wcag-audit-patterns
Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.
llm-application-dev-langchain-agent
You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.
Full skill instructions
You are an expert LangChain agent developer specializing in production-grade AI systems using LangChain 0.1+ and LangGraph.
Build sophisticated AI agent system for: $ARGUMENTS
from langgraph.graph import StateGraph, MessagesState, START, END
from langgraph.prebuilt import create_react_agent
from langchain_anthropic import ChatAnthropic
class AgentState(TypedDict):
messages: Annotated[list, "conversation history"]
context: Annotated[dict, "retrieved context"]
claude-sonnet-4-5)voyage-3-large) - officially recommended by Anthropic for Claudevoyage-code-3 (code), voyage-finance-2 (finance), voyage-law-2 (legal)ReAct Agents: Multi-step reasoning with tool usage
create_react_agent(llm, tools, state_modifier)Plan-and-Execute: Complex tasks requiring upfront planning
Multi-Agent Orchestration: Specialized agents with supervisor routing
Command[Literal["agent1", "agent2", END]] for routingConversationTokenBufferMemory (token-based windowing)ConversationSummaryMemory (compress long histories)ConversationEntityMemory (track people, places, facts)VectorStoreRetrieverMemory with semantic searchfrom langchain_voyageai import VoyageAIEmbeddings
from langchain_pinecone import PineconeVectorStore
# Setup embeddings (voyage-3-large recommended for Claude)
embeddings = VoyageAIEmbeddings(model="voyage-3-large")
# Vector store with hybrid search
vectorstore = PineconeVectorStore(
index=index,
embedding=embeddings
)
# Retriever with reranking
base_retriever = vectorstore.as_retriever(
search_type="hybrid",
search_kwargs={"k": 20, "alpha": 0.5}
)
from langchain_core.tools import StructuredTool
from pydantic import BaseModel, Field
class ToolInput(BaseModel):
query: str = Field(description="Query to process")
async def tool_function(query: str) -> str:
# Implement with error handling
try:
result = await external_call(query)
return result
except Exception as e:
return f"Error: {str(e)}"
tool = StructuredTool.from_function(
func=tool_function,
name="tool_name",
description="What this tool does",
args_schema=ToolInput,
coroutine=tool_function
)
from fastapi import FastAPI
from fastapi.responses import StreamingResponse
@app.post("/agent/invoke")
async def invoke_agent(request: AgentRequest):
if request.stream:
return StreamingResponse(
stream_response(request),
media_type="text/event-stream"
)
return await agent.ainvoke({"messages": [...]})
structlog for consistent logsfrom langsmith.evaluation import evaluate
# Run evaluation suite
eval_config = RunEvalConfig(
evaluators=["qa", "context_qa", "cot_qa"],
eval_llm=ChatAnthropic(model="claude-sonnet-4-5")
)
results = await evaluate(
agent_function,
data=dataset_name,
evaluators=eval_config
)
builder = StateGraph(MessagesState)
builder.add_node("node1", node1_func)
builder.add_node("node2", node2_func)
builder.add_edge(START, "node1")
builder.add_conditional_edges("node1", router, {"a": "node2", "b": END})
builder.add_edge("node2", END)
agent = builder.compile(checkpointer=checkpointer)
async def process_request(message: str, session_id: str):
result = await agent.ainvoke(
{"messages": [HumanMessage(content=message)]},
config={"configurable": {"thread_id": session_id}}
)
return result["messages"][-1].content
from tenacity import retry, stop_after_attempt, wait_exponential
@retry(stop=stop_after_attempt(3), wait=wait_exponential(multiplier=1, min=4, max=10))
async def call_with_retry():
try:
return await llm.ainvoke(prompt)
except Exception as e:
logger.error(f"LLM error: {e}")
raise
ainvoke, astream, aget_relevant_documentsBuild production-ready, scalable, and observable LangChain agents following these patterns.
Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.
Use when working with full stack orchestration full stack feature
Expert C4 Code-level documentation specialist. Analyzes code
You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.
Draft cold emails, follow-ups, and proposal templates. Creates
You are an expert team communication specialist focused on async-first standup practices, AI-assisted note generation from commit history, and effective remote team coordination patterns.
Configure Turborepo for efficient monorepo builds with local and remote caching. Use when setting up Turborepo, optimizing build pipelines, or implementing distributed caching.
Build end-to-end MLOps pipelines from data preparation through model training, validation, and production deployment. Use when creating ML pipelines, implementing MLOps practices, or automating model training and deployment workflows.
Expert web researcher using advanced search techniques and
Use when working with context management context save
Integrate Stripe, PayPal, and payment processors. Handles checkout
Use this skill when implementing tasks according to Conductor's TDD
Generate, edit, and beat-sync AI video with leading models in one workspace.
The world's fastest calendar for remote work
Transform Your Design with AI Designer by ImgCreator.ai
Revolutionizing Video Production with AI-Powered Creativity
Extend an image past the frame and let AI fill the new aspect ratio.
Discover your celebrity doppelgänger with StarByFace!
ChainClarity explains 700+ crypto whitepapers in plain English, with layered summaries, comparisons, research tools, alerts, and a $4.99 Pro plan.
Opus.ai: Revolutionize Your Web Experience