Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
Development

skills-manager-cli

Drive the Skills Manager CLI (`skm`) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex, Cursor, Gemini, OpenCode, or any other supported tool; when asked to run skm / Skills Manager CLI; or when setting up Skills Manager without the GUI. Do not use for `npx skills` / skills.sh search (different CLI), for writing SKILL.md content (skill-creator), or for marketplace browse/install (not in skm).

jiweiyeah · Static checks on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add jiweiyeah/Skills-Manager --skill skills-manager-cli

About this skill


name: skills-manager-cli description: > Drive the Skills Manager CLI (skm) to initialize the hub, adopt unmanaged skills, list/enable/disable skills per AI tool, and doctor/fix symlink sync. Use whenever the user or an agent needs to manage skills from a terminal, SSH session, CI job, or headless machine; when a skill is missing in Claude Code, Codex, Cursor, Gemini, OpenCode, or any other supported tool; when asked to run skm / Skills Manager CLI; or when setting up Skills Manager without the GUI. Do not use for npx skills / skills.sh search (different CLI), for writing SKILL.md content (skill-creator), or for marketplace browse/install (not in skm).

Skills Manager CLI (skm)

New here? This skill drives skm, the command-line tool that ships with Skills Manager — a desktop app (macOS / Windows / Linux) that installs one copy of a skill into a central hub and symlinks it into every AI coding tool you use (Claude Code, Codex, Cursor, Gemini, and ~30 more), so you write a skill once and it shows up everywhere.

If you found this skill on ClawHub but don't have Skills Manager yet, that is the missing piece: skm is not a standalone binary you npm install. Get it by installing the app from the official website (then Settings → Command Line Tool, or run skm init), or grab a skm-<target>.tar.gz / .zip from the GitHub Releases page. Source and docs: https://github.com/jiweiyeah/skills-manager.

skm is the terminal front-end of Skills Manager. It reads and writes the same ~/.skills-manager/config.json and the same hub/tool symlinks as the desktop app, so GUI and CLI are interchangeable.

It does not create, edit, search, translate, tag, or marketplace-install skills. Those stay in the GUI (or you write files into the hub yourself, then skm enable).

Preconditions

  1. Resolve the binary. Prefer skm on PATH. If missing, say so and point at install: the Skills Manager app (Settings → Command Line Tool), or a release archive skm-<target>.tar.gz / .zip from GitHub Releases. Do not fall back to npx skills — that is a different, unrelated CLI.
  2. Confirm with skm --version. A stale binary from an older app release should be updated from Settings or a matching release.
  3. Every command except init requires an initialized config. If stderr says so, run skm init --json once — it is idempotent and will not clobber an existing config. skm init and Settings → Install CLI also copy this companion skill into the hub and enable it for every currently active tool, so you usually do not need to install it by hand.

Hub path is fixed at ~/.skills-manager/skills (%USERPROFILE%\.skills-manager\skills on Windows). save() always rewrites skills_dir to that default; there is no supported way to pick another hub from the CLI.

Agent conventions

These exist because skm is designed to be called by agents, not just humans.

  • Prefer --json on init, list, doctor, fix, and adopt (apply). Data is one JSON document on stdout. Errors go to stderr as {"error":"..."} when the command was in JSON mode, otherwise error: .... A command can print a result on stdout and still exit 1 (fix with failed repairs) — parse stdout, then trust the exit code.
  • enable / disable have no --json. Success is a one-line enabled '<id>' for '<tool>' (or disabled). Failure is error: ... on stderr, exit 1.
  • Never wait on a TTY prompt. adopt without --yes and without --json blocks on [y/N]. Pass --yes when applying. --json also skips the prompt (and therefore applies) — still pass --yes so the intent is obvious in the command line.
  • skm adopt --json --dry-run is not a machine-readable preview: if candidates exist it prints nothing. Preview with skm adopt --dry-run (human text), then apply with skm adopt --yes --json.
  • doctor --json exits 0 even when there are issues. Gate on .issues_count, not the exit code.
  • fix without --yes does not repair. JSON then looks like {"applied": false, "issues_found": N, ...}. Apply with skm fix --yes --json.
  • Write commands (init, adopt, enable, disable, fix --yes) take an advisory lock on config.json and fail fast if another skm is mid-write. Retry once. The desktop app does not take this lock.
  • Do not enable a skill for every detected tool unless the user asked. Pick the tool they named, or the host agent (see Which tool).

JSON shapes, exit codes, and the dry-run/apply matrix live in references/json.md. Read that before parsing output or writing a script.

Command map

IntentCommand
First-run / is it initialized?skm init --json
What skills exist, and where are they linked?skm list --json
Same, one tool onlyskm list --tool <id> --json
Turn a hub skill on for a toolskm enable <skill> --for <tool>
Turn it off (remove the link, keep the hub copy)skm disable <skill> --for <tool>
Which tools are installed, any broken links?skm doctor --json
Repair what doctor reportedskm fix --yes --json
Preview leftover real dirs in tool skill foldersskm adopt --dry-run
Move those dirs into the hub and relinkskm adopt --yes --json

<skill> and <tool> accept an exact id, an exact instance_id, or a unique prefix (claude → claude-code). Ambiguous prefixes error and list the matches — do not guess, rerun with a longer token. Exact tool id wins before prefix (trae is Trae, not Trae CN). Full ids and collision notes: references/tools.md.

Workflows

First-run on a machine with no GUI

Read the complete source ↗