Agent skill

Agr Release

by computerlovetech in computerlovetech/agr

Release process for the agr package. An agent skill from computerlovetech/agr.

MITAuto-check passedDevOps & Cloud

Install Agr Release

skills CLI
$ npx skills add computerlovetech/agr --skill agr-release -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install computerlovetech/agr agr-release --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/computerlovetech/agr.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/agr-release .claude/skills/agr-release && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
agr-release
GitHub stars
451
Token cost
~1.6k tokens
SKILL.md length
767 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
MIT

At a glance

Release process for the agr package. An agent skill from computerlovetech/agr.

  • Works in 8 steps: Figure out what changed → Run quality checks → Check if docs need updating → …
  • The user wants to cut a release
  • SKILL.md covers Before you start, Step 1: Figure out what changed, Step 2: Run quality checks and Step 3: Check if docs need…, plus 6 more sections
  • Calls git, gh and uv

What it does

Agr Release is an agent skill from computerlovetech/agr. Release process for the agr package. Handles version bumping (major/minor/patch/beta), changelog updates, pre-release quality checks, git tagging, and monitoring the GitHub Actions publish pipeline. Use this skill whenever the user wants to cut a release, bump the version, publish to PyPI, or asks about the release process — even if they just say "let's ship it" or "time for a new version".

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in DevOps & Cloud, covering Deployment, Changelog and release notes and CI/CD. It works with Git and GitHub Actions. The repository describes itself as: Educational package-manager project for AI agent skills. Not actively maintained. The licence is MIT.

When your agent uses it

  • The user wants to cut a release
  • Bump the version
  • Publish to PyPI
  • Asks about the release process — even if they just say lets ship it

Example prompts

  • “s ship it”
  • “time for a new version”
  • “/agr-release”

Workflow steps

8 steps, taken from the step headings in SKILL.md.

  1. Figure out what changed
  2. Run quality checks
  3. Check if docs need updating
  4. Bump the version
  5. Update the changelog
  6. Commit, tag, and push
  7. Monitor the pipeline
  8. Verify the release

What it can do on your machine

Read from SKILL.md and the folder at commit f260b65. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git
    • gh
    • uv
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Links to these hosts (documentation or services it may open):

    • pypi.org

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agr Release loads about 1.6k tokens when it runs. Until then it costs about 101 tokens; SKILL.md has 767 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~101
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from computerlovetech/agr at commit f260b65, republished under its MIT licence (© computerlovetech). 767 words, ~1,614 tokens.

Download SKILL.mdSave it as .claude/skills/agr-release/SKILL.md (or your agent's skills folder).
name
agr-release
description
Release process for the agr package. Handles version bumping (major/minor/patch/beta), changelog updates, pre-release quality checks, git tagging, and monitoring the GitHub Actions publish pipeline. Use this skill whenever the user wants to cut a release, bump the version, publish to PyPI, or asks about the release process — even if they just say "let's ship it" or "time for a new version".

agr Release Process

This skill walks through the full release process for the agr package. The release is tag-driven: pushing a vX.Y.Z tag triggers the GitHub Actions pipeline that runs quality checks, builds the package, publishes to PyPI, and creates a GitHub Release.

Your job is to prepare everything so that when the tag is pushed, the pipeline succeeds on the first try.

Before you start

Verify the preconditions. If any fail, stop and tell the user.

  1. Clean working tree — git status should show no uncommitted changes
  2. On the main branch — releases should only come from main
  3. Up to date with remote — git pull to make sure you're not behind

Ask the user what kind of release this is:

  • patch (0.7.10 → 0.7.11) — bug fixes, small changes
  • minor (0.7.10 → 0.8.0) — new features, backwards-compatible
  • major (0.7.10 → 1.0.0) — breaking changes
  • beta (0.7.11b1) — pre-release for testing

If the user already said what type they want, don't ask again.

Step 1: Figure out what changed

Before touching any files, understand what's being released.

bash
# See all commits since the last release tag
git log $(git describe --tags --abbrev=0)..HEAD --oneline

Also check the [Unreleased] section in CHANGELOG.md — it may already have entries. Cross-reference with the git log to make sure nothing is missing. If there are commits that aren't reflected in the changelog, add them.

