agentleFS
Sign inStart free
prestariusprestarius/jet-skills-stack/skills/changelog-watch/SKILL.md

changelog-watch

Skill1 starsChanged 2 months agoMITView on GitHub

Diff the Claude Code changelog since this stack's verified baseline and report which skills, hooks, or docs are possibly stale. Invoke as /changelog-watch by hand or on a schedule; not model-triggered.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 1 is distinctive, and 1 is 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.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the stack current without re-auditing everything.

    line 10
  2. Very specific:

    Baseline: Read metadata.verified_against from ${CLAUDE_SKILL_DIR}/../../.claude-plugin/plugin.json (or the version given in $ARGUMENTS).

    line 12

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Keep the stack current without re-auditing everything. Output a short "possibly stale" list.

  1. Baseline. Read metadata.verified_against from ${CLAUDE_SKILL_DIR}/../../.claude-plugin/plugin.json (or the version given in $ARGUMENTS). Run claude --version for the installed version.
  2. Fetch the changelog. https://code.claude.com/docs/en/changelog.md. Keep only entries newer than the baseline. Ignore "bug fixes and reliability" lines.
  3. Map entries to components with ${CLAUDE_SKILL_DIR}/references/keyword-map.md. An entry that changes a default or removes a feature outranks one that adds an option: mark the former possibly stale, the latter new material, consider adding.
  4. Report. A table: version → entry (one line) → affected component → verdict. Then the three highest-leverage follow-ups as concrete edits (file + what to change). If nothing maps, say "no drift since <baseline>" and stop.
  5. Never edit files. This skill reports; the user applies changes and bumps metadata.verified_against + verified_date in plugin.json when done.

To run it weekly: /schedule with the prompt /changelog-watch (cloud routine; the plugin must be in enabledPlugins there), or /loop 7d /changelog-watch in a long-lived local session.

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