agentleFS
jessepinkman9900jessepinkman9900/claude-second-brain/.claude/skills/release/SKILL.md

release

Skill46 starsChanged 7 months agoMITView on GitHub

Full release flow for claude-second-brain: resolves the next version, audits CI workflows via /update-workflows, syncs docs + ship log via /update-docs, then bumps package.json and opens a single PR containing all three commits via /package-release. Trigger phrases: /release, ship a new version, cut a release, prepare a release.

196 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

  • 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

    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

  • 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

  • rivet-devSkill

    launch-graphics

    Generate agentOS marketing/launch graphics (launch & social heroes, code-snippet cards) from the committed generators in docs-internal/graphics. Use when asked to make, update, or render an agentOS launch image, social image, "agentOS Apps" graphic, or technical code-snippet image.

    Also in 3 projects that use this

  • +3 more from Grinv

The file

We split this skill into the rules it gives an agent

11 rules. 0 are common, 5 are distinctive, and 6 are very specific to this project.

  • 0

    Common

    Most of the 186 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 6

    Very specific

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

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

    Run /update-workflows to catch pack-test.yml drift before CI sees it.

    line 12
  2. Distinctive:

    Commit any workflow edits.

    line 13
  3. Very specific:

    Run /update-docs so the docs site and ship log reflect what's shipping (ship log entry uses the target version).

    line 14
  4. Distinctive:

    Commit the docs changes.

    line 15
  5. Very specific:

    Run /package-release to bump package.json, commit, push, and open the PR.

    line 16
  6. Very specific:

    If you only want one half, run /update-workflows, /update-docs, or /package-release directly — each is usable standalone.

    line 20
  7. Distinctive:

    Read the current version:

    line 31
  8. Distinctive:

    If the audit reports "pack-test is in sync — nothing to update," skip to Step 4.

    line 54
  9. Very specific:

    If /update-workflows modified any files (check git status):

    line 60
  10. Distinctive:

    If nothing changed, skip this step.

    line 67
  11. Very specific:

    Commit the bump (chore: bump version to X.Y.Z)

    line 93

“Common” is measured: kept by at least 6 in 10 of the 186 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

Orchestrates a complete release for claude-second-brain:

  1. Resolve the target version.
  2. Run /update-workflows to catch pack-test.yml drift before CI sees it.
  3. Commit any workflow edits.
  4. Run /update-docs so the docs site and ship log reflect what's shipping (ship log entry uses the target version).
  5. Commit the docs changes.
  6. Run /package-release to bump package.json, commit, push, and open the PR.

The result is one PR containing up to three commits (workflows → docs → version) so CI passes on first push.

If you only want one half, run /update-workflows, /update-docs, or /package-release directly — each is usable standalone.

Preconditions

  • Current branch has commits relative to main.
  • Working tree is otherwise clean (no unrelated staged/unstaged changes — the orchestrator will commit anything staged).

Steps

Step 1 — Resolve target version

Read the current version:

cat package.json | grep '"version"'

Apply the same semver logic /package-release uses:

SignalBump
Breaking CLI / template changes, or commits containing "breaking"major
New skills, new CLI flags, new template sections, or new behaviorminor
Bug fixes, docs, refactors onlypatch

If the user passed an argument (/release patch, /release 0.2.0, etc.) use it directly. Otherwise summarize the diff (git log main..HEAD --oneline + git diff main...HEAD --stat), suggest a bump, and ask the user to confirm. Do not continue until confirmed.

Record the resolved version as vX.Y.Z for the rest of the flow.

Step 2 — Run /update-workflows

Invoke the update-workflows skill. When it asks for approval of its proposal, forward it to the user and wait.

If the audit reports "pack-test is in sync — nothing to update," skip to Step 4.

Let /update-workflows apply its edits.

Step 3 — Commit workflow changes

If /update-workflows modified any files (check git status):

git add .github/workflows/pack-test.yml .claude/skills/pack-test/SKILL.md
git commit -m "chore(ci): sync pack-test with current repo state"

If nothing changed, skip this step.

Step 4 — Run /update-docs

Invoke the update-docs skill. When it asks for approval of its proposal, forward that proposal to the user and wait.

Critical: the ship log entry for this release must use the version resolved in Step 1 (vX.Y.Z) and today's date. If /update-docs proposes a different version, correct it before approving.

Let /update-docs apply its edits.

Step 5 — Commit docs changes

If /update-docs modified any files (check git status):

git add docs/ vocs.config.ts
git commit -m "chore(docs): update ship log and docs for vX.Y.Z"

If nothing changed, skip this step.

Step 6 — Run /package-release

Invoke /package-release <arg> with the version resolved in Step 1 (e.g. /package-release 0.8.0). It will:

  • Bump package.json to X.Y.Z
  • Commit the bump (chore: bump version to X.Y.Z)
  • Push the branch
  • Open a PR — whose commit list will include any workflow commit from Step 3, any docs commit from Step 5, and the version-bump commit

Step 7 — Report

Tell the user which commits landed in the PR — omit any step that was skipped:

Release PR opened: [url]

  • Workflow commit: chore(ci): sync pack-test with current repo state (if applicable)
  • Docs commit: chore(docs): update ship log and docs for vX.Y.Z (if applicable)
  • Version commit: chore: bump version to X.Y.Z

After merge, release-publish.yml tags vX.Y.Z, creates a GitHub Release, and publishes claude-second-brain@X.Y.Z to npm.

What can go wrong

  • User declines workflow or docs proposal — stop; do not proceed to /package-release. The branch is left with whatever has already been committed; retry after resolving the concern.
  • Version mismatch between ship log and package.json — Step 4's correction gate prevents this; if it slips through, the PR reviewer will catch it. Fix by amending the docs commit before merge.
  • Nothing to release — if git log main..HEAD is empty, abort.

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.