Answer a question from data
Answer a question from a database or table: read the schema, write a read-only query, sanity-check the result, and answer with the query shown.
In Lobstack: Skills › Library › Add
What your agent will do.
Someone asks a question the numbers can answer — how many, how much, which, since when — and the data is in a connected database, an Airtable base or a file.
- 01
Restate the question with its terms pinned down: the date range, the timezone, what counts as a "customer" or an "active" user. Ask when a choice would change the answer.
- 02
Read the schema and a few sample rows before writing a query. Column names mislead; "created_at" is sometimes the import date.
- 03
Write one read-only query. Never insert, update, delete or alter anything, even when the connection would allow it.
- 04
Sanity-check before answering: the row count, nulls in the columns you used, the date range actually returned, and rows doubled by a join. A join that doubles rows doubles the answer.
- 05
Answer in one sentence first, then show the query, then the checks you ran and any rows you left out and why.
- 06
When the answer is a trend or a comparison, add a chart in a chart fence.
- 07
When the data cannot answer the question, name the missing table or field instead of approximating.
Show the query every time. A number nobody can re-run is an opinion.
The whole SKILL.md: 34 lines of Markdown.
Add it in the app from Skills › Library, or copy it and paste it into Skills › Add a skill.
---name: data-questiondescription: "Answer a question from a database or table: read the schema, write a read-only query, sanity-check the result, and answer with the query shown."metadata: title: "Answer a question from data" category: data tags: [data, sql]--- ## When to use this Someone asks a question the numbers can answer -- how many, how much, which,since when -- and the data is in a connected database, an Airtable base or afile. ## How 1. Restate the question with its terms pinned down: the date range, the timezone, what counts as a "customer" or an "active" user. Ask when a choice would change the answer.2. Read the schema and a few sample rows before writing a query. Column names mislead; "created_at" is sometimes the import date.3. Write one read-only query. Never insert, update, delete or alter anything, even when the connection would allow it.4. Sanity-check before answering: the row count, nulls in the columns you used, the date range actually returned, and rows doubled by a join. A join that doubles rows doubles the answer.5. Answer in one sentence first, then show the query, then the checks you ran and any rows you left out and why.6. When the answer is a trend or a comparison, add a chart in a chart fence.7. When the data cannot answer the question, name the missing table or field instead of approximating. Show the query every time. A number nobody can re-run is an opinion.
- Data
Data report with spreadsheet
Turn a dataset or export into a report: the working spreadsheet with formulas, and a short document with charts that says what the numbers mean.
SKILL.md · App - Data
What changed in the numbers
Check a set of numbers for what changed: compare to the usual range, find the biggest moves, and say which ones are real.
SKILL.md · App - Data
What the launch did
Read how a campaign did per channel — clicks, signups, replies — from analytics and the Distribution table, and say which channel to repeat and which to drop, with the numbers.
SKILL.md · App - Engineering
Commit message from a diff
Write a commit message from a diff: a subject line that states what was found, then prose explaining why the change was made.
SKILL.md · App - Engineering
Triage a failing build
Triage a red CI run: find the first real failure, attribute it to a change, and say whether the code is wrong or the runner was.
SKILL.md · App - Engineering
Review what a linter cannot
Review a change for what a linter cannot see: whether it is correct, what it breaks elsewhere, and which parallel list it forgot to update.
SKILL.md · App