From Boardroom Analyst
Validate a local DuckDB database and dbt artifacts, then build datamart_context.json for governed executive analysis. Use when the user connects a DuckDB datamart, dbt project, manifest.json, catalog.json, or asks whether their data mart is ready for Boardroom Analyst.
How this skill is triggered — by the user, by Claude, or both
Slash command
/boardroom-analyst:boardroom-onboardingThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Build the semantic context before answering business questions.
Build the semantic context before answering business questions.
target/manifest.json; use target/catalog.json and dbt YAML docs when present.python <plugin-root>/scripts/build_datamart_context.py --dbt-project <dbt-project> --output datamart_context.json
python <plugin-root>/scripts/run_duckdb_query.py --database <warehouse.duckdb> --query-id q_healthcheck --sql "select 1 as ok" --output analysis_runs/q_healthcheck.json
datamart_context.json. Report table coverage, documented metrics, warning count, and any low-trust tables.For artifact fields and refusal behavior, read ../../references/artifacts.md and ../../references/trust-policy.md when needed.
npx claudepluginhub kasrsf/boardroom-analyst --plugin boardroom-analystSearches MemPalace before answering questions about past work, people, projects, or prior decisions. Returns verbatim stored content instead of guessing from model memory.
Guides Payload CMS config (payload.config.ts), collections, fields, hooks, access control, APIs. Debugs validation errors, security, relationships, queries, transactions, hook behavior.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.