configs.

12|7|Updated Mar 10, 2025

Search Tags:#organization #deduplication #backup-restore #discovery-configs #research-memory #memory-cleanup

Ready to run

npx skills add https://github.com/acertainKnight/project-thoth --skill research-memory-cleanup

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: research-memory-cleanup
Source: https://github.com/acertainKnight/project-thoth/tree/main/src/thoth/.skills/_archived/research-memory-cleanup
Command: npx skills add https://github.com/acertainKnight/project-thoth --skill research-memory-cleanup

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Defragment and clean research agent memory - consolidate paper info, organize research domains, remove redundancy from research tracking.

Core Features & Use Cases

Consolidate duplicate paper entries to a single canonical record.
Organize scattered notes into clearly defined research domains.
Clean and trim outdated discovery configs with safe rollback.

Quick Start

Step 1: Backup current memory npx tsx [SKILL_DIR]/scripts/backup-memory.ts $LETTA_AGENT_ID .letta/backups/working

Step 2: Spawn memory subagent for cleanup Task({ subagent_type: "memory", description: "Clean research memory", prompt: "[specific cleanup task]" })

Step 3: Restore the cleaned memory npx tsx [SKILL_DIR]/scripts/restore-memory.ts $LETTA_AGENT_ID .letta/backups/working

Frequently Asked Questions about research-memory-cleanup

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

FAQPage Schema

How do I consolidate duplicate research papers in my memory?▼

Consolidating duplicate papers involves backing up your memory, running the memory-subagent cleanup workflow to merge scattered paper entries into canonical records, and restoring the deduplicated result. The Skill automates this 3-step process with rollback support to ensure safe consolidation across your research domains.

Can I organize my research notes into domains without losing data?▼

Yes. The Skill organizes scattered notes into clearly defined research domains while maintaining data integrity through explicit backup and rollback capability. The deterministic workflow ensures you can restore your original memory if needed before applying domain organization.

What's the safest way to clean up outdated research tracking data?▼

Use the 3-step backup-cleanup-restore workflow. First backup your current memory, then spawn a memory-subagent to trim discovery configs and remove redundancy, finally restore the cleaned memory. This auditable approach lets you roll back if the cleanup removes data you need.

How do I handle research memory deduplication at scale across multiple domains?▼

The Skill applies deterministic deduplication and cleanup to large research memories spanning multiple domains. It consolidates citation networks and discovery configs while preserving domain structure, using the memory-subagent to process scattered notes and redundant entries systematically.

Do I need special setup or dependencies to clean my research memory?▼

No external dependencies are required. You need access to your agent ID and a backup directory. The Skill uses built-in scripts and a memory-subagent for cleanup, making it portable across research environments without additional tools or configuration.

Why should I deduplicate papers instead of manually organizing my research memory?▼

Manual organization is time-consuming and error-prone at scale. Deduplication automatically consolidates redundant paper entries, removes outdated discovery configs, and organizes notes deterministically, freeing you to focus on research rather than memory maintenance.