Agent skills for Zed

NVIDIA RAG Blueprint — deploy, configure, troubleshoot and manage any RAG action: agentic RAG, VLM, guardrails, query rewriting…

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality) for a deployed NVIDIA RAG Blueprint.

Build Retrieval-Augmented Generation (RAG) systems for LLM applications with vector databases and semantic search.

RAG (Retrieval-Augmented Generation) implementation workflow covering embedding selection, vector database setup, chunking strategies, and…

Query expansion, HyDE, and multi-query generation for improved retrieval

Cross-encoder reranking and MMR diversity filtering for improved retrieval quality

When to activate: RAG, retrieval augmented generation, LangChain, LlamaIndex, vector stores, embeddings, retrieval, chunking, reranking…

Rebase the current branch with smart conflict resolution.

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

Create, inspect, validate, explain, and improve Ralph hat collections.

Explain the Ralph Loop plugin, how it works, and available skills.

Run an autonomous, iterative development loop using the Ralph Wiggum technique.

Run a sequential three-tier code review on a finished implementation branch — Haiku (surface) → Sonnet (logic) → Opus (deep).

Consensus-driven implementation planning via strict Planner/Architect/Critic iteration.

Consensus planning entrypoint that auto-gates vague ralph/autopilot/team requests before execution

Ramp performance tuning \u2014 corporate card and expense management\

Ramp reference architecture \u2014 corporate card and expense management\

Run accessibility and visual design review

Create custom AI subagents with proper plugin structure, persona generation, and companion routing skills.

Build persistent agents on Azure AI Foundry using the Microsoft Agent Framework Python SDK.

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.