Release Dbt MCP

dbt-labs/release-dbt-mcp

Release a new version of dbt-mcp to PyPi

324 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

595

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/dbt-labs/dbt-mcp --skill release-dbt-mcp

found in the instruction text

WebFetch fetches pages from the network

as written by the author

Initiate the Create release PR GitHub workflow. Use the auto for the bump input. Don't set the prerelease input.
Wait for this to start and then poll the status of this running workflow.
Once it finishes successfully, approve & squash merge (gh pr merge --squash --admin) the PR that was created. This repo does not allow merge commits. This is an autogenerated PR, so it is okay to bypass CI. This is the only case that bypassing CI is okay.
Merging this PR will kick off the Release dbt-mcp workflow.
Wait for this to start and then poll the status of this running workflow. When the workflow waits for GitHub environment approval, open the page with open <url>
Ask the user to continue once they have approved the GitHub environment.
Once the user continues, continue polling the status of the Release dbt-mcp workflow.
When that workflow has finished successfully. Ensure that the new version of dbt-mcp is on PyPI by checking the JSON API at https://pypi.org/pypi/dbt-mcp/json (the HTML page is JS-rendered and won't work with WebFetch).
Report to the user the status of all GitHub workflows that ran and the status of the release.

Copy the folder

Take dbt-labs/release-dbt-mcp from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.