vinta/update-playbooks
(project) Use when refreshing install tasks in playbooks/roles/ against upstream docs — bumping a pinned version, adopting a newly recommended install method, repointing a doc link that moved, or realigning the community.general pin with the brew-installed ansible
npx skills add https://github.com/vinta/hal-9000 --skill update-playbooks
Close the drift between each install task in playbooks/roles/*/tasks/main.yml and the upstream docs it cites, then commit per tool.
Drift takes three forms, and all three are read off the same page — the # comment URL above the task:
A release line is the version prefix a project treats as a stable series: Node 24.x, Python 3.14.x, kubectl 1.35.x. Every bump stays inside the line (24.15.0 -> 24.18.0 is in-line for Node because Node's line is the major). When a newer line exists (Node 26, Python 3.15, kubectl 1.36), keep the pin on its current line and report the newer line in the final summary so the user can decide.
One pin lives outside the roles and answers to a different source of truth — playbooks/collections/requirements.yml, covered in §4.
grep -rn -E '^# https?://|^- name:' playbooks/roles/*/tasks/main.yml
Adjacent line numbers pair each URL with the task it documents. Done when every install task is listed with its role, its doc URL, and any version pinned in its name, command body, or download URL.
Fetch each doc URL once and take all three answers off that one page:
gh api repos/OWNER/REPO/releases --jq '.[].tag_name' for a github.com/OWNER/REPO link, WebFetch otherwisecurl -sIL -o /dev/null -w '%{http_code} %{url_effective}\n' URLDone when every task has today's version, install commands, and final URL confirmed from its page. Anything recalled from training data is stale by definition.
Apply the drift found, matching the surrounding task style:
name:, each command line, and any URL. Done when grepping the file for the old version returns nothing.creates: guard at the binary those commands actually produce.# comment at the URL that resolved.Prefer Homebrew. When the page lists Homebrew among the macOS installs it supports, install with the homebrew module at state: latest rather than the vendor script — state: latest also absorbs whatever separate upgrade task the script needed, as fnm and bun already show. Two things disqualify it, and both send you back to the method the page recommends:
homebrew_tap task above the install; an unaffiliated third party's tap does not.Homebrew always installs the newest release, so it cannot hold a pin. Where a task deliberately pins a version, keep the pinned download and leave the method alone — trading the pin for brew is a decision for the user, not drift to close.
playbooks/collections/requirements.yml pins community.general, the collection supplying the homebrew, homebrew_tap, and homebrew_cask modules the roles install through. Upstream releases do not drive this pin — the brew-installed ansible does. Brew bundles its own copy of the collection, ~/.ansible/collections takes precedence over it, and the pin is what fills ~/.ansible/collections. So a pin that disagrees with brew means ansible-lint validates different module code than ansible-playbook executes, silently.
ansible-galaxy collection list community.general
When they differ, set the pin to brew's version. Never the reverse, and never to the newest release on Galaxy — a pin ahead of brew shadows the bundled collection just as badly as one behind it. Editing the pin is where this skill stops: installing it is make install's job, so note in the final summary that the bump takes effect on the next make install.
Run make lint. Then create one commit per tool with the commit skill, passing what moved, e.g. bump kubectl to v1.35.7 or install foundryup from getfoundry.sh. A collection pin bump is its own commit, separate from any role. Close with a summary: what changed per tool, which tools were already current, and any newer release lines waiting on the user.
Take vinta/update-playbooks from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.