Your agent can do more. Find the skill that makes it happen.
Find your next superpower If you are an agent, refer to our llms.txt for full access.Designs retrieval pipelines for knowledge-grounded AI applications using semantic search and embedding-based indexing. Configures vector stores, augments model context with retrieved documents, and evaluates retrieval quality.
Handles the service lifecycle from installation and startup through debugging and teardown. Configures features including Agentic RAG, ingestion, search, models, guardrails, query rewriting, and observability.
Guides the development of Retrieval-Augmented Generation systems for LLM applications. Covers embedding models, vector databases, chunking strategies, semantic search, and retrieval optimization.
Works with benchmarks organized around corpus/, train.json, and evaluate_rag.py. Focuses on RAG quality rather than production monitoring or latency and throughput testing.
Covers Retrieval-Augmented Generation implementation patterns, including document chunking, embeddings, and vector stores. Supports vector and semantic search with retrieval optimization.
Covers retrieval-augmented generation for LLM applications using vector databases and semantic search. Supports knowledge-grounded AI, document question answering, and integration with external knowledge bases.
Runs a profiling pass and an aiperf load test from a single YAML configuration. Focuses on performance rather than accuracy scoring, deployment, or service repair.
Test Retrieval-Augmented Generation (RAG) systems for data poisoning, prompt injection via retrieved documents, and data exfiltration through manipulated context windows. Use this skill when assessing RAG-based chatbots, knowledge bases, enterprise AI assistants, or any system that augments LLM responses with external document retrieval. Covers document injection, embedding manipulation, knowledge…
Provides retrieval-augmented generation patterns for grounded LLM responses. Covers contextual retrieval, HyDE, agentic and multimodal RAG, document embeddings, hybrid search, query decomposition, reranking, and pgvector search.
Optimizes Active Record queries and implements Turbo Frames and Streams for partial page updates. Configures Action Cable connections, Sidekiq background workers, and RSpec suites for Rails 7+ applications.
Looks up up-to-date Railway documentation to provide accurate answers. Supports questions about platform features, how Railway works, and supplied docs.railway.com URLs.
Provides an interactive planning conversation to develop focused, well-structured ralph-loop commands.
Skills give your agent reusable instructions for a specific job. Pick one, read what it does, and bring it into your workflow.
A name only tells half the story. Search the full description and instructions to find the right fit.
Read the skill, visit its source, and see exactly what you’re adding to your agent.
Copy the install command from a skill page and run it in your project.
npx skillycli add owner/repo --skill name