ArieGoldkin/claude-forge

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Build AI-first applications with RAG pipelines, embeddings, vector databases, agentic workflows (ReAct, multi-agent, Opus 4.5), LLM integration, prompt engineering, streaming, and cost optimization. Use when: building an AI feature, integrating an LLM, setting up vector search, or designing agent architectures.…

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

AI coaching & conversational support — empathetic interactions, safety guardrails, motivational interviewing, SMART goals, crisis handling. Applicable to coaching, therapy, education, customer support.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Text embeddings for semantic search and similarity. Covers model selection (OpenAI text-embedding-3, nomic-embed), chunking strategies, batch processing, cosine similarity, and vector DB integration. Use when: converting text to vectors, choosing embedding models, implementing chunking, or setting up semantic search.…

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

LLM function calling and tool use patterns. Covers JSON tool schemas (strict mode), execution loops, structured output with Pydantic, parallel tool calls, and LangChain tool binding. OpenAI and Anthropic patterns. Use when: enabling LLMs to call external tools, defining tool schemas, building tool execution loops, or…

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Golden dataset curation, backup/restore, validation with schema checks, duplicate detection, and coverage analysis.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

LLM observability with Langfuse — tracing, evaluation, prompt versioning, cost tracking, and LLM-as-judge scoring.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

LangGraph workflow patterns for stateful multi-step LLM workflows. State schemas (TypedDict/Pydantic), conditional routing, parallel fan-out/fan-in, human-in-the-loop gates, checkpointing, and supervisor agents. Use when: building LangGraph workflows, adding approval steps, coordinating agents, or persisting state.…

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

LLM application patterns for evaluation, streaming, and testing. Evaluation: LLM-as-judge, multi-dimension scoring, hallucination detection, Langfuse integration. Streaming: SSE, FastAPI endpoints, tool calls in streams, backpressure. Testing: mocking LLM responses, VCR.py recording, structured output validation. Use…

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Multi-agent fan-out/fan-in workflows — supervisor delegation, conflict resolution, and parallel research pipeline synthesis.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Google NotebookLM programmatic access — create notebooks, manage sources (URLs, PDFs, YouTube, Drive), generate audio/video/slides/quizzes, and chat with documents. Triggers on notebooklm, podcast from docs, research notebook.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Local LLM inference with Ollama. Use when setting up local models for development, CI pipelines, or cost reduction. Covers model selection, LangChain integration, and performance tuning.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

(Aspirational) Production hybrid search with PGVector + BM25 using Reciprocal Rank Fusion, metadata filtering, and performance optimization for semantic retrieval.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Provider-native prompt caching for Claude and OpenAI. Use when optimizing LLM costs with cache breakpoints, caching system prompts, or reducing token costs for repeated prefixes.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

RAG pipeline patterns for grounded LLM responses. Covers basic retrieval, citations, hybrid search (semantic + keyword with RRF), context window management, and sufficiency checks for hallucination prevention. Use when: building a Q&A system, adding citations, implementing knowledge bases, or preventing…

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Redis semantic caching for LLM apps — vector similarity matching, multi-level cache, TTL strategies, cache warming.

ArieGoldkin/claude-forge

Skill Claude CodeCodex

Part of atk

Real-time streaming with SSE, WebSockets, ReadableStream — backpressure, reconnection, and LLM streaming patterns.