From 71a733b7c15a9a827e863efdf6d7d713344ca871 Mon Sep 17 00:00:00 2001 From: Eddie A Tejeda <669988+eddietejeda@users.noreply.github.com> Date: Wed, 21 Oct 2026 16:29:10 -0700 Subject: [PATCH] skill: surface SQL writes in the hotdata skill --- skills/hotdata/SKILL.md | 4 ++-- skills/hotdata/references/WORKFLOWS.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/skills/hotdata/SKILL.md b/skills/hotdata/SKILL.md index cdf5b80..4293afd 100644 --- a/skills/hotdata/SKILL.md +++ b/skills/hotdata/SKILL.md @@ -1,6 +1,6 @@ --- name: hotdata -description: Use this skill when the user wants to run core hotdata CLI commands — auth, workspaces, instant databases, tables, basic SQL query, database context (context:DATAMODEL), jobs, datasources/ingests/runs (pull external data), and skill install. Activate for "run hotdata", "list workspaces", "list databases", "instant database", "load parquet", "list tables", "show table columns", "execute a query", "database context", "context:DATAMODEL", "ingest", "datasource", "ingest run", "show a run", "schedule an ingest", "import data from", "connect a data source", "connector", "pull data from postgres/mysql/an API/S3 buckets/Iceberg", or general Hotdata CLI usage. This skill bundles three specialized guides under subskills/, loaded on demand: read subskills/search/SKILL.md for full-text/vector search and retrieval indexes, subskills/analytics/SKILL.md for OLAP analytics, query history, stored results, and Chain materializations, and subskills/geospatial/SKILL.md for geospatial/GIS. +description: Use this skill when the user wants to run core hotdata CLI commands — auth, workspaces, instant databases, tables, SQL queries and writes, database context (context:DATAMODEL), jobs, datasources/ingests/runs (pull external data), and skill install. Activate for "run hotdata", "list workspaces", "list databases", "instant database", "load parquet", "list tables", "show table columns", "execute a query", "insert rows", "database context", "context:DATAMODEL", "ingest", "datasource", "ingest run", "show a run", "schedule an ingest", "import data from", "connect a data source", "connector", "pull data from postgres/mysql/an API/S3 buckets/Iceberg", or general Hotdata CLI usage. This skill bundles three specialized guides under subskills/, loaded on demand: read subskills/search/SKILL.md for full-text/vector search and retrieval indexes, subskills/analytics/SKILL.md for OLAP analytics, query history, stored results, and Chain materializations, and subskills/geospatial/SKILL.md for geospatial/GIS. version: 0.44.1 --- @@ -209,7 +209,7 @@ hotdata databases detach ref # when finished (optional) Without `--alias`, the attached database answers to its own catalog alias (`reference.public.regions`). Notes worth knowing: -- **Read-only.** Loads always target your own database's catalog, never an attached one. +- **Read-only.** Loads and SQL writes always target your own database's catalog, never an attached one. - **Not transitive.** You see the database you attached, not the ones *it* has attached. - **The source cannot be deleted while you hold it** — that delete is refused until you detach. An *expiring* source is still removed on its `expires_at`, so check that date before relying on one. diff --git a/skills/hotdata/references/WORKFLOWS.md b/skills/hotdata/references/WORKFLOWS.md index ae0bea5..d7ef1ab 100644 --- a/skills/hotdata/references/WORKFLOWS.md +++ b/skills/hotdata/references/WORKFLOWS.md @@ -84,7 +84,7 @@ A `hotdata query` runs inside **one** instant database; its scope sees that data 4. [ ] Query across databases: `hotdata query "SELECT … FROM .public. JOIN .. ON …"` 5. [ ] (Optional) `hotdata databases detach ` when finished; record required attachments in **context:DATAMODEL → Cross-database joins** -Attaching is read-only (loads still target your own database) and not transitive (you see what you attached, not what it attached). The source cannot be deleted while you hold it, but an *expiring* source still goes on its `expires_at` — check that date before depending on one. +Attaching is read-only (loads and SQL writes still target your own database) and not transitive (you see what you attached, not what it attached). The source cannot be deleted while you hold it, but an *expiring* source still goes on its `expires_at` — check that date before depending on one. **Do not** export a database to parquet just to query it — attach is the live path.