release-dbt-mcp

Release a new version of dbt-mcp to PyPi

安装方式

默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。

用 Codex 或 Claude 帮你安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。

直接命令不会经过审查 Prompt；运行前请先检查来源。

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

命令会保持在同一行。复制前请横向滚动并检查完整内容。

想先保存到本地？可下载 SkillsMP 当前能够提供的文件。

决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。

SKILL.md

来源说明 · 只读预览

name	release-dbt-mcp
description	Release a new version of dbt-mcp to PyPi
disable-model-invocation	true

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.