メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | ask-database |
| description | 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. |
| license | MIT |
Translate a question into SQL, run it through QueryBear's read-only gateway, and return the answer in plain language.
QueryBear is read-only — never propose this skill for INSERT/UPDATE/DELETE/DDL. Mutations will be rejected by the gateway.
Pick a connection.
get_schema and run_query with no connection argument.list_connections once and ask the user to pick (or infer from context: "production" vs "staging").Read the schema once per task with get_schema. Note the relevant tables and column types before writing SQL. Don't guess column names.
Write a focused SELECT.
LIMIT — usually 100 — unless the user explicitly asks for everything.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.
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.
**Answer:** <one sentence with the number/list/whatever>
```sql
<the query you ran>
| col | col |
|---|---|
| ... | ... |
## Don't
- Don't try to mutate. QueryBear blocks it; even attempting wastes a turn.
- Don't `SELECT *` on a wide table without a `LIMIT`.
- Don't guess column names. Re-read the schema if you're unsure.
- Don't return a 500-row table inline. Summarize and offer the full export.
## Reference
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`.
Strip the AI-isms out of any text — em-dash overuse, "It's not just X, it's Y", inflated significance, sycophantic openers, rule-of-three padding. Use when the user says "humanize this", "make this less AI", "tighten this", or pastes obviously-AI prose and asks for a rewrite.
Interview the user relentlessly about a plan or design until every branch of the decision tree is resolved. Use when the user says "grill me", "stress-test this plan", "poke holes in this", or "what am I missing".
Look at what the user keeps re-explaining to the agent and propose new SKILL.md files that would replace those repeated explanations. Use when the user says "what skills should I have", "suggest skills", "audit my skills", or when you notice you're being asked the same kind of task three times in a row.
Take a raw bug report and turn it into a clean, prioritized ticket with a title, repro steps, and severity. Use when the user says "triage this", pastes a support escalation, or asks "what's this bug".
Read a pull request diff like a senior engineer. Flag risk, suggest tests, point out missing edge cases. Use when the user asks to "review PR", "look at this diff", or pastes a GitHub PR URL.