eyadsibai
@eyadsibai
Public Skills
nemo-evaluator
by eyadsibai
Use when evaluating LLMs, running benchmarks like MMLU/HumanEval/GSM8K, setting up evaluation pipelines, or asking about "NeMo Evaluator", "LLM benchmarking", "model evaluation", "MMLU", "HumanEval", "GSM8K", "benchmark harnesses"
context-compression
by eyadsibai
Use when compressing agent context, implementing conversation summarization, reducing token usage in long sessions, or asking about "context compression", "conversation history", "token optimization", "context limits", "summarization strategies"
Accessibility
by eyadsibai
This skill should be used when the user asks about "accessibility", "a11y", "WCAG", "screen readers", "keyboard navigation", "ARIA", "accessible design", "inclusive design", or mentions making apps accessible.
subagent-driven-development
by eyadsibai
Use when executing implementation plans with independent tasks in the current session
langchain-agents
by eyadsibai
Use when "LangChain", "LLM chains", "ReAct agents", "tool calling", or asking about "RAG pipelines", "conversation memory", "document QA", "agent tools", "LangSmith"
vector-databases
by eyadsibai
Use when "vector database", "embedding storage", "similarity search", "semantic search", "Chroma", "ChromaDB", "FAISS", "Qdrant", "RAG retrieval", "k-NN search", "vector index", "HNSW", "IVF"
plugin-development
by eyadsibai
Use when creating Claude Code plugins, writing skills, building commands, developing agents, or asking about "plugin development", "create skill", "write command", "build agent", "SKILL.md", "plugin structure", "progressive disclosure"
scientific-computing
by eyadsibai
Use when "scientific computing", "astronomy", "astropy", "bioinformatics", "biopython", "symbolic math", "sympy", "statistics", "statsmodels", "scientific Python"
dspy-prompting
by eyadsibai
Use when "DSPy", "declarative prompting", "automatic prompt optimization", "Stanford NLP", or asking about "optimizing prompts", "prompt compilation", "modular LLM programming", "chain of thought", "few-shot learning"
multi-agent-patterns
by eyadsibai
Use when designing multi-agent systems, implementing supervisor patterns, coordinating multiple agents, or asking about "multi-agent", "supervisor pattern", "swarm", "agent handoffs", "orchestration", "parallel agents"
dispatching-parallel-agents
by eyadsibai
Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
networkx
by eyadsibai
Use when "NetworkX", "graph analysis", "network analysis", "graph algorithms", "shortest path", "centrality", "PageRank", "community detection", "social network", "knowledge graph"
data-engineering
by eyadsibai
Use when "data pipelines", "ETL", "data warehousing", "data lakes", or asking about "Airflow", "Spark", "dbt", "Snowflake", "BigQuery", "data modeling"
canvas-design
by eyadsibai
Use when "creating posters", "visual art", "design philosophy", "PDF art", "PNG design", or asking about "abstract art", "visual design", "museum-quality graphics"
llm-inference
by eyadsibai
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"
geopandas
by eyadsibai
Use when "GeoPandas", "geospatial", "GIS", "shapefile", "GeoJSON", or asking about "spatial analysis", "coordinate transformation", "spatial join", "choropleth map", "buffer analysis", "geographic data", "map visualization"
ml-engineering
by eyadsibai
Use when "deploying ML models", "MLOps", "model serving", "feature stores", "model monitoring", or asking about "PyTorch deployment", "TensorFlow production", "RAG systems", "LLM integration", "ML infrastructure"
memory-systems
by eyadsibai
Use when implementing agent memory, persisting state across sessions, building knowledge graphs, tracking entities, or asking about "agent memory", "knowledge graph", "entity memory", "vector stores", "temporal knowledge", "cross-session persistence"
visualization
by eyadsibai
Use when "data visualization", "plotting", "charts", "matplotlib", "plotly", "seaborn", "graphs", "figures", "heatmap", "scatter plot", "bar chart", "interactive plots"
agent-evaluation
by eyadsibai
Use when evaluating agent performance, building test frameworks, measuring quality, or asking about "agent evaluation", "LLM-as-judge", "agent testing", "quality metrics", "evaluation rubrics", "agent benchmarks"
rag-frameworks
by eyadsibai
Use when "RAG", "retrieval augmented generation", "LangChain", "LlamaIndex", "sentence transformers", "embeddings", "document QA", "chatbot with documents", "semantic search"
planning-with-files
by eyadsibai
This skill should be used when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls. Implements Manus-style file-based planning with task_plan.md, findings.md, and progress.md.
writing-plans
by eyadsibai
Use when you have a spec or requirements for a multi-step task, before touching code
nanobanana
by eyadsibai
Use when "nanobanana", "generate image", "create image", "edit image", "AI drawing", "Gemini image", "image generation"