Knuckles-Team Dataset Readiness Assessment Workflow
Profile a dataset, validate it against reviewed quality rules, and produce an owner-confirmed data dictionary. Use when a local CSV, TSV, JSON, or JSON Lines dataset must be assessed before analysis, ingestion, governance review, or handoff.
Steps
Step 1: dataset-profiler [depends_on: none]
Agent: profiling-specialist
Skill: dataset-profiler
Step 2: data-quality-auditor [depends_on: dataset-profiler]
Agent: quality-specialist
Skill: data-quality-auditor
Step 3: data-dictionary-builder [depends_on: dataset-profiler]
Agent: documentation-specialist
Skill: data-dictionary-builder
Execution
Run this workflow as a dependency-ordered DAG. Steps with no unmet depends_on run in parallel; dependents run after their prerequisites complete.
- Run first (in parallel): Step 1 — dataset-profiler
- After level 0: Step 2 — data-quality-auditor; Step 3 — data-dictionary-builder
Execution: If graph-os is reachable, offload the whole DAG via graph_orchestrate action=execute_workflow (or the kg-delegate skill) for true parallel/swarm execution. Otherwise execute the steps natively in dependency order: run steps with no unmet depends_on in parallel, then their dependents.