メニュー
Discover which GhostCrab dimensions, facets, graph edges, projections, and evidence paths can support a natural-language answer via MCP. Use when a projection contract is not enough, when the user asks what data exists, or how to move from a business question to evidence-backed JSON.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Audit gaps between a natural-language GhostCrab question and evidence available through MCP on a SQLite workspace. Use when a projection is missing, a Type A contract exists without evidence, required facets or graph edges are not verified, a Type B snapshot is absent, an MCP tool fails, or the user asks what to add to make an operational answer reliable.
Review GhostCrab projections and explain purpose, readiness, required dimensions, facets, edges, and limits. Use for projection scope review, Type A contracts, Type B snapshots, or readiness on a Personal workspace.
Audit gaps between a natural-language GhostCrab question and evidence available through MCP on a SQLite workspace. Use when a projection is missing, a Type A contract exists without evidence, required facets or graph edges are not verified, a Type B snapshot is absent, an MCP tool fails, or the user asks what to add to make an operational answer reliable.
Review GhostCrab projections and explain purpose, readiness, required dimensions, facets, edges, and limits. Use for projection scope review, Type A contracts, Type B snapshots, or readiness on a Personal workspace.
Transform GhostCrab/MindBrain materialized projection responses into visual, presentation-ready reports with KPI cards, timelines, deltas, heatmaps, evidence tables, provenance, and recommendations. Use when a user wants a projection report to be clearer, more narrative, more visual, or demo-ready.
Audit gaps between a natural-language GhostCrab question and evidence available through MCP on a SQLite workspace. Use when a projection is missing, a Type A contract exists without evidence, required facets or graph edges are not verified, a Type B snapshot is absent, an MCP tool fails, or the user asks what to add to make an operational answer reliable.
| name | ghostcrab-evidence-discovery |
| description | Discover which GhostCrab dimensions, facets, graph edges, projections, and evidence paths can support a natural-language answer via MCP. Use when a projection contract is not enough, when the user asks what data exists, or how to move from a business question to evidence-backed JSON. |
Map a business question to MCP surfaces that can answer it on SQLite Personal.
References: RUNTIME_QUERY_PIPELINE.md, ARTIFACT_KINDS.md, PROJECTIONS_DISCOVERY.md, ENUM_BUSINESS_FACETS.md.
Resolve {starterkit} via STARTERKIT_PATHS.md — Phase B runtime section in {starterkit}/personal-mcp/SOP_SEQUENCE.md.
ghostcrab_status + active workspace.ghostcrab_projections_list when projection ids or scopes are unknown.ghostcrab_facet_catalog / ghostcrab_facet_inspect with <module>.<slot_snake_case> keys — see ENUM_BUSINESS_FACETS.md.ghostcrab_search / ghostcrab_count on agent_facts.ghostcrab_combined_search when graph-linked facts may matter.ghostcrab_schema_list / ghostcrab_schema_inspect for registered ghostcrab:* shapes and target=facets module schemas.ghostcrab_pack for active analysis_plan projections.ghostcrab_graph_search / ghostcrab_traverse for graph paths.ghostcrab_coverage for schema population overview.Formal ontology dimensions (LinkML) live in ontology_* — discover via ghostcrab_ontology_list after ghostcrab_ontology_import or CLI compile, not via bare schema_register for LinkML source.
{
"question": "",
"workspace_id": "",
"evidence_paths": [],
"pack_context": null,
"graph_context": null,
"projection_scopes": [],
"gaps": [],
"mcp_tools_used": []
}
Gap labels: no_facts, no_graph_path, projection_only, ontology_vocab_missing, tool_gap.
ghostcrab_traverse or ghostcrab_graph_search results.ghostcrab-gap-auditor.