Claude Skills by FerroxLabs

Knowledge graph engineering covering ontology design, graph database selection (Neo4j, Amazon Neptune, ArangoDB), entity and relation extraction from text, graph-based RAG (GraphRAG), knowledge graph embeddings, graph query optimization, and integration patterns with LLM systems. Use when the user asks about knowledge graph builder, knowledge graph builder best practices, or needs guidance on knowledge graph builder implementation. Do NOT use when the user needs a different specialized skill ...

Large language model fine-tuning expertise covering LoRA and QLoRA parameter-efficient methods, full fine-tuning strategies, dataset preparation and curation, instruction tuning, DPO alignment, evaluation frameworks, Hugging Face TRL and PEFT libraries, compute optimization, and deployment of fine-tuned models. Use when the user asks about llm fine tuner, llm fine tuner best practices, or needs guidance on llm fine tuner implementation. Do NOT use when the user needs a different specialized s...

Guides expert-level llm integration patterns implementation: ai-ml and backend decision frameworks, production-ready patterns, and concrete templates for llm integration patterns workflows. Use when the user asks about llm integration patterns, llm integration patterns configuration, or ai-ml best practices for llm projects. Do NOT use when the user needs a different ai ml engineering capability -- check sibling skills in the ai ml engineering subcategory.

LLM API integration covering OpenAI, Anthropic, and Google API patterns, streaming responses, function calling and tool use, token counting, cost optimization, fallback strategies, rate limit handling, response caching, and multi-model routing. Use when the user asks about llm integrator, llm integrator best practices, or needs guidance on llm integrator implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Machine learning operations covering MLflow experiment tracking and model registry, model versioning and reproducibility, model serving with TorchServe and Triton, A/B testing models in production, data and concept drift detection, feature stores, CI/CD for ML pipelines, and GPU resource optimization. Use when the user asks about ml ops engineer, ml ops engineer best practices, or needs guidance on ml ops engineer implementation. Do NOT use when the user needs a different specialized skill or...

ML pipeline design covering feature engineering, model training workflows, hyperparameter tuning, cross-validation, experiment tracking (MLflow, W&B), model versioning, data versioning (DVC), reproducibility, and pipeline orchestration. Use when the user asks about ml pipeline, ml pipeline best practices, or needs guidance on ml pipeline implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

MLOps and deployment covering model serving (TorchServe, TF Serving, Triton), containerized inference, A/B testing deployment, model monitoring (data drift, concept drift), feature stores, CI/CD for ML, GPU optimization, and model compression. Use when the user asks about mlops engineer, mlops engineer best practices, or needs guidance on mlops engineer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Advanced model evaluation covering LLM benchmarks, evaluation frameworks (lm-evaluate-harness, HELM, RAGAS), leaderboard interpretation, custom metrics design, human evaluation protocols, automated LLM-as-judge patterns, and evaluation pipeline architecture for both traditional ML and generative AI systems. Use when the user asks about model evaluation specialist, model evaluation specialist best practices, or needs guidance on model evaluation specialist implementation. Do NOT use when the u...

ML model assessment covering classification metrics (precision, recall, F1, AUC-ROC), regression metrics (MAE, RMSE, R2), confusion matrix analysis, cross-validation strategies, bias detection, fairness metrics, and A/B testing for models. Use when the user asks about model evaluator, model evaluator best practices, or needs guidance on model evaluator implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Multimodal AI pipeline design covering vision-language models, text-audio integration, image generation, model selection across modalities, preprocessing pipelines, fusion architectures, and production deployment of multi-modal inference systems. Use when the user asks about multimodal ai builder, multimodal ai builder best practices, or needs guidance on multimodal ai builder implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technolo...

NLP processing covering tokenization, named entity recognition, sentiment analysis, text classification, summarization, topic modeling, language detection, text preprocessing, transformer architecture, and Hugging Face pipeline usage. Use when the user asks about nlp engineer, nlp engineer best practices, or needs guidance on nlp engineer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Advanced Notion workspace design covering database architecture, relations and rollups, templates, dashboard creation, team workspaces, formulas, API integrations, and using Notion as a CRM, project manager, and knowledge wiki. Use when the user asks about notion master, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of notion master or requires a different specialized skill.

