agentleFS
arimxyerarimxyer/toolchest/.claude/skills/check-marketplace-sync/SKILL.md

check-marketplace-sync

Skill1 starsChanged 5 months agoApache-2.0View on GitHub

Verify that plugins/, .claude-plugin/marketplace.json, and the root README plugin table are all in sync. Reports any plugin that appears in one or two of those places but not all three. Use when the user asks to check, audit, or verify the marketplace state.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Verify the three sources of truth for the plugin list agree.

    line 10
  2. Distinctive:

    Use a small table:

    line 46
  3. Distinctive:

    If anything is out of sync, ask the user whether to fix it.

    line 56
  4. Distinctive:

    Don't compare description strings across the three sources for drift — only check presence.

    line 60
  5. Distinctive:

    Don't check per-plugin README.md skill tables — that's a separate concern.

    line 61
  6. Distinctive:

    Don't modify any files unless the user explicitly asks for a fix.

    line 62

≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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

check-marketplace-sync

Verify the three sources of truth for the plugin list agree.

The three sources

  1. Filesystem — directories under plugins/ that contain .claude-plugin/plugin.json
  2. Marketplace manifest — entries in .claude-plugin/marketplace.json's plugins[] array
  3. Public README table — rows under "## Available Plugins" in the root README.md

A plugin is in sync only if it appears in all three.

Procedure

  1. List plugin directories: every plugins/<name>/ that contains a .claude-plugin/plugin.json.

    for d in plugins/*/; do
      name=$(basename "$d")
      [ -f "$d/.claude-plugin/plugin.json" ] && echo "$name"
    done | sort
  2. List plugin names from the marketplace manifest:

    jq -r '.plugins[].name' .claude-plugin/marketplace.json | sort
  3. List plugin names from the README table — read README.md and extract the first column of every row in the "Available Plugins" table whose name is not ↳ (the continuation marker for additional skills of the same plugin). Names appear wrapped in backticks: `pixijs`, `animation-library`, etc.
  4. Compare the three sets. Report:

    • Missing from marketplace.json — directory exists, no manifest entry
    • Missing from README table — directory exists, no README row
    • Orphan in marketplace.json — manifest entry with no directory
    • Orphan in README table — README row with no directory
    • In sync — appears in all three

    Use a small table:

    plugin              dir  manifest  readme
    pixijs              ✓    ✓         ✓
    animation-library   ✓    ✓         ✓
  5. Also verify each plugins/<name>/.claude-plugin/plugin.json parses as JSON (jq -e . <file> > /dev/null). Report any parse failures.
  6. If anything is out of sync, ask the user whether to fix it. Do not silently patch.

Out of scope

  • Don't compare description strings across the three sources for drift — only check presence.
  • Don't check per-plugin README.md skill tables — that's a separate concern.
  • Don't modify any files unless the user explicitly asks for a fix.

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.