Group changes into the standard Keep a Changelog categories:

  • Added — new features
  • Changed — changes to existing functionality
  • Fixed — bug fixes
  • Removed — removed features
  • Docs — documentation-only changes

Step 2: Run quality checks

Run all three locally before proceeding. These are the same checks the CI pipeline runs, so catching failures here saves a round-trip.

bash
uv run ruff check .
uv run ruff format --check .
uv run pytest -m "not e2e and not network and not slow"
uv run ty check

If anything fails, fix it before continuing. The release commit should pass CI cleanly.

Step 3: Check if docs need updating

Not every release needs doc changes — use judgement. Docs updates are warranted when:

  • A CLI command was added, removed, or its flags changed
  • A new module or public API was added
  • Behavior that users rely on changed in a way they'd notice

The docs to consider:

  • README.md — the primary entry point, should reflect current capabilities
  • docs/docs/reference.md — CLI command reference
  • docs/docs/index.md — landing page / getting started
  • Other files in docs/docs/ as relevant (sdk.md, configuration.md, etc.)
  • Skills in skills/ — if any exist and are affected by the changes

If nothing user-facing changed (internal refactors, test improvements, dependency bumps), skip this step and move on.

Step 4: Bump the version

The version lives in pyproject.toml (the single source of truth — importlib.metadata picks it up at runtime via agr/__init__.py):

  1. pyproject.toml line 7: version = "X.Y.Z"

Calculate the new version based on the current version and the release type the user chose.

For beta releases, append b1 (or increment the beta number if one already exists):

  • 0.7.10 → 0.7.11b1 (first beta of next patch)
  • 0.7.11b1 → 0.7.11b2 (next beta)
  • 0.7.11b2 → 0.7.11 (promote beta to stable)
Show full SKILL.md (310 more words)Show less

Step 5: Update the changelog

In CHANGELOG.md:

  1. Replace ## [Unreleased] with ## [X.Y.Z] - YYYY-MM-DD (today's date)
  2. Make sure all changes from Step 1 are included under the right categories
  3. Add a new empty ## [Unreleased] section at the top
  4. Review the entries — they should be concise but descriptive enough that a user scanning the changelog understands what changed without reading the code

The changelog format matters because the GitHub Actions pipeline extracts the version's section to use as release notes. Malformed entries = bad release notes.

Step 6: Commit, tag, and push

bash
# Stage the changed files
git add pyproject.toml agr/__init__.py CHANGELOG.md
# Plus any docs files you updated

# Commit
git commit -m "release: vX.Y.Z"

# Tag
git tag vX.Y.Z

# Push commit and tag
git push origin main
git push origin vX.Y.Z

Wait for the user to confirm before pushing. Show them a summary of what will be pushed:

  • The version being released
  • The changelog entry
  • Which files were modified
  • The tag that will be created

Step 7: Monitor the pipeline

After pushing the tag, monitor the GitHub Actions pipeline:

bash
# Watch the workflow run
gh run list --workflow=publish.yml --limit=1
gh run watch $(gh run list --workflow=publish.yml --limit=1 --json databaseId -q '.[0].databaseId')

The pipeline has four stages:

  1. Quality Checks — ruff + pytest
  2. Build Package — uv build + verify
  3. Publish to PyPI — trusted publishing via OIDC
  4. Create GitHub Release — extracts notes from CHANGELOG.md

If any stage fails, read the logs and help the user fix it:

bash
gh run view <run-id> --log-failed

Common failure modes:

  • Quality checks fail → something slipped past local checks, fix and re-tag
  • PyPI publish fails → usually a version conflict (version already exists on PyPI)
  • Release notes extraction fails → changelog format issue

Step 8: Verify the release

Once the pipeline succeeds, confirm:

bash
# Check PyPI (may take a minute to propagate)
pip index versions agr

# Check the GitHub release exists
gh release view vX.Y.Z

Tell the user the release is live and share the links:

If something goes wrong after pushing

If the pipeline fails and you need to retry:

  1. Fix the issue
  2. Delete the tag locally and remotely: git tag -d vX.Y.Z && git push origin :refs/tags/vX.Y.Z
  3. Amend the release commit if needed, or create a new fix commit
  4. Re-tag and re-push

This is destructive — confirm with the user before deleting tags.

© computerlovetech, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/agr-release of computerlovetech/agr.

