← PresetCONTENT HISTORY
WHAT CHANGED
Update to Preset
Snapshot Oct 24, 2026 · 13:46 UTC · version 0.1.4
Collection source: downloaded plugin package.
First saved snapshot
No earlier snapshot is available to establish a change.
Save Preset and check future changes in Following.
Up to 10 plugins free · no card required.
Compare saved observations
Download comparison JSONFull technical diff · 0 changed fields
Full snapshot data
{
"description": "Use Superset MCP tools for dataset inspection, semantic-layer querying, and virtual dataset creation. Use only for MCP tool workflows; do not use for direct API work.",
"included_files": [
{
"relative_path": "references/dataset-workflows.md",
"size_in_bytes": 731
}
],
"name": "preset-mcp-datasets",
"skill_md_contents": "---\nname: preset-mcp-datasets\ndescription: Use Superset MCP tools for dataset inspection, semantic-layer querying, and virtual dataset creation. Use only for MCP tool workflows; do not use for direct API work.\n---\n\n# preset-mcp-datasets\n\nUse for dataset-centered MCP workflows.\n\n## Always\n\n- Use `list_datasets` and `get_dataset_info` for dataset discovery.\n- Respect permission-denied responses; do not work around them with chart, dashboard, SQL, or API calls.\n- Use saved metrics and dimensions from `get_dataset_info`; `query_dataset` accepts saved metrics only, not ad-hoc expressions. When no saved metric fits, compute the aggregate with `execute_sql` (route to `preset-mcp-sqllab`) instead of guessing metric names or stopping to ask.\n- Use `query_dataset` for semantic-layer data results.\n- Use `create_virtual_dataset` only when the user wants to save SQL as a chartable dataset.\n\n## Decision Rules\n\n- Metadata only: `list_datasets`, `get_dataset_info`.\n- Result table from metrics/dimensions: route through `preset-mcp-data` / `query_dataset`.\n- SQL-to-chartable-dataset workflow: `create_virtual_dataset`.\n- Visualization from dataset: route to `preset-mcp-visualization`.\n- Database discovery: use `list_databases` and `get_database_info` through discovery.\n\n## Workflow Order\n\n1. Find the dataset with one list/search call (use a search filter and sufficient `page_size`); paginate or refine the filter only when the target is not in the returned page.\n2. Inspect columns and metrics with one `get_dataset_info` call before data or chart workflows.\n3. Query semantic-layer results only when the user asks for data.\n4. Save virtual datasets only when persistence is requested.\n\n## Retrieve\n\n- Dataset workflows: [references/dataset-workflows.md](references/dataset-workflows.md)\n"
}SHA-256 of public snapshot: 7073b88e69fa33e33a8f19010822802e2a298c06565a4c4c8b347933f5f75612