/install-duckdb
Install or update DuckDB extensions. Each argument is either a plain extension name (installs from core) or name@repo (e.g. magic@community). Pass --update to update extensions instead of installing.
$ npx -y skills add duckdb/duckdb-skills --skill install-duckdb --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/install-duckdb
Context preview
The summary Claude sees to decide when to auto-load this skill.
Install or update DuckDB extensions. Each argument is either a plain extension name (installs from core) or name@repo (e.g. magic@community). Pass --update to update extensions instead of installing.
SKILL.md
install-duckdb.SKILL.mdname: install-duckdb
description: >
Install or update DuckDB extensions. Each argument is either a plain
extension name (installs from core) or name@repo (e.g. magic@community).
Pass --update to update extensions instead of installing.
argument-hint: "[--update] [ext1 ext2@repo ext3 ...]"
allowed-tools: Bash
Arguments: `$@`
Each extension argument has the form `name` or `name@repo`.
- `name` → `INSTALL name;`
- `name@repo` → `INSTALL name FROM repo;`
Step 1 — Locate DuckDB
DUCKDB=$(command -v duckdb)
If not found, tell the user:
> **DuckDB is not installed.** Install it first with one of: > - macOS: `brew install duckdb` > - Linux: `curl -fsSL https://install.duckdb.org | sh` > - Windows: `winget install DuckDB.cli` > > Then re-run `/duckdb-skills:install-duckdb`.
Stop if DuckDB is not found.
Step 2 — Check for --update flag
If `--update` is present in `$@`, remove it from the argument list and set mode to **update**. Otherwise mode is **install**.
Step 3 — Build and run statements
**Install mode:**
Parse each remaining argument:
- If it contains `@`, split on `@` → `INSTALL <name> FROM <repo>;`
- Otherwise → `INSTALL <name>;`
Run all in a single DuckDB call:
"$DUCKDB" :memory: -c "INSTALL <ext1>; INSTALL <ext2> FROM <repo2>; ..."
**Update mode:**
First, check if the DuckDB CLI itself is up to date:
CURRENT=$(duckdb --version | grep -oE '[0-9]+\.[0-9]+\.[0-9]+')
LATEST=$(curl -fsSL https://duckdb.org/data/latest_stable_version.txt)
- If `CURRENT` == `LATEST` → report DuckDB CLI is up to date.
- If `CURRENT` != `LATEST` → ask the user:
> **DuckDB CLI is outdated** (installed: `CURRENT`, latest: `LATEST`). Upgrade now?
If the user agrees, detect the platform and run the appropriate upgrade command:
- macOS (`brew` available): `brew upgrade duckdb`
- Linux: `curl -fsSL https://install.duckdb.org | sh`
- Windows: `winget upgrade DuckDB.cli`
Then update extensions:
- No extension names → update all: `UPDATE EXTENSIONS;`
- With extension names → update in a single call (ignore `@repo`):
`UPDATE EXTENSIONS (<name1>, <name2>, ...);`
"$DUCKDB" :memory: -c "UPDATE EXTENSIONS;"
# or
"$DUCKDB" :memory: -c "UPDATE EXTENSIONS (<ext1>, <ext2>, ...);"
Report success or failure after the call completes.
Read more
name: install-duckdb description: > Install or update DuckDB extensions. Each argument is either a plain extension name (installs from core) or name@repo (e.g. magic@community). Pass --update to update extensions instead of installing. argument-hint: "[--update] [ext1 ext2@repo ext3 ...]" allowed-tools: Bash
Arguments: `$@`
Each extension argument has the form `name` or `name@repo`.
- `name` → `INSTALL name;`
- `name@repo` → `INSTALL name FROM repo;`
Step 1 — Locate DuckDB
DUCKDB=$(command -v duckdb)
If not found, tell the user:
> **DuckDB is not installed.** Install it first with one of: > - macOS: `brew install duckdb` > - Linux: `curl -fsSL https://install.duckdb.org | sh` > - Windows: `winget install DuckDB.cli` > > Then re-run `/duckdb-skills:install-duckdb`.
Stop if DuckDB is not found.
Step 2 — Check for --update flag
If `--update` is present in `$@`, remove it from the argument list and set mode to **update**. Otherwise mode is **install**.
Step 3 — Build and run statements
**Install mode:**
Parse each remaining argument:
- If it contains `@`, split on `@` → `INSTALL <name> FROM <repo>;`
- Otherwise → `INSTALL <name>;`
Run all in a single DuckDB call:
"$DUCKDB" :memory: -c "INSTALL <ext1>; INSTALL <ext2> FROM <repo2>; ..."
**Update mode:**
First, check if the DuckDB CLI itself is up to date:
CURRENT=$(duckdb --version | grep -oE '[0-9]+\.[0-9]+\.[0-9]+') LATEST=$(curl -fsSL https://duckdb.org/data/latest_stable_version.txt)
- If `CURRENT` == `LATEST` → report DuckDB CLI is up to date.
- If `CURRENT` != `LATEST` → ask the user:
> **DuckDB CLI is outdated** (installed: `CURRENT`, latest: `LATEST`). Upgrade now?
If the user agrees, detect the platform and run the appropriate upgrade command:
- macOS (`brew` available): `brew upgrade duckdb`
- Linux: `curl -fsSL https://install.duckdb.org | sh`
- Windows: `winget upgrade DuckDB.cli`
Then update extensions:
- No extension names → update all: `UPDATE EXTENSIONS;`
- With extension names → update in a single call (ignore `@repo`):
`UPDATE EXTENSIONS (<name1>, <name2>, ...);`
"$DUCKDB" :memory: -c "UPDATE EXTENSIONS;" # or "$DUCKDB" :memory: -c "UPDATE EXTENSIONS (<ext1>, <ext2>, ...);"
Report success or failure after the call completes.
A Claude Code plugin that adds DuckDB-powered skills for data exploration and session memory.
Repo: duckdb/duckdb-skills
Other skills on duckdb-skills.
- /attach-db
Attach a DuckDB database file for use with /duckdb-skills:query. Explores the schema (tables, columns, row counts) and writes a SQL state file so subsequent queries can restore this session automatically via duckdb -init.
Open skill - /convert-file
Convert any data file to another format: CSV, Parquet, JSON, Excel, GeoJSON, and more. Use when the user says "convert to parquet", "save as xlsx", "export as JSON", "make this a CSV", "turn into parquet", or any variation of format-to-format conversion for data files. Also
Open skill - /duckdb-docs
Search DuckDB and DuckLake documentation and blog posts. Returns relevant doc chunks for a question or keyword using full-text search against a locally cached index.
Open skill - /query
Run SQL queries against the attached DuckDB database or ad-hoc against files. Accepts raw SQL or natural language questions. Uses DuckDB Friendly SQL idioms.
Open skill - /read-file
Read any data file (CSV, JSON, Parquet, Avro, Excel, spatial, SQLite) or remote URL (S3, HTTPS). Use when user references a data file, asks "what's in this file", or wants to preview/profile a dataset. Not for source code.
Open skill - /read-memories
Search past Claude Code session logs to recall prior decisions, patterns, or unresolved work. Use when user says "do you remember", "what did we do", references past conversations, or you need context from prior sessions.
Open skill

