Skip to main content

V3 Memory Specialist

Skill Verified Active

Agent skill for v3-memory-specialist - invoke with $agent-v3-memory-specialist

Purpose

To unify disparate memory systems into a high-performance, AgentDB-backed solution with HNSW indexing, achieving massive search speed improvements and enabling cross-agent memory sharing.

Features

  • Unifies 7+ disparate memory systems
  • Integrates with AgentDB for unified storage
  • Implements HNSW indexing for 150x-12,500x search speed improvement
  • Supports both semantic and structured memory queries
  • Facilitates SONA integration for learning pattern storage

Use Cases

  • When needing to consolidate multiple memory backends into a single, high-performance system.
  • To achieve significant speedups in memory retrieval for AI agents.
  • For integrating advanced memory features like cross-agent sharing and SONA pattern learning.
  • During the migration from legacy memory systems to a modern, unified architecture.

Non-Goals

  • Replacing the core LLM or agent orchestration framework itself.
  • Providing a generic interface for unrelated data storage.
  • Implementing new memory systems from scratch without leveraging existing paradigms.

Workflow

  1. Initialize memory system unification process.
  2. Check current memory systems and AgentDB integration status.
  3. Execute memory system unification using AgentDB and HNSW indexing.
  4. Store memory patterns using agentic-flow for performance tracking.

Practices

  • Memory system unification
  • Performance optimization
  • Data migration
  • AgentDB integration

Prerequisites

  • agentic-flow@alpha installed

Code Execution

  • info:LoggingThe `pre_execution` and `post_execution` hooks print informational messages to stdout, and error output is redirected. A dedicated audit log file is not explicitly mentioned or implemented.

Installation

npx skills add ruvnet/ruflo

Runs the Vercel skills CLI (skills.sh) via npx — needs Node.js locally and at least one installed skills-compatible agent (Claude Code, Cursor, Codex, …). Assumes the repo follows the agentskills.io format.

Quality Score

Verified
99 /100
Analyzed about 11 hours ago

Trust Signals

Last commitabout 13 hours ago
Stars50.2k
LicenseMIT
Status
View Source

Similar Extensions

V3 Memory Unification

99

Unify 6+ memory systems into AgentDB with HNSW indexing for 150x-12,500x search improvements. Implements ADR-006 (Unified Memory Service) and ADR-009 (Hybrid Memory Backend).

Skill
ruvnet

Memory Management

99

AgentDB memory system with HNSW vector search. Provides 150x-12,500x faster pattern retrieval, persistent storage, and semantic search capabilities for learning and knowledge management. Use when: need to store successful patterns, searching for similar solutions, semantic lookup of past work, learning from previous tasks, sharing knowledge between agents, building knowledge base. Skip when: no learning needed, ephemeral one-off tasks, external data sources available, read-only exploration.

Skill
ruvnet

Dsql

100

Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL migration, DDL operations, query plan explainability, and SQL compatibility validation. Triggers on phrases like: DSQL, Aurora DSQL, create DSQL table, DSQL schema, migrate to DSQL, distributed SQL database, serverless PostgreSQL-compatible database, DSQL query plan, DSQL EXPLAIN ANALYZE, why is my DSQL query slow.

Skill
awslabs

Wrap Up Ritual

100

End-of-session ritual that audits changes, runs quality checks, captures learnings, and produces a session summary. Use when saying "wrap up", "done for the day", "finish coding", or ending a coding session.

Skill
rohitg00

Orchestrate

100

Wire Commands, Agents, and Skills together for complex features. Use when building features that need research, planning, and implementation phases.

Skill
rohitg00

Trading Memory

100

Domain knowledge for AI trading memory — Outcome-Weighted Memory (OWM) architecture, 5 memory types, recall scoring, and behavioral analysis. Use when recording trades, recalling similar contexts, analyzing performance, or checking behavioral drift. Triggers on "record trade", "remember trade", "recall", "similar trades", "performance", "behavioral", "disposition", "affective state", "confidence".

Skill
mnemox-ai

© 2025 SkillRepo · Find the right skill, skip the noise.