mcp-engine-ai-readines…
Use when preparing or assessing a Power BI semantic model for Copilot, Fabric data agents, or natural-language Q&A — clear…
Use when creating or running model tests, applying test packs, capturing baselines or snapshots, exporting test results, checking dependency impact before a refactor, or using checkpoints, changesets, undo, redo, and rollback. For assessing overall model quality, use
$ npx -y skills add maxanatsko/mcp-engine-public --skill mcp-engine-testing-changes --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/mcp-engine-testing-changesContext preview
The summary Claude sees to decide when to auto-load this skill.
Use when creating or running model tests, applying test packs, capturing baselines or snapshots, exporting test results, checking dependency impact before a refactor, or using checkpoints, changesets, undo, redo, and rollback. For assessing overall model quality, use
name: mcp-engine-testing-changes description: Use when creating or running model tests, applying test packs, capturing baselines or snapshots, exporting test results, checking dependency impact before a refactor, or using checkpoints, changesets, undo, redo, and rollback. For assessing overall model quality, use mcp-engine-model-quality; for authoring the changes themselves, use mcp-engine-schema-authoring or mcp-engine-semantic-authoring; for orchestrating a full multi-object refactor around these safety tools, use mcp-engine-refactoring.
Proof that model changes are safe, reproducible, and reversible, through `manage_tests`, `manage_model_changes`, and `manage_dependencies`.
1. Inspect what exists: `manage_tests` `{ "operation": "list" }`; `manage_model_changes` `{ "operation": "list_checkpoints" }` and `{ "operation": "list_transactions" }`. 2. Validate definitions before saving: `manage_tests` `{ "operation": "validate", "spec": { <complete test definition> } }`, then save the same definition with `{ "operation": "put", "spec": { <same definition> } }` — both operations require the definition (`put` takes `spec` or bulk `items`; payload shapes are in the unit-testing guide). Never save a large generated batch unvalidated. 3. Run the smallest useful scope first: `{ "operation": "run", "spec": { "tags": [...] } }` or `{ "operation": "run", "spec": { "test_ids": [...] } }` before a full-suite run. 4. Export when the user needs a shareable result: `{ "operation": "export", "spec": { "format": "markdown" } }`, or `export_tests` for a portable definition bundle. 5. Before broad edits, pin a rollback point: `manage_model_changes` `{ "operation": "pin_checkpoint", "name": "before-<edit>" }` (`name` is required), or stage the batch as a changeset (`create_changeset` with a `name` → `add_to_changeset` → `preview_changeset` → `apply_changeset`, threading the returned `changeset_id`).
After testing or change-tracking work, report:
1. Tests created, changed, or run, with pass/fail counts and the names of failing tests. 2. Validation outcomes for saved definitions. 3. Baselines or snapshots captured or compared. 4. Checkpoint, changeset, or transaction ids available for rollback.
The SemanticOps MCP (formerly MCP Engine) is a Power BI tool that lets AI assistants like Claude interact with your Power BI models programmatically: read your model structure, run DAX queries, modify your semantic model, and perform advanced analytics - all through natural conversation.
Use when preparing or assessing a Power BI semantic model for Copilot, Fabric data agents, or natural-language Q&A — clear…
Use when starting a SemanticOps MCP session, connecting to a Power BI model, checking the current connection, applying saved…
Use when a Power BI measure or query returns wrong values, unexpected blanks, inflated or duplicated totals, a total row that…
Use when a DAX query, measure, or visual is slow, when interpreting analyze timings, Storage Engine / Formula Engine splits, or…
Use when the user asks for a model audit, model quality review, scorecard, bad-practices or best-practices assessment, or a…
Use when a user types onboarding, asks to set up SemanticOps MCP, wants help choosing Free vs Pro, or wants licensing, modes,…