Open the folder on GitHubat commit f260b65

Compare with similar skills

Agr Release next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agr Release compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Agr Release this skillcomputerlovetech/agr451—~1.6kAutomated safety check: PassMIT
OpenWork Release Processdifferent-ai/openwork24k—~2.3kAutomated safety check: PassCustom licence
Sake CI Releasekattouf/Sake116—~731Automated safety check: PassMIT
ClickUp CLI Release Processkrodak/clickup-cli121—~906Automated safety check: WarnMIT
Vercel CI Integrationjeremylongshore/tons-of-skills-marketplace2.8k—~1.9kAutomated safety check: PassMIT
Adf MasterKilo-Org/kilo-marketplace190—~3.2kAutomated safety check: PassMIT

Similar skills

  • OpenWork Release Process

    different-ai/openwork

    Cuts an OpenWork desktop release through a tag-driven GitHub Actions workflow that makes no commits, with pre-tag checks on open fix PRs and verification afterward.

    24k GitHub stars~2.3k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Sake CI Release

    kattouf/Sake

    A skill your agent uses when working on CI workflows, GitHub Actions, release process, changelog generation (git-cliff), or dependabot configuration.

    116 GitHub stars~731 tokensUpdated 6 mo ago
    DevelopmentAuto-check passed
  • ClickUp CLI Release Process

    krodak/clickup-cli

    Walks through releasing a new version of clickup-cli: pre-release checks, version bump, tagging, CI watch, release notes and the Homebrew update.

    121 GitHub stars~906 tokensUpdated 2 days ago
    DevOps & CloudAuto-check: warnings
  • Vercel CI Integration

    jeremylongshore/tons-of-skills-marketplace

    Configure Vercel CI/CD with GitHub Actions, preview deployments, and automated testing.

    2.8k GitHub stars~1.9k tokensUpdated today
    DevOps & CloudAuto-check passed
  • Adf Master

    Kilo-Org/kilo-marketplace

    Azure Data Factory (ADF) CI/CD, deployment, and pipeline development.

    190 GitHub stars~3.2k tokensUpdated 10 days ago
    DevOps & CloudAuto-check passed
  • CI/CD pipeline design methodology, deployment strategies, GitHub Actions patterns, and branch/release strategies.

    617 GitHub stars~2.8k tokensUpdated 22 days ago
    DevOps & CloudAuto-check passed

More from computerlovetech/agr

  • Skill Debrief

    computerlovetech/agr

    Debrief an AI agent skill (SKILL.md) after using it — capture session feedback or a retrospective and fold it back into the skill.

    451 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed
  • Agr CLI

    computerlovetech/agr

    Install, share, sync, and create AI agent skills across coding tools (Claude Code, Cursor, Codex, OpenCode, Copilot, Pi) using the agr CLI.

    451 GitHub stars~3k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Agr Release

What does Agr Release do?

Release process for the agr package. An agent skill from computerlovetech/agr. Agr Release is an agent skill from computerlovetech/agr. Release process for the agr package.

When should I use Agr Release?

Agr Release fits situations like: the user wants to cut a release; bump the version; publish to PyPI; asks about the release process — even if they just say lets ship it.

How do I install Agr Release in Claude Code?

Run `npx skills add computerlovetech/agr --skill agr-release -a claude-code`. Or copy the skill folder (skills/agr-release in computerlovetech/agr) into .claude/skills/agr-release in your project. Claude Code loads it when a task matches its description.

How do I install Agr Release in Codex?

Run `npx skills add computerlovetech/agr --skill agr-release -a codex`. Or copy the skill folder (skills/agr-release in computerlovetech/agr) into .agents/skills/agr-release in your project. Codex loads it when a task matches its description.

Can I use Agr Release in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add computerlovetech/agr --skill agr-release -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agr-release, .gemini/skills/agr-release, .github/skills/agr-release and .opencode/skills/agr-release in your project.

What does Agr Release need to run?

Going by SKILL.md and its folder, Agr Release needs the command-line tools its instructions call (git, gh, uv and pip).

Does Agr Release access the network?

SKILL.md names 1 domain. As links in the text: pypi.org. This is read from the text; nothing was executed.

Is Agr Release safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Agr Release use?

Agr Release is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agr Release use?

About 1.6k tokens (SKILL.md is roughly 6.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agr Release?

Skills that share tags, products or a category with Agr Release: OpenWork Release Process (different-ai/openwork, 24k stars), Sake CI Release (kattouf/Sake, 116 stars), ClickUp CLI Release Process (krodak/clickup-cli, 121 stars) and Vercel CI Integration (jeremylongshore/tons-of-skills-marketplace, 2.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agr Release?

computerlovetech (a GitHub organization) maintains it in computerlovetech/agr, which has 451 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on August 12, 2026.

Source: computerlovetech/agr on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.