PBI Schema Authoring
SkillProductivityUse when creating, updating, renaming, or deleting tables, columns, calculated columns, relationships, hierarchies, calendars, or partitions, or changing refresh strategy and incremental refresh policy. For measures, calculation groups, or named expressions, use mcp-engine-semantic-authoring; for RLS roles or perspectives, use mcp-engine-security-governance; for multi-object refactors or renames with downstream consumers, use mcp-engine-refactoring.
Available today. Use it from your connected AI after setup.
No other account needed.
Connect ahel once, and every AI you use reads what you have installed.
Then ask your AI: use the PBI Schema Authoring skill
What this skill tells your AI
The instructions your AI receives, as published by maxanatsko/mcp-engine-public in skills/mcp-engine-schema-authoring/SKILL.md and read by ahel’s review.
Physical model structure work through manage_schema. Keep edits explicit, ordered, and dependency-aware.
Safe edit order
- Inspect current state:
list_model{ "operation": "list", "spec": { "type": "tables" } }, then repeat forcolumnsandrelationships(spec.typetakes exactly one value per call). - Before renaming or deleting, check consumers:
manage_dependencies{ "operation": "used_by", "spec": { "target": { "type": "column", "table": "<table>", "name": "<column>" } } }(spec.targetis required on every call, with the object's singular type);{ "operation": "summary", "spec": { "target": ... } }to gauge impact breadth. - For multi-object or risky edits, pin a rollback point first:
manage_model_changes{ "operation": "pin_checkpoint", "name": "before-<edit>" }(nameis required), and preferdry_run: trueon the write. - Apply the
manage_schemaoperation (create_table,update_column_properties,create_calc_column,create_relationship,create_hierarchy,create_partition,refresh_partition, …) with per-item identifiers inside each bulk item. - Validate after the edit: a scoped
run_query{ "operation": "execute", "query": "<validation query>" }that exercises the changed relationship, column, or partition.
Branch by task
- Tables, columns, calculated columns, visibility, formatting, date-table marking: column-and-table-authoring-guide.
- Relationships — re-check filter direction, inactive relationships, and ambiguity before applying: relationships-guide.
- Hierarchies: hierarchies-guide. Calendars and date tables: calendar-guide.
- Partitions and refresh scope: partitions-refresh-guide. Incremental policy design: incremental-refresh-policy-guide.
Guardrails
- Confirm destructive changes and refresh-impacting edits with the user before execution.
- Keep schema changes separate from semantic rewrites unless the task explicitly spans both.
Report results
After schema work, report:
- Each operation applied, with table and target names.
- Whether
dry_runortransactionwas used and the outcome. - Dependency-check results for renamed or deleted objects.
- The validation query run and its result.
- The checkpoint or transaction available for rollback.
Signals
- GitHub stars
- 256
- Forks
- 65
- Last commit
- Aug 2026
Advanced
- Catalog kind
- skill
- Gateway key
mcp-engine-schema-authoring- Source
- github.com/maxanatsko/mcp-engine-public