ae-dataops — Claude Code skill: DataOps via ae-cli

What ae-dataops does

The skill maps agent behaviour onto ae-cli across six domains: dataops_repo, dataops_datatable, dataops_flow, dataops_operations, dataops_ide, dataops_integration. It ships parameter tables, output and error handling notes, plus reference files for tables, flows and entity lifecycle. The agent opens only the section matching the task at hand.

The ground rules matter more than the command list. Table and field edits land in DEV, and a release to PROD is a separate step you ask for. Manual flow runs and backfills go to PROD. Which environment a SQL query hits follows from the tables it touches, so a sample query is no reason to pick one. Ordinary write commands run without --yes; the flag is reserved for high-risk-write after you confirm. --dry-run on field mutations and recycling checks server state, while elsewhere it only echoes the local request and validates nothing about permissions, connections or SQL.

ae-cli must be on PATH — the skill declares it as a required binary, and nothing runs without it. One trap worth knowing: ok:true is not proof the job finished, because data can still hold REJECTED or FAILED. Async calls hand back an ID, and that same operation is what you poll; resubmitting because it is still running just duplicates work.