agentleFS
Kaalia0912Kaalia0912/dsh-data-analysis-mode/skills/install-duckdb/SKILL.md

install-duckdb

Skill2 starsChanged 3 months agoMITView on GitHub

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.

  • Pipes a download into a shell
  • Installs packages

3 other projects use a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

9 rules. About 0 are common, 4 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If not found, tell the user:

    line 23
  2. Distinctive:

    Stop if DuckDB is not found.

    line 32
  3. Very specific:

    If --update is present in $@, remove it from the argument list and set mode to update.

    line 36
  4. Very specific:

    If it contains @, split on @ → INSTALL <name> FROM <repo>.

    line 44
  5. Distinctive:

    Run all in a single DuckDB call:

    line 47
  6. Very specific:

    If CURRENT == LATEST → report DuckDB CLI is up to date.

    line 62
  7. Very specific:

    If CURRENT != LATEST → ask the user:

    line 63
  8. Distinctive:

    If the user agrees, detect the platform and run the appropriate upgrade command:

    line 66
  9. Very specific:

    No extension names → update all: UPDATE EXTENSIONS.

    line 73

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.