Advanced Obsidian knowledge management covering Zettelkasten methodology, linking strategy, graph navigation, essential community plugins, templates, daily notes workflow, publishing options, and personal knowledge management principles. Use when the user asks about obsidian power user, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of obsidian power user or requires a different specialized skill.

PKM systems comparison covering PARA, Zettelkasten, GTD, and Building a Second Brain methodologies with capture workflows, processing routines, retrieval strategies, tool selection guidance, and information diet management. Use when the user asks about personal knowledge manager, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of personal knowledge manager or requires a different specialized skill.

Prompt engineering mastery covering chain-of-thought reasoning, few-shot learning, system prompt design, structured output with JSON mode, prompt injection prevention, temperature and top-p tuning, context window management, evaluation metrics, and A/B testing prompts. Use when the user asks about prompt engineer, prompt engineer best practices, or needs guidance on prompt engineer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated tec...

Guides expert-level prompt engineering implementation: ai-ml and best-practices decision frameworks, production-ready patterns, and concrete templates for prompt engineering workflows. Use when the user asks about prompt engineering, prompt engineering configuration, or ai-ml best practices for prompt projects. Do NOT use when the user needs a different ai ml engineering capability -- check sibling skills in the ai ml engineering subcategory.

RAG system design covering document chunking strategies, embedding model selection, vector database selection (Pinecone, Weaviate, Chroma, pgvector), retrieval strategies (hybrid search, re-ranking), context window packing, and assessment of faithfulness and relevance. Use when the user asks about rag architect, rag architect best practices, or needs guidance on rag architect implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technolog...

Guides expert-level rag pipeline design implementation: ai-ml and database decision frameworks, production-ready patterns, and concrete templates for rag pipeline design workflows. Use when the user asks about rag pipeline design, rag pipeline design configuration, or ai-ml best practices for rag projects. Do NOT use when the user needs a different ai ml engineering capability -- check sibling skills in the ai ml engineering subcategory.

Advanced Excel and Google Sheets mastery covering lookup functions, pivot tables, conditional formatting, macros and Apps Script, data validation, dashboard creation, and financial modeling techniques for business analysis. Use when the user asks about spreadsheet wizard, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of spreadsheet wizard or requires a different specialized skill.

Synthetic data generation covering LLM-based data creation, statistical data synthesis, privacy-preserving techniques (differential privacy, k-anonymity), tabular data generation, text augmentation, image augmentation, validation frameworks, and quality assurance for generated datasets. Use when the user asks about synthetic data generator, synthetic data generator best practices, or needs guidance on synthetic data generator implementation. Do NOT use when the user needs a different speciali...

Guides expert-level vector database patterns implementation: ai-ml and database decision frameworks, production-ready patterns, and concrete templates for vector database patterns workflows. Use when the user asks about vector database patterns, vector database patterns configuration, or ai-ml best practices for vector projects. Do NOT use when the user needs a different ai ml engineering capability -- check sibling skills in the ai ml engineering subcategory.

Vector database engineering covering Pinecone, Weaviate, Qdrant, pgvector, Milvus, and Chroma selection and configuration, indexing strategies (HNSW, IVF, PQ), similarity search optimization, hybrid search, filtering, multi-tenancy, scaling patterns, and production operations. Use when the user asks about vector db engineer, vector db engineer best practices, or needs guidance on vector db engineer implementation. Do NOT use when the user needs a different specialized skill or is asking about...

Systematic API design quality assessment evaluating REST and GraphQL APIs for consistency, usability, documentation completeness, and adherence to best practices. Use when the user asks about api design review, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of api design review or requires a different specialized skill.

