ask-database

Name: ask-database
Author: spencerpauly

15stars4forks

How to install ask-database?

spencerpauly/skills-repo/ask-database

$npx -y skills add spencerpauly/skills-repo --skill ask-database

Installs into the current project.

Summary

Answer a natural-language question by writing a SELECT against the user's connected database via the QueryBear MCP. Use when the user asks "how many", "which users", "what's our", "give me a list of", or otherwise asks a question whose answer lives in their database.

Files · 1

View on GitHub

SKILL.md

1	# Ask Database
2
3	Translate a question into SQL, run it through QueryBear's read-only gateway, and return the answer in plain language.
4
5	## When to use
6
7	- The user asks a question whose answer is stored in their database: "how many active subscriptions do we have", "which users haven't logged in in 30 days", "what's the median order value last week".
8	- The user pastes a SQL question or asks "can you run this query".
9
10	QueryBear is read-only — never propose this skill for INSERT/UPDATE/DELETE/DDL. Mutations will be rejected by the gateway.
11
12	## Steps
13
14	1. Pick a connection.
15	- If the user has only one database, skip discovery and call `get_schema` and `run_query` with no `connection` argument.
16	- If they have multiple and you don't know which, call `list_connections` once and ask the user to pick (or infer from context: "production" vs "staging").
17
18	2. Read the schema once per task with `get_schema`. Note the relevant tables and column types before writing SQL. Don't guess column names.
19
20	3. Write a focused SELECT.
21	- Always include a `LIMIT` — usually 100 — unless the user explicitly asks for everything.
22	- Aggregate when the question is a count, sum, average, or distribution.
23	- Prefer one query that answers the question over five exploratory queries.
24
25	4. Run it via `run_query`. If QueryBear rejects the query (blocked column, blocked table, row-limit hit, timeout), surface the error message verbatim — don't paraphrase or guess around it.
26
27	5. Translate the result back to English. Lead with the answer. Show the underlying SQL underneath in a code block so the user can audit it. If the result is a list of more than ~10 rows, summarize patterns and offer to drill in.
28
29	## Output format
30
31	```markdown
32	Answer: <one sentence with the number/list/whatever>
33
34	```sql
35	<the query you ran>
36	```
37
38	\| col \| col \|
39	\|-----\|-----\|
40	\| ... \| ... \|
41	```
42
43	## Don't
44
45	- Don't try to mutate. QueryBear blocks it; even attempting wastes a turn.
46	- Don't `SELECT *` on a wide table without a `LIMIT`.
47	- Don't guess column names. Re-read the schema if you're unsure.
48	- Don't return a 500-row table inline. Summarize and offer the full export.
49
50	## Reference
51
52	QueryBear MCP — read-only SQL gateway with schema introspection, query parsing, and row-limit enforcement. Tools used by this skill: `list_connections`, `get_schema`, `run_query`.

People who liked this also viewed

6 picks

Type

ask-database

15stars4forks

View on GitHub

How to install ask-database?

spencerpauly/skills-repo/ask-database

$npx -y skills add spencerpauly/skills-repo --skill ask-database

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# Ask Database
2
3	Translate a question into SQL, run it through QueryBear's read-only gateway, and return the answer in plain language.
4
5	## When to use
6
7	- The user asks a question whose answer is stored in their database: "how many active subscriptions do we have", "which users haven't logged in in 30 days", "what's the median order value last week".
8	- The user pastes a SQL question or asks "can you run this query".
9
10	QueryBear is read-only — never propose this skill for INSERT/UPDATE/DELETE/DDL. Mutations will be rejected by the gateway.
11
12	## Steps
13
14	1. Pick a connection.
15	- If the user has only one database, skip discovery and call `get_schema` and `run_query` with no `connection` argument.
16	- If they have multiple and you don't know which, call `list_connections` once and ask the user to pick (or infer from context: "production" vs "staging").
17
18	2. Read the schema once per task with `get_schema`. Note the relevant tables and column types before writing SQL. Don't guess column names.
19
20	3. Write a focused SELECT.
21	- Always include a `LIMIT` — usually 100 — unless the user explicitly asks for everything.
22	- Aggregate when the question is a count, sum, average, or distribution.
23	- Prefer one query that answers the question over five exploratory queries.
24
25	4. Run it via `run_query`. If QueryBear rejects the query (blocked column, blocked table, row-limit hit, timeout), surface the error message verbatim — don't paraphrase or guess around it.
26
27	5. Translate the result back to English. Lead with the answer. Show the underlying SQL underneath in a code block so the user can audit it. If the result is a list of more than ~10 rows, summarize patterns and offer to drill in.
28
29	## Output format
30
31	```markdown
32	Answer: <one sentence with the number/list/whatever>
33
34	```sql
35	<the query you ran>
36	```
37
38	\| col \| col \|
39	\|-----\|-----\|
40	\| ... \| ... \|
41	```
42
43	## Don't
44
45	- Don't try to mutate. QueryBear blocks it; even attempting wastes a turn.
46	- Don't `SELECT *` on a wide table without a `LIMIT`.
47	- Don't guess column names. Re-read the schema if you're unsure.
48	- Don't return a 500-row table inline. Summarize and offer the full export.
49
50	## Reference
51
52	QueryBear MCP — read-only SQL gateway with schema introspection, query parsing, and row-limit enforcement. Tools used by this skill: `list_connections`, `get_schema`, `run_query`.

People who liked this also viewed

6 picks

Type