From Boardroom Analyst
Answer executive follow-up questions by running local read-only DuckDB SQL against a dbt-documented datamart, citing query provenance and caveats. Use when the user asks drill-down questions after a Boardroom Analyst brief or wants to query executive metrics interactively.
How this skill is triggered — by the user, by Claude, or both
Slash command
/boardroom-analyst:boardroom-queryThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Answer follow-up questions through a local query loop with provenance.
Answer follow-up questions through a local query loop with provenance.
datamart_context.json and the latest analysis_run.json when available.python <plugin-root>/scripts/run_duckdb_query.py --database <warehouse.duckdb> --query-id q_followup_001 --sql-file <query.sql> --output analysis_runs/q_followup_001.json
Use ../../references/artifacts.md when updating an existing run manifest.
Searches 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.
npx claudepluginhub kasrsf/boardroom-analyst --plugin boardroom-analyst