Embedding Strategies
Seth Hobson· Community
A guide to selecting and optimizing embedding models for semantic search and RAG applications.
Data and AIClaude CodeClaude appsOpenAI Codex+14 more
MITGitHub stars of the source repository42.3k
Agent Skills
Trusted skills for AI agents from official vendors and established maintainers. Every skill is attributed to its author, scanned, and comes with install steps for your AI tool.
Results
706 skills
Vector Index Tuning
Seth Hobson· Community
A guide to optimizing vector index performance for latency, recall, and memory usage.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Grpo Rlvr Training
Seth Hobson· Community
A structured workflow for training reasoning and verifiable task behavior using GRPO and Reinforcement Learning from Verifiable Rewards.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Spark Optimization
Seth Hobson· Community
Best practices and patterns for optimizing Apache Spark job performance, memory management, and data processing efficiency.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Database Admin
Seth Hobson· Community
An expert database administrator for cloud-native environments, automation, and reliability engineering.
Data and AIClaude CodeMITGitHub stars of the source repository42.3k
Kpi Dashboard Design
Seth Hobson· Community
A framework for designing effective, actionable KPI dashboards that drive business decisions through clear metrics and visualization best practices.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Trace To Training Data
Seth Hobson· Community
Convert graded evaluation traces and production logs into SFT examples and DPO preference pairs for model training.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Similarity Search Patterns
Seth Hobson· Community
Guidelines and implementation patterns for building efficient similarity search systems using vector databases.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Data Quality Frameworks
Seth Hobson· Community
A framework for implementing data quality validation using Great Expectations, dbt tests, and data contracts.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskGitHub stars of the source repository42.3k
Social Evidence Research
Seth Hobson· Community
A rigorous protocol for researching social media discussions while maintaining strict traceability between claims and source evidence.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Dataset Curation
Seth Hobson· Community
Prepare, format, and validate datasets for supervised fine-tuning and preference training.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository42.3k
Qdrant Horizontal Scaling
GitHubOfficial
Expert guidance on scaling Qdrant vector database deployments, covering vertical versus horizontal strategies and cluster configuration.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Arize Dataset
GitHubOfficial
Manage and query Arize datasets for evaluation and experimentation using the ax CLI.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITLow riskGitHub stars of the source repository40.9k
Qdrant Scaling Query Volume
GitHubOfficial
Optimizes Qdrant query performance by using statistical subsampling to reduce inter-shard data transfer for high-limit queries.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Qdrant Search Strategies
GitHubOfficial
A guide for selecting and implementing advanced Qdrant search strategies to improve retrieval quality and relevance.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Comet Opik
GitHubOfficial
Unified agent for instrumenting, auditing, and managing LLM application telemetry and prompts using Comet Opik.
Data and AIGitHub CopilotMITLow riskGitHub stars of the source repository40.9k
Pinecone RAG
GitHubOfficial
A guide for implementing RAG pipelines and persistent agent memory using the Pinecone vector database.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreApache-2.0GitHub stars of the source repository40.9k
Ms SQL Dba
GitHubOfficial
Manage and maintain Microsoft SQL Server databases using the MS SQL extension.
Data and AIGitHub CopilotMITGitHub stars of the source repository40.9k
Snowflake Semanticview
GitHubOfficial
Manage Snowflake semantic views through the Snowflake CLI with a structured validation workflow.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Qdrant Version Upgrade
GitHubOfficial
Best practices and version compatibility rules for upgrading Qdrant database instances.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Power Bi Model Design Review
GitHubOfficial
A comprehensive framework for auditing and optimizing Power BI data models for performance, scalability, and maintainability.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Qdrant Minimize Latency
GitHubOfficial
A guide to optimizing Qdrant query latency through configuration, resource management, and search parameter tuning.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Power Bi Report Design Consultation
GitHubOfficial
A comprehensive framework for designing effective, accessible, and user-friendly Power BI reports.
Data and AIClaude CodeClaude appsOpenAI Codex+14 moreMITGitHub stars of the source repository40.9k
Kusto Assistant
GitHubOfficial
An expert KQL assistant for live Azure Data Explorer analysis using the Azure MCP server.
Data and AIGitHub CopilotMITLow riskGitHub stars of the source repository40.9k