Tarun Jain
Community@lucifertrj · Banglore, India
Head down and build.
Agent Skills by Tarun Jain
Showing 33 vetted skills indexed across 1 GitHub repositories.
llm-arena
Coordinate AI-vs-AI Tic-Tac-Toe and Reversi battles across OpenAI, Anthropic, and Gemini providers.
qdrant-performance-optimization
Apply indexing, memory, and query tuning to optimize Qdrant deployments.
ai-memory
Stores and retrieves user data to maintain context across AI conversations.
frontend-design
Generate production-ready frontend components with design tokens and guidelines.
qdrant-clients-sdk
Provide official Qdrant client SDKs for Python, JavaScript/TypeScript, Rust, Go, .NET, and Java.
qdrant-search-quality
Diagnose Qdrant search quality issues across embedding models, configuration, and query strategies.
qdrant-minimize-latency
Tune Qdrant index parameters and memory usage to reduce single-query latency.
qdrant-scaling-qps
Apply Qdrant scaling guidelines to increase query throughput.
qdrant-scaling-query-volume
Apply Poisson-based sub-sampling to Qdrant queries across shards.
qdrant-tenant-scaling
Scale multi-tenant Qdrant deployments using shared collections and tenant keys.
qdrant-vertical-scaling
Plan vertical scaling of Qdrant nodes to increase RAM and CPU.
qdrant-sliding-time-window
Rotate Qdrant shards or collections to retain recent vectors and expire old data.
qdrant-horizontal-scaling
Diagnose Qdrant capacity and guide horizontal scaling decisions.
qdrant-memory-usage-optimization
Diagnose and optimize Qdrant deployment memory usage with quantization and on-disk storage.
qdrant-indexing-performance-optimization
Diagnose and optimize slow Qdrant indexing and data ingestion.
qdrant-search-speed-optimization
Diagnose and fix slow Qdrant search performance with HNSW and quantization tuning.
qdrant-search-strategies
Combine Qdrant hybrid search, reranking, and relevance feedback strategies.
qdrant-search-quality-diagnosis
Compare exact KNN ground truth with approximate HNSW results to measure Qdrant recall.
llm-arena-frontend
Prototype React frontends for LLM Arena game visualization with Vite and Tailwind.
llm-arena-backend
Automate FastAPI backend processing of LLM-powered game moves with LiteLLM integration.
polars
Perform fast, memory-efficient transformations on large tabular datasets with Polars.
pandas-eda-workflow
Perform exploratory data analysis on tabular data with pandas.
skill-md-creator
Convert user notes into SKILL.md entries with YAML frontmatter and structured body outlines.
nltk-nlp-text-cleaning
Clean, tokenize, and normalize English text with NLTK for NLP pipelines.