rag-patterns
Retrieval-Augmented Generation architecture patterns. Chunking strategies, retrieval pipelines, re-ranking, hybrid search, evaluation, and production RAG system design. USE WHEN: user mentions "RAG", "retrieval augmented generation", "document Q&A", "knowledge base chatbot", "semantic search pipeline", "chunking strategy" DO NOT USE FOR: vector database specifics - use `vector-databases`; LangChain implementation - use `langchain`; direct LLM API calls - use Claude/OpenAI SDK skills
What this skill does
# RAG Patterns
## Standard RAG Pipeline
```
Documents → Chunk → Embed → Store (vector DB)
Query → Embed → Retrieve → Augment prompt → Generate answer
```
## Chunking Strategies
```python
from langchain_text_splitters import RecursiveCharacterTextSplitter
# Recommended defaults
splitter = RecursiveCharacterTextSplitter(
chunk_size=800, # chars (not tokens)
chunk_overlap=200,
separators=["\n\n", "\n", ". ", " ", ""],
)
chunks = splitter.split_documents(docs)
```
| Strategy | Best For | Chunk Size |
|----------|----------|------------|
| Fixed-size with overlap | General text | 500-1000 chars |
| Recursive character | Structured docs | 500-1000 chars |
| Semantic (by meaning) | Long-form content | Variable |
| Document-aware (markdown headers) | Technical docs | Section-based |
### Metadata Enrichment
```python
for chunk in chunks:
chunk.metadata.update({
"source": doc.metadata["source"],
"section": extract_section_title(chunk),
"doc_id": doc.metadata["id"],
"chunk_index": i,
})
```
## Retrieval Strategies
### Hybrid Search (keyword + semantic)
```python
from langchain.retrievers import EnsembleRetriever
from langchain_community.retrievers import BM25Retriever
bm25 = BM25Retriever.from_documents(docs, k=5)
vector_retriever = vectorstore.as_retriever(search_kwargs={"k": 5})
hybrid = EnsembleRetriever(
retrievers=[bm25, vector_retriever],
weights=[0.3, 0.7],
)
```
### Re-ranking
```python
from cohere import Client
cohere = Client(api_key=COHERE_API_KEY)
def rerank(query: str, documents: list[str], top_n: int = 5):
response = cohere.rerank(
model="rerank-english-v3.0",
query=query,
documents=documents,
top_n=top_n,
)
return [documents[r.index] for r in response.results]
```
### Multi-query Retrieval
```python
# Generate multiple query variations for better recall
prompt = """Generate 3 different versions of this question
to retrieve relevant documents: {question}"""
queries = llm.invoke(prompt).split("\n")
all_docs = set()
for q in queries:
all_docs.update(retriever.invoke(q))
```
## Prompt Construction
```python
SYSTEM_PROMPT = """Answer based only on the provided context.
If the context doesn't contain the answer, say "I don't have enough information."
Cite sources using [Source: filename] format.
Context:
{context}"""
def format_context(docs, max_tokens=3000):
context_parts = []
for doc in docs:
source = doc.metadata.get("source", "unknown")
context_parts.append(f"[Source: {source}]\n{doc.page_content}")
return "\n\n---\n\n".join(context_parts)
```
## Evaluation
| Metric | Measures | Tool |
|--------|----------|------|
| Context Relevance | Are retrieved docs relevant? | RAGAS, manual |
| Faithfulness | Does answer match context? | RAGAS |
| Answer Relevance | Does answer address question? | RAGAS |
| Retrieval Recall | Are correct docs retrieved? | Custom eval set |
```python
from ragas import evaluate
from ragas.metrics import faithfulness, answer_relevancy, context_precision
result = evaluate(dataset, metrics=[faithfulness, answer_relevancy, context_precision])
```
## Anti-Patterns
| Anti-Pattern | Fix |
|--------------|-----|
| Chunks too large (>1500 chars) | Use 500-1000 char chunks with 200 overlap |
| No metadata on chunks | Store source, section, page number |
| No retrieval evaluation | Build eval set, measure recall and precision |
| Stuffing all chunks in prompt | Limit to top-K (3-5), use re-ranking |
| Ignoring hybrid search | Combine BM25 + vector for better recall |
| No citation/source tracking | Pass metadata through pipeline |
## Production Checklist
- [ ] Chunking strategy tuned with eval set
- [ ] Hybrid search (BM25 + vector) enabled
- [ ] Re-ranking on retrieval results
- [ ] Source attribution in answers
- [ ] Guardrails for out-of-scope questions
- [ ] Monitoring: retrieval latency, answer quality scores
- [ ] Incremental indexing for new documents
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.