reorx

reorx / skm

Public

A better skills manager

46
5
100% credibility
Found Mar 17, 2026 at 46 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
Python
AI Summary

SKM is a command-line tool for discovering, installing, updating, and managing skill directories for AI agents like Claude and Codex by linking them from GitHub repositories or local paths.

How It Works

1
🔍 Discover SKM

You learn about a simple helper that lets you easily add special toolkits to your AI assistants from shared collections or your own folders.

2
📥 Add SKM to Your Computer

With one easy line, you bring SKM onto your machine so it's ready to help.

3
📝 Pick Your Skill Collections

You make a short list of skill packs from the web or your personal folders that you want your AIs to have.

4
🚀 Bring Skills Home

You say go, and SKM grabs the collections, finds the skills inside, and neatly places them where each AI looks for them.

5
📋 Check Your Setup

You peek at the list to see all your skills and exactly where they're ready for your AIs.

6
🔄 Stay Fresh

When updates come out, you refresh to give your AIs the newest versions of their skills.

🎉 AIs Superpowered!

Now your AI helpers have all these amazing skills loaded up, making them way smarter and more capable right away.

Sign up to see the full architecture

5 more

Sign Up Free

Star Growth

See how this repo grew from 46 to 46 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is skm?

skm is a Python CLI tool for managing skills for AI coding agents like Claude, Codex, and OpenClaw. It clones GitHub repos or links local directories, auto-detects skills via SKILL.md files, and symlinks them into agent skill folders such as ~/.claude/skills/ – all from a simple YAML config at ~/.config/skm/skills.yaml. Run `skm install` to sync everything idempotently, adding new skills, updating links, and pruning stale ones.

Why is it gaining traction?

Unlike manual cloning or per-project setups, skm offers declarative config with direct installs like `skm i https://github.com/vercel-labs/agent-skills`, interactive TUI selection of skills and agents, and commands like `check-updates`, `update`, and `view` for previews. It auto-updates your config on direct installs and handles local paths or specific skills, delivering a better GitHub Copilot experience via curated repos without touching unmanaged files.

Who should use this?

Devs using AI agents for code tasks who pull skills from GitHub repos to boost productivity on React best practices or UI guidelines. Teams curating better skills for