Skip to content

Packs

Data and analytics

When to use it
For analysts and the people who rely on their numbers: review SQL for the bugs that quietly inflate a figure, and spec dashboards around a decision instead of every chart that was easy to make.
Covers
Define and trust the numbers (2)
Where you decide
  • G9 review — measure → review
  • G9.1 human — measure → sign-off
Size
7 skills · 1 loop · 2 gates, 2 need a person
npx skilldrop-cli install --pack data-analytics

Installs 7 skills, including core.

Other ways to install

The pack's loops too, each as an invokable skill:

npx skilldrop-cli install --loop --pack data-analytics

In Claude Code, as a plugin (after /plugin marketplace add sananthanarayan/skilldrop):

/plugin install data-analytics@skilldrop

Into Cursor, Kiro or another IDE:

npx skilldrop-cli install --pack data-analytics --ide cursor

Start here: Check a query before its number goes into a report

Paste this into your agent:

Review this Postgres query before it goes into the finance dashboard. One row per region; customers.customer_id is unique and an order has many order_items. Finance reports in New York time.

SELECT c.region, SUM(o.amount_usd) AS revenue_usd
FROM orders o
JOIN customers c ON c.customer_id = o.customer_id
JOIN order_items oi ON oi.order_id = o.order_id
WHERE o.created_at BETWEEN '2026-09-01' AND '2026-09-30'
GROUP BY c.region;
Before you start
  • A SQL query whose number you need to trust, and the database it runs on
How to tell it worked
sql-review opens with a verdict, flags the order_items join as multiplying revenue and the BETWEEN as losing 30 September, gives a corrected query with New York boundaries, and lists verification queries to prove the fix.
If nothing happens
If the review jumps to indexes before correctness, ask for it by name ("use sql-review"). If it guesses the database, tell it which one: integer division and timezone functions differ between engines.

A typical session

When: A number matters (a board metric, a finance figure, a team KPI) and people either disagree about it or are about to build a dashboard on it.

You bring:

  1. sql-review
    You
    Run it on the query that reports the number, with the engine and what one output row should represent.
    You get
    A verdict and line-by-line findings, each with the wrong result and corrected SQL, plus the full corrected query and verification queries.
    You decide
    Trust the number, or fix the SQL and review again. If the findings turn on what the number should mean (timezone, exclusions), settle that with the metric's owner first.
  2. dashboard-spec
    You
    Give it the audience, the decision and the list of requested charts.
    You get
    A one-page spec: questions in priority order, one chart per question with its metric named and any undefined one flagged as a build blocker, filters, freshness SLA, layout, and a cut list.
  3. doc-critique
    You
    Run it on the dashboard spec before sharing it with the BI team.
    You get
    A verdict and severity-tagged findings with a fix for each.
    You decide
    Hand the spec to the builder, or revise it.

You end with: Reviewed SQL whose number you can defend, and a dashboard spec a BI developer can build without guessing.

Loops

Compare Data and analytics with another pack

Skills in this pack (2)

Included from core (5)