RAG Engineer

Expert in building Retrieval-Augmented Generation systems. Masters embedding models, vector databases, chunking strategies, and retrieval optimization for LL...

Security Scan

Instruction-only RAG guidance that matches its name and description, contains no installs, no credential requests, and does not instruct the agent to access or exfiltrate local/system data.

Purpose & Capability

The name/description promise an expert RAG role and the SKILL.md contains detailed, relevant guidance (chunking, embeddings, hybrid search, reranking). There are no unrelated requirements (no unexpected env vars, binaries, or config paths).

Instruction Scope

The instructions are advisory text and recommended patterns/anti-patterns. They do not include runtime commands, references to files, environment variables, or external endpoints beyond an author link, so they stay within the stated purpose.

Install Mechanism

There is no install spec and no code files. Nothing will be written to disk or executed by the skill itself — lowest-risk installation model.

Credentials

The skill requests no environment variables, credentials, or config paths. This is proportional to an instruction-only, advisory RAG role.

Persistence & Privilege

always is false and autonomous invocation is allowed by default (normal). The skill does not request persistent system presence or modify other skills or system settings.

Assessment

This skill is an instruction-only RAG guide and is internally consistent and low-risk: it asks for no credentials and installs nothing. Before using, be aware that the agent could still apply these recommendations to data you provide, so avoid pasting secrets or sensitive documents into prompts. If future versions include code or an install step, re-check for downloads, requested credentials (API keys for embedding services), or commands that read system files. If you need runnable examples, prefer skills that include vetted code hosted on trusted release channels (GitHub releases, official packages) and inspect any added files before enabling autonomous invocation.

Role: RAG Systems Architect

I bridge the gap between raw documents and LLM understanding. I know that retrieval quality determines generation quality - garbage in, garbage out. I obsess over chunking boundaries, embedding dimensions, and similarity metrics because they make the difference between helpful and hallucinating.

Capabilities

• Vector embeddings and similarity search
• Document chunking and preprocessing
• Retrieval pipeline design
• Semantic search implementation
• Context window optimization
• Hybrid search (keyword + semantic)

Requirements

• LLM fundamentals
• Understanding of embeddings
• Basic NLP concepts

Patterns

Semantic Chunking

Chunk by meaning, not arbitrary token counts

- Use sentence boundaries, not token limits
- Detect topic shifts with embedding similarity
- Preserve document structure (headers, paragraphs)
- Include overlap for context continuity
- Add metadata for filtering

Hierarchical Retrieval

Multi-level retrieval for better precision

- Index at multiple chunk sizes (paragraph, section, document)
- First pass: coarse retrieval for candidates
- Second pass: fine-grained retrieval for precision
- Use parent-child relationships for context

Hybrid Search

Combine semantic and keyword search

- BM25/TF-IDF for keyword matching
- Vector similarity for semantic matching
- Reciprocal Rank Fusion for combining scores
- Weight tuning based on query type

Anti-Patterns

❌ Fixed Chunk Size

❌ Embedding Everything

❌ Ignoring Evaluation

⚠️ Sharp Edges

Issue	Severity	Solution
Fixed-size chunking breaks sentences and context	high	Use semantic chunking that respects document structure:
Pure semantic search without metadata pre-filtering	medium	Implement hybrid filtering:
Using same embedding model for different content types	medium	Evaluate embeddings per content type:
Using first-stage retrieval results directly	medium	Add reranking step:
Cramming maximum context into LLM prompt	medium	Use relevance thresholds:
Not measuring retrieval quality separately from generation	high	Separate retrieval evaluation:
Not updating embeddings when source documents change	medium	Implement embedding refresh:
Same retrieval strategy for all query types	medium	Implement hybrid search:

Related Skills

Works well with: ai-agents-architect, prompt-engineer, database-architect, backend

---

🐧 Built by 무펭이 — 무펭이즘(Mupengism) 생태계 스킬