Modern vision projects require choices across detection, segmentation, VLMs, depth, and deployment. This skill guides architecture, model selection, optimization, and edge deployment for practical computer vision systems.

Analytical database work needs schema and query choices that match ClickHouse behavior. This skill gives Claude, Codex, and Claude Code practical patterns for tables, ingestion, aggregation, monitoring, and pipelines.

Custom D3.js visualisation work requires many chart patterns and integration choices. This skill provides reusable guidance, templates, and references for building interactive SVG charts.

RAG projects can ingest weak or unsupported sources that reduce answer quality. This skill gives a structured verification workflow before content enters the knowledge base.

ClickHouse projects often need better schema choices, faster queries, and safer ingestion patterns. This skill provides practical ClickHouse table, query, monitoring, and pipeline guidance.

Teams often struggle to turn metrics, dashboards, and research into clear business decisions. This skill structures analysis, KPI design, forecasting, and recommendations for Claude, Codex, and Claude Code.

Database setup and automation across LibreOffice Base can require unfamiliar connection formats and UNO services. This skill provides focused workflows, examples, and operational guidance.

Azure Monitor queries require correct clients, credentials, resource identifiers, time ranges, and response handling. This skill provides focused Python and Kusto patterns for logs and metrics.

Azure Table integrations require careful client, key, query, and transaction choices. This skill provides focused Python patterns for Storage Tables and Cosmos DB Table API.

Cosmos DB applications require correct authentication, partitioning, queries, and throughput choices. This skill provides practical Python SDK patterns for common NoSQL workflows.

Manual image inspection limits scale. This skill guides Azure AI Vision workflows for captions, OCR, objects, people, and smart crops.

Building reliable NLP workflows requires correct SDK setup and operation selection. This skill provides practical Python patterns for Azure AI Language text analysis.

Document extraction workflows require precise Azure REST SDK patterns and asynchronous operation handling. This skill provides practical TypeScript guidance for analysis, classification, and custom models.

Documents and media are difficult to convert into consistent, searchable data. This skill guides Python workflows using Azure AI Content Understanding analyzers and structured results.

Time-series monitoring requires reliable patterns for detecting unusual behavior. This skill provides Java examples for Azure AI client setup, analysis, training, inference, and model management.

Unclear events and inconsistent conversions make analytics difficult to trust. This skill creates decision-focused measurement plans, quality scores, validation steps, and governance guidance.

Amplitude workflows require careful tool lookup, ID resolution, and status checks. This skill guides Claude, Codex, and Claude Code through Rube MCP tool sequences for common Amplitude tasks.

Airflow pipelines often fail because dependencies, retries, sensors, and tests are designed inconsistently. This skill provides reusable patterns for production DAG design and validation.

Weak experiment design creates misleading results and wasted traffic. This skill applies hypothesis, metrics, sample size, tracking, execution, and analysis gates before decisions.

Choosing the wrong chart can hide or distort important data patterns. This skill helps Claude, Codex, and Claude Code select chart types, improve dashboards, and explain visualization choices.