skills.rest
neverprepared
neverpreparedOFFICIAL
Explore all skills by this author →
GitHub

rag-wrapper

Automate RAG-wrapped memory augmentation for agents using Qdrant.

Updated Aug 27, 2026
Search Tags:#context#rag#agent#memory#qdrant#prompt
One-click install
npx skills add https://github.com/neverprepared/ink-bunny --skill rag-wrapper-neverprepared
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: rag-wrapper
Source: https://github.com/neverprepared/ink-bunny/tree/main/reflex/plugins/reflex/skills/rag-wrapper
Command: npx skills add https://github.com/neverprepared/ink-bunny --skill rag-wrapper-neverprepared

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Patterns for wrapping any agent with Qdrant context retrieval to provide persistent memory and context-aware decision making.

Core Features & Use Cases

  • RAG-based context retrieval to enhance agent recall across tasks.
  • Patterns for querying, formatting, and reinjecting context into task prompts.
  • Use Case: Wrap a chatbot or long-running agent to maintain memory across sessions.

Quick Start

Wrap a target agent with Qdrant-backed memory by delegating to a rag-proxy agent with the target and the task.

Frequently Asked Questions about rag-wrapper

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

FAQPage Schema
How do I add persistent memory to an agent using RAG?▼

Add persistent memory to an agent by wrapping it with RAG context retrieval. This automates querying a vector database, formatting the retrieved context, and reinjecting it into task prompts for context-aware decisions.

How do I maintain context across long-running agent workflows?▼

Maintain context across long-running agent workflows by applying RAG-wrapped memory augmentation. It retrieves persistent context from storage and constructs enriched prompts delegated to the target agent.

Does this RAG memory wrapper require Qdrant to function?▼

Yes, this RAG memory wrapper relies on Qdrant to store and query persistent context. It automates querying Qdrant, formatting the retrieved contexts, and constructing enriched prompts for delegation.

What is the best way to wrap a chatbot with persistent memory?▼

The best way to wrap a chatbot with persistent memory is delegating to a rag-proxy agent. This applies RAG-based context retrieval to enhance agent recall and maintain memory across sessions.

When do I need RAG context retrieval for onboarding agents?▼

You need RAG context retrieval for onboarding agents when complex workflows require persistent context retrieval. It formats retrieved contexts and constructs enriched prompts to provide context-aware decision making.

Related Skills

Explore More Software Engineering Skills→
mindmorassmindmorass
2

qdrant-patterns

Store and retrieve documents in Qdrant for semantic search.

Community
Advanced
just-cameronjust-cameron
23

working-with-subagents

Coordinates stateful scout, coder, and memory subagents to execute delegated tasks with context preservation.

Community
Intermediate
zhangzhang-111-izhangzhang-111-i
2

senior-prompt-engineer

Analyze and optimize LLM prompts for clarity and token efficiency.

Community
Advanced
JCETools-PetraJCETools-Petra
16

ai-llm-engineering

Design RAG pipelines with chunking, embedding, retrieval, and evaluation metrics.

Community
Advanced