skills-state
Skill7 starsChanged 5 days agoMITView on GitHub
Inventory にある skill 個別の Projection 状態(active / archive / off)を CLI で切り替える。deck 全体ではなく1つだけ動かしたい時に使う。トリガー: 「スキルを有効化」「〜をactiveに」「〜をarchiveに」「スキルをオフに」「activate/archive skill」
In this repository6 other files it gives its agents.
- check-vendor-updatesSkill
- skill-deck-managerSkill
- skills-addSkill
- skills-checkSkill
- skills-restoreSkill
- vendor-forkSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 1 is distinctive, and 3 are 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Use this skill when the user wants to move one or a few managed skills between Active, Archive, and Off without touching the rest of the …
- Very specific: line 16
Verify: MY_SKILLS_CATALOG_DIR is set and points at an existing skills.lock.json.
- Very specific: line 24
Verify: .active, .archive, and .tracked report the counts and .untracked lists active skills outside the Inventory.
- Very specific: line 36
Verify: rerun status --json.
≈ “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.
Files
Skills State
Use this skill when the user wants to move one or a few managed skills between Active, Archive, and Off without touching the rest of the Projection.
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: Check the current state
"$ENGINE_ROOT/skill-loom" --catalog-dir "$MY_SKILLS_CATALOG_DIR" status --json | jq '{tracked, active, archive, untracked}'Verify: .active, .archive, and .tracked report the counts and .untracked lists active skills outside the Inventory. Unknown skill names are rejected in Step 3 (exit 2, before any write).
Step 3: Set the state
"$ENGINE_ROOT/skill-loom" --catalog-dir "$MY_SKILLS_CATALOG_DIR" skill <active|archive|off> <names...> -yactive: restores from Archive, or installs managed skills that are Off (External via the skills CLI, Custom from the Catalog repo).archive: moves the files to~/.agents/skills-archive, removes the agent-facing symlinks, and drops the skill from the skills CLI lock so a laterskills updatewon't resurrect it.off: trashes the Projection copies and drops the skill from the skills CLI lock.
Verify: rerun status --json; the counts moved. For active, ~/.claude/skills/<name> resolves into the Active directory.
Safety
- Unknown names abort with exit 2 before any write. Register the skill first (skills-add,
draft promote) and retry. offis trash-based and reversible viaskill active, but re-installing an External Skill hits the network again.-yskips the confirmation prompt; keep it for agent-driven runs, drop it for interactive ones.- The previous Active set is saved to the
_lastpreset before each change;preset restoreundoes it.
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
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.

