agentleFS
Sign inStart free
tethertotetherto/qvac/.agents/skills/qv-release-train/SKILL.md

qv-release-train

Skill697 starsChanged 18 days agoApache-2.0View on GitHub

Release the packages of a release train (inference, sdk, cli, ai-sdk-provider, the two plugins) together from one branch and one publish run. Use when releasing the SDK chain, writing a version plan, or invoking /qv-release-train.

  • Installs packages

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 1 is distinctive, and 4 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 4

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Follow docs/ci/RELEASE-TRAIN.md.

    line 8
  2. Distinctive:

    Every train package moves.

    line 22
  3. Very specific:

    Before the version pass, set every range between train packages to the current workspace version, then run pnpm install --lockfile-only.

    line 24
  4. Very specific:

    Do not run /qv-sdk-inference-version: the version pass writes the @qvac/inference range.

    line 27
  5. Very specific:

    Never approve the npm or pypi deployment.

    line 32

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Release train

Follow docs/ci/RELEASE-TRAIN.md. It holds the procedure, the configuration and the checks CI runs. This skill adds what an agent does differently.

When to use

  • The user asks to release the SDK chain or the train, or invokes /qv-release-train.

A hotfix of one train package, and any package outside every train (registry-server, rag, logging, error, test-suite), stays on the per-package flow in docs/gitflow.md.

Agent rules

  • Every train package moves. Ask the user for the bump of each when the work does not make it clear.
  • Before the version pass, set every range between train packages to the current workspace version, then run pnpm install --lockfile-only.
  • Show the user the nx release version --dry-run output before applying it.
  • Do not run /qv-sdk-inference-version: the version pass writes the @qvac/inference range. Regenerate packages/sdk-python per qv-sdk-changelog when @qvac/sdk moves.
  • Open both PRs with qv-sdk-pr-create: one release PR, one backmerge, for the whole train.
  • Never approve the npm or pypi deployment; tell the user when each waits.
  • On a failed run, report it. Do not publish a package by hand and do not move or delete a tag.

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.

Check your setup, free