REST and GraphQL API design expertise covering REST maturity model, resource naming, pagination patterns, filtering and sorting, HATEOAS, versioning strategies, error response formats, rate limiting headers, and OpenAPI specification. Use when the user asks about api designer, api designer best practices, or needs guidance on api designer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Expert guide for designing and configuring API gateways including Kong, AWS API Gateway, and cloud-native solutions. Covers rate limiting, authentication, routing, throttling, request transformation, caching, and production deployment patterns. Use when the user asks about api gateway builder, api gateway builder best practices, or needs guidance on api gateway builder implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Authentication and authorization engineering expertise covering JWT architecture, OAuth 2.0/OIDC flows, session management, RBAC/ABAC, MFA implementation, API key management, token refresh, PKCE flow, and SSO integration. Use when the user asks about auth engineer, auth engineer best practices, or needs guidance on auth engineer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Guides expert-level authentication patterns implementation: security and web-development decision frameworks, production-ready patterns, and concrete templates for authentication patterns workflows. Use when the user asks about authentication patterns, authentication patterns configuration, or security best practices for authentication projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Guides expert-level authorization patterns implementation: security and design-patterns decision frameworks, production-ready patterns, and concrete templates for authorization patterns workflows. Use when the user asks about authorization patterns, authorization patterns configuration, or security best practices for authorization projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Expert guide for designing reliable background job systems including worker architectures, queue selection, retry strategies, dead letter queues, idempotency patterns, job scheduling, and monitoring for production workloads. Use when the user asks about background job designer, background job designer best practices, or needs guidance on background job designer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Guides expert-level background jobs patterns implementation: architecture and optimization decision frameworks, production-ready patterns, and concrete templates for background jobs patterns workflows. Use when the user asks about background jobs patterns, background jobs patterns configuration, or backend best practices for background projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Guides expert-level caching strategies implementation: optimization and database decision frameworks, production-ready patterns, and concrete templates for caching strategies workflows. Use when the user asks about caching strategies, caching strategies configuration, or backend best practices for caching projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Caching architecture expertise covering cache-aside, write-through, write-behind, read-through patterns, TTL strategies, cache invalidation, CDN caching, application caching, database query caching, distributed caching, and cache warming. Use when the user asks about caching strategist, caching strategist best practices, or needs guidance on caching strategist implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

ClickHouse columnar OLAP expert covering table engine selection (MergeTree family), materialized views, aggregating merge trees, data sharding and replication, query optimization for analytical workloads, data ingestion patterns, and partition management for high-performance analytics. Use when the user asks about clickhouse analyst, clickhouse analyst best practices, or needs guidance on clickhouse analyst implementation. Do NOT use when the user needs a different specialized skill or is ask...

CockroachDB distributed SQL expert covering multi-region deployment, survivability goals, schema design for distributed systems, online schema changes, transaction contention management, follower reads, locality-optimized partitioning, and operational best practices for globally distributed SQL databases. Use when the user asks about cockroachdb engineer, cockroachdb engineer best practices, or needs guidance on cockroachdb engineer implementation. Do NOT use when the user needs a different s...

Database schema design expertise covering normalization, denormalization strategies, indexing, query optimization, partitioning, connection pooling, migration management, multi-tenancy patterns, and read replicas. Use when the user asks about database architect, database architect best practices, or needs guidance on database architect implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Database schema migration expert covering zero-downtime migration strategies, schema evolution patterns, data backfill techniques, migration tooling (Flyway, Liquibase, custom), rollback planning, blue-green database deployments, large table migrations, and migration testing strategies. Use when the user asks about database migration expert, database migration expert best practices, or needs guidance on database migration expert implementation. Do NOT use when the user needs a different speci...

Guides expert-level database migration patterns implementation: database and automation decision frameworks, production-ready patterns, and concrete templates for database migration patterns workflows. Use when the user asks about database migration patterns, database migration patterns configuration, or database best practices for database projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Database performance assessment evaluating query efficiency, indexing strategy, connection management, configuration, and scaling readiness to produce an actionable performance scorecard. Use when the user asks about database performance audit, related techniques, best practices, or needs guidance in this domain. Do NOT use when the request is outside the scope of database performance audit or requires a different specialized skill.

Amazon DynamoDB expert covering single-table design, partition key strategies, GSI and LSI patterns, capacity modes (on-demand vs provisioned), DynamoDB Streams, transactions, TTL, DAX caching, and access pattern-driven data modeling for NoSQL at scale. Use when the user asks about dynamodb architect, dynamodb architect best practices, or needs guidance on dynamodb architect implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology...

Elasticsearch design and operations expertise covering index design, mapping types, custom analyzer configuration, search query construction (bool, multi-match, function_score), aggregations, index lifecycle management, cluster sizing and architecture, performance tuning, and Kibana dashboard creation. Use when the user asks about elasticsearch engineer, elasticsearch engineer best practices, or needs guidance on elasticsearch engineer implementation. Do NOT use when the user needs a differen...

Event-driven architecture expertise covering event sourcing, CQRS, message brokers (Kafka, RabbitMQ), saga patterns, eventual consistency, idempotency, event schema design, dead letter queues, and building resilient distributed systems. Use when the user asks about event driven architect, event driven architect best practices, or needs guidance on event driven architect implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

File processing pipeline expertise covering upload handling (multipart, streaming, resumable), virus scanning, image processing, PDF generation, storage backends, presigned URLs, and file type validation. Use when the user asks about file processor, file processor best practices, or needs guidance on file processor implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Graph database engineering expert covering Neo4j administration and Cypher optimization, property graph modeling patterns, traversal algorithms (BFS, DFS, shortest path), graph indexing strategies, performance tuning, use case evaluation, graph data pipelines, and comparison with relational approaches. Use when the user asks about graph database engineer, graph database engineer best practices, or needs guidance on graph database engineer implementation. Do NOT use when the user needs a diffe...

Graph database design expertise covering Neo4j and Cypher query language, property graph model, graph schema design, traversal patterns, path algorithms (shortest path, all paths), graph indexing, community detection, recommendation engines, knowledge graphs, and graph data modeling best practices. Use when the user asks about graph db architect, graph db architect best practices, or needs guidance on graph db architect implementation. Do NOT use when the user needs a different specialized sk...

GraphQL schema design expertise covering schema-first vs code-first, resolver patterns, DataLoader for N+1 prevention, subscriptions, federation, authentication, Relay cursor pagination, error handling, and schema evolution. Use when the user asks about graphql builder, graphql builder best practices, or needs guidance on graphql builder implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Guides expert-level graphql implementation implementation: api-design and frameworks decision frameworks, production-ready patterns, and concrete templates for graphql implementation workflows. Use when the user asks about graphql implementation, graphql implementation configuration, or api-design best practices for graphql projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Guides expert-level graphql schema design implementation: api-design and design-patterns decision frameworks, production-ready patterns, and concrete templates for graphql schema design workflows. Use when the user asks about graphql schema design, graphql schema design configuration, or api-design best practices for graphql projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Expert guide for designing and building gRPC services including protobuf schema design, streaming patterns, interceptors, error handling, load balancing, and performance optimization across polyglot environments. Use when the user asks about grpc engineer, grpc engineer best practices, or needs guidance on grpc engineer implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.

Guides expert-level message queue patterns implementation: architecture and automation decision frameworks, production-ready patterns, and concrete templates for message queue patterns workflows. Use when the user asks about message queue patterns, message queue patterns configuration, or backend best practices for message projects. Do NOT use when the user needs a different backend infrastructure capability -- check sibling skills in the backend infrastructure subcategory.

Microservices architecture expertise covering service decomposition, inter-service communication, saga pattern, API gateway, service mesh, distributed tracing, data ownership, and monolith decomposition strategies. Use when the user asks about microservices architect, microservices architect best practices, or needs guidance on microservices architect implementation. Do NOT use when the user needs a different specialized skill or is asking about an unrelated technology domain.