Azure Data Factory ML & Analytics Patterns — orchestrate ML workflows with ADF

Prerequisites: an Azure subscription with billed Azure Data Factory, Azure Machine Learning, and (optionally) Databricks usage — no usable free tier; familiarity with ADF pipelines Install "Azure Data Factory ML & Analytics Patterns — orchestrate ML workflows with ADF" for me. It gives my agent @josiahsiegel's ADF ML pattern library: Azure ML batch endpoints via WebActivity (SDK v2, migrated off SDK v1), Azure OpenAI Batch API pipeline patterns, ADF ML scoring orchestration, SQL-to-Storage archival pipelines, AI Services integration via REST connector, Databricks notebook execution from ADF, Data Flow feature engineering, and Synapse/Fabric integration — with a pattern quick-reference, security best practices (managed identity, Key Vault, never hardcode secrets), cost optimization, and links to detailed reference JSON. MIT licensed. Repository: https://github.com/josiahsiegel/claude-plugin-marketplace/blob/main/plugins/adf-master/skills/adf-ml-analytics/SKILL.md 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder and summarize what it does in one or two sentences. 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code — secrets via Key Vault and managed identity only. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "adf-ml-analytics". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. verify the deprecation dates against live Azure docs — the March 2026 notices will go stale; confirm my Azure subscription has the ML and Databricks resources; never put real keys in pipeline JSON). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.