research-memory-cleanup
CommunityClean and organize your research memory.
System Documentation
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- Clean and trim outdated discovery configs with safe rollback.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
Dependency Matrix
Required Modules
None requiredComponents
Standard package💻 Claude Code Installation
Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.
Please help me install this Skill: Name: research-memory-cleanup Download link: https://github.com/acertainKnight/project-thoth/archive/main.zip#research-memory-cleanup Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.