agentleFS
Sn4kyGitSn4kyGit/qa-agent-blueprint/.claude/skills/whats-new/SKILL.md

whats-new

Skill2 starsChanged 8 days agoApache-2.0View on GitHub

Show what changed in the blueprint since a project was onboarded or re-boarded — renders the relevant CHANGELOG sections in the user's language, noting which changes call for /re-board. Use for "/whats-new", "was ist neu", "changelog", or right after a plugin update. Read-only; the apply step is /re-board.

9 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 0 are distinctive, and 3 are very specific to this project.

  • 0

    Common

    Most of the 7 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 3

    Very specific

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

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

    Read the installed blueprint version from .claude-plugin/plugin.json (via the support link.

    line 15
  2. Very specific:

    Read the Blueprint version stamps of all onboarded projects (projects/*/PROJECT.md, skipping _template and EXAMPLE).

    line 18
  3. Very specific:

    Start a re-board, edit a project file, or "helpfully" apply a change.

    line 52

“Common” is measured: kept by at least 6 in 10 of the 7 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

/whats-new — what changed since this project was onboarded

Orientation only, like /qa-help: render the delta, then stop. Do not start any work from it — if a change calls for action, the action is /re-board and the user runs it next. Answer in the user's language.

Steps

  1. Read the installed blueprint version from .claude-plugin/plugin.json (via the support link; plugin mode: $CLAUDE_PLUGIN_ROOT/.claude-plugin/plugin.json).
  2. Read the Blueprint version stamps of all onboarded projects (projects/*/PROJECT.md, skipping _template and EXAMPLE). No stamp = "pre-0.5.0" (the field did not exist yet).
  3. In the blueprint's CHANGELOG.md, take every version section NEWER than the oldest stamp across the projects. Sections are ## [X.Y.Z] — date; stop at the first section that is not newer. Include [Unreleased] only when the running version is a dev checkout (installed version matches no section — practically: the blueprint repo itself).
  4. Render, in the user's language:

    • one line per project: <KEY>: onboarded at <stamp or "pre-0.5.0">, blueprint is at <installed>
    • the changelog entries between, grouped by version, compressed to what each change means for the user (one line each — the full CHANGELOG stays the reference, do not paste it verbatim)
    • a closing line per change that touches project files: "betrifft projects/<KEY>/… → /re-board <KEY> brings it up to date" — the version-stamp field itself, Secrets source, flow maps, and similar schema changes always qualify; pure plugin-internal changes (hooks, evals, docs) get "no project action needed".

    Example shape (German user, one project):

    SHOP: onboarded at 0.11.0, blueprint ist 0.12.0
    
    **0.12.0 — wer am Steuer sitzt**
    - Ausführungsmodus pro Projekt wählbar (mcp-only / hybrid / cli-first) —
      betrifft projects/SHOP/PROJECT.md → /re-board SHOP bringt es auf Stand.
    - Neue Pipeline-Doku + /recon-Skill — kein Projekt-Eingriff nötig.
  5. Nothing to show (all stamps current): say so in one line and stop.

What this skill never does

Start a re-board, edit a project file, or "helpfully" apply a change. Update the stamps itself (that is /re-board's job — a stamp that moves without the project being upgraded makes this skill lie).

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.