agentleFS
YunosukeYoshinoYunosukeYoshino/skill-loom/.agents/skills/skill-deck-manager/SKILL.md

skill-deck-manager

Skill7 starsChanged 5 days agoMITView on GitHub

Catalog の Inventory から active Projection を HTML チェックリストで整理する。Projection を削除せず切り替えたい時に使う。トリガー: 「デッキ整理」「projection 切替」「active スキル整理」「スキルを減らす」

The file

We split this skill into the rules it gives an agent

10 rules. About 0 are common, 5 are distinctive, and 5 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 5

    Very specific

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

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

    Use this skill when the user wants to inspect, reduce, or switch the active global skills loaded from ~/.agents/skills.

    line 8
  2. Very specific:

    Verify: MY_SKILLS_CATALOG_DIR is set and points at an existing skills.lock.json.

    line 16
  3. Very specific:

    Verify: status --json reports the counts (.active, .archive) and list --json one deck object per line, both without errors.

    line 25
  4. Distinctive:

    Verify: the checklist lists the active skills of the selected Catalog.

    line 35
  5. Distinctive:

    Keep checked the Skills that should remain active, then submit the form.

    line 39
  6. Distinctive:

    Verify: the refreshed counts match the number of kept skills.

    line 41
  7. Distinctive:

    Do not use destructive delete commands for skill cleanup.

    line 47
  8. Very specific:

    Treat ~/.agents/skills as the active projection and ~/.agents/skills-archive as reversible storage.

    line 48
  9. Distinctive:

    If a skill is unmanaged or untracked, call that out before applying changes.

    line 49
  10. Very specific:

    Prefer core first, then switch to frontend, backend, workflow, design, writing, or research only when needed.

    line 50

≈ “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

Skill Deck Manager

Use this skill when the user wants to inspect, reduce, or switch the active global skills loaded from ~/.agents/skills.

Workflow

Step 1: Select the Catalog and Engine

Set MY_SKILLS_CATALOG_DIR to the Catalog that owns skills.lock.json, and resolve the Engine launcher as ENGINE_ROOT/skill-loom.

Verify: MY_SKILLS_CATALOG_DIR is set and points at an existing skills.lock.json.

Step 2: Preview the selected Catalog

"$ENGINE_ROOT/skill-loom" --catalog-dir "$MY_SKILLS_CATALOG_DIR" status --json
"$ENGINE_ROOT/skill-loom" --catalog-dir "$MY_SKILLS_CATALOG_DIR" list --json

Verify: status --json reports the counts (.active, .archive) and list --json one deck object per line, both without errors.

Step 3: Start the HTML checklist

"$ENGINE_ROOT/skill-loom" --catalog-dir "$MY_SKILLS_CATALOG_DIR" ui

Open the printed localhost URL.

Verify: the checklist lists the active skills of the selected Catalog.

Step 4: Switch the Projection

Keep checked the Skills that should remain active, then submit the form.

Verify: the refreshed counts match the number of kept skills.

The UI moves unchecked active skills to ~/.agents/skills-archive and restores checked archived skills back to ~/.agents/skills. It does not delete skills.

Safety

  • Do not use destructive delete commands for skill cleanup.
  • Treat ~/.agents/skills as the active projection and ~/.agents/skills-archive as reversible storage.
  • If a skill is unmanaged or untracked, call that out before applying changes.
  • Prefer core first, then switch to frontend, backend, workflow, design, writing, or research only when needed.

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.