agentleFS
tbhbtbhb/vale-ai-tells/.claude/skills/release/SKILL.md

release

Skill118 starsChanged 37 days agoMITView on GitHub

Cut a vale-ai-tells release end-to-end. Versions the changelog entry, bumps the package pins in the README, commits through the commit skill, tags, and waits for the workflow that publishes the three zips. Use when the operator asks to release, tag, or publish a version of this repository, and when a task ends in one.

193 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use create-agent-adapter, changelog-style and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • MicrosoftSkill

    create-agent-adapter

    Technical guide for creating a new Paperclip agent adapter. Use when building a new adapter package, adding support for a new AI coding tool (e.g. a new CLI agent, API-based agent, or custom process), or when modifying the adapter system. Covers the required interfaces, module structure, registration points, and conventions derived from the existing claude-local and codex-local adapters.

    Also in 5 projects that use this

  • GrinvSkill

    changelog-style

    Turn a commit range into CHANGELOG.md entries following common-changelog style. Use when finishing a PR or cutting a release, to write/fix the [Unreleased] section's entries — moving [Unreleased] under a new dated version heading is a separate, automated step (see the release skill / scripts/sync-version.ts), not this skill's job.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    component-release

    Prepares a verifiable Agent Landing Zone UI release. Use for release branches, VERSION, changelog entries, tags, release notes, and compatibility evidence; never publish without explicit human approval.

    Also in 4 projects that use this

  • GrinvSkill

    docs-consistency-check

    Check README/manifest.json/server.json/CHANGELOG.md/AGENTS.md and docs/*.md for drift against the actual registered tools and source. Use after adding, renaming, or removing a tool, or as part of a live-audit pass.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    documentation-consistency

    Keeps AI Landing Zone contributor, user, and operator documentation aligned with shipped Bicep behavior. Use for parameters, defaults, outputs, topology, deployment flow, operations, or releases.

    Also in 8 projects that use this

  • parcadeiSkill

    agent-context-isolation

    Agent Context Isolation

    Also in 3 projects that use this

  • +3 more from Grinv

The file

We split this skill into the rules it gives an agent

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

  • 0

    Common

    Most of the 183 edited versions we read keep these.

  • 4

    Distinctive

    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:

    Run git status. Working directory must show no changes and stay on main.

    line 14
  2. Distinctive:

    Run git log --oneline -3. Confirm the tip commit matches what you want tagged.

    line 15
  3. Very specific:

    Check version format: must match vMAJOR.MINOR.PATCH

    line 16
  4. Distinctive:

    Read CHANGELOG.md and make these edits:

    line 23
  5. Very specific:

    Add a comparison link at the bottom of the file, before the current top link: [$ARGUMENTS_NO_V]: …

    line 27
  6. Very specific:

    Use grep -n "releases/download" README.md to enumerate every occurrence before editing.

    line 37
  7. Distinctive:

    Keep the body short and trigger-free.

    line 50
  8. Very specific:

    Run gh release view $ARGUMENTS to confirm:

    line 64
  9. Very specific:

    All three package assets appear in the release: ai-tells.zip, ai-tells-commits.zip, ai-tells-experimental.zip

    line 68

“Common” is measured: kept by at least 6 in 10 of the 183 edited versions of this file we could read. “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

Perform a full release for version $ARGUMENTS.

1. Pre-flight

  • Run git status. Working directory must show no changes and stay on main.
  • Run git log --oneline -3. Confirm the tip commit matches what you want tagged.
  • Check version format: must match vMAJOR.MINOR.PATCH
  • Get the previous version tag for use in step 4: git tag --sort=-version:refname | grep "^v" | head -1
<!-- vale Google.Headings = NO -->

2. Update CHANGELOG.md

Read CHANGELOG.md and make these edits:

  1. Replace ## [Unreleased] with ## [$ARGUMENTS_NO_V] - YYYY-MM-DD, using today's date. The heading uses the version without the leading v to match the existing convention and to match the link reference added in step 3 (rumdl will report MD053 Unused link/image reference if the two get out of sync).
  2. Insert a new empty ## [Unreleased] section before it
  3. Add a comparison link at the bottom of the file, before the current top link: [$ARGUMENTS_NO_V]: https://github.com/tbhb/vale-ai-tells/compare/PREV_TAG...$ARGUMENTS where PREV_TAG refers to the tag found in step 1 and ARGUMENTS_NO_V strips the leading v

Writing CHANGELOG entries: Metacommentary uses scope: raw, which bypasses <!-- vale off --> inline suppression. Don't quote literal trigger phrases from that rule (the Let's [verb] patterns) in the CHANGELOG. Paraphrase them instead, as in v1.4.0.

3. Update README.md

<!-- vale Google.Headings = YES -->

The release workflow builds three packages at every tag (ai-tells.zip, ai-tells-commits.zip, ai-tells-experimental.zip). Bump the version in every releases/download/vX.Y.Z/... URL in the README so all package references point at the new tag.

Use grep -n "releases/download" README.md to enumerate every occurrence before editing.

4. Pre-commit checks

Run:

  • mise run devtools:lint-yaml: confirm any new YAML files pass
  • mise run test-clean: confirm false positives file remains clean

5. Commit

Invoke the commit skill, telling it to stage CHANGELOG.md and README.md and nothing else, and to use chore: release $ARGUMENTS as the subject. That skill owns the COMMIT_AGENTMSG draft, the Assisted-by and Signed-off-by trailers the commit-trailers hook requires, and the gates. A hand-written git commit here fails that hook, since a bare subject carries no trailers.

Keep the body short and trigger-free. The commit-msg hook lints the message with all ai-tells rules, and a release commit has little to explain beyond the version. Never name a flagged phrase or token in it.

6. Publish

Run:

mise run release $ARGUMENTS

This creates the annotated tag (using -a -m), pushes the commit and tag, then waits for the GitHub Actions release workflow to complete. It extracts the CHANGELOG entry and updates the release notes automatically.

7. Verify

Run gh release view $ARGUMENTS to confirm:

  • Release notes match the CHANGELOG entry
  • The "Full Changelog" comparison link appears and points to the right range
  • All three package assets appear in the release: ai-tells.zip, ai-tells-commits.zip, ai-tells-experimental.zip

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.