dr-financial-summary

Financial Summary

What this skill does

A quick overview of the user's financial data — revenue, key expense categories, gross profit, gross margin, monthly trend direction. Built for a morning check-in or 30-second meeting prep. Uses the aggregation start→poll tools (start_aggregation_by_alias → get_aggregation_result_by_alias, or their by-id twins) for real totals — no row caps, no estimation from samples. Totals default to the latest complete fiscal year (or trailing 12 closed months), never an unscoped all-time figure, and every snapshot is labeled with the period and scenario it covers.

This skill is self-contained: it discovers the client's financials table and field names itself (Step 2). It does not depend on a saved profile, a learn step, or any prior setup — every Datarails environment names its table and fields differently, so discovery happens inline, once per conversation.

Workflow

Step 1: Verify the connection

If any Datarails tool call fails with an authentication or connection error, tell the user:

The Datarails connector isn't connected. Click the "+" button next to the prompt, select Connectors, find Datarails, and click Connect.

Then STOP — do not retry until the user reconnects.

Step 2: Discover the financials table and its fields

If you already identified the financials table, its field names, and the account categories earlier in THIS conversation, reuse them — skip to Step 3. Discovery is cheap but not free; do it once per conversation, then carry the values forward.

1. list_data_models. Pick the financials table: the one whose name (or alias) matches /financial|cube|p&?l|ledger|gl/i; if none match, the largest by row count. Note both its numeric id and its alias (the alias may be empty). Prefer the alias path when an alias exists — friendlier field names, far fewer tokens.

2. Fields. If the table has an alias, list_aliased_fields(<alias>); otherwise get_fields_by_id(<financials_table_id>) (capture each field's numeric id — the by-id tools address fields by id). Bind these by case-insensitive match on the field alias/name (respecting the noted type):

   • <amount_field> — numeric: ^amount$ → transaction_amount → value
   • <scenario_field> — categorical: ^scenario$ → ^version$
   • <date_field> — date/timestamp: reporting_date → posting_date → ^date$
   • <account_level_fields> — categorical: every account-hierarchy level field (alias/name matching an account word with a level-like suffix, e.g. /acc(ount)?.*l\d/i). Keep all levels as candidates — <account_field> (the P&L grain) is chosen in item 3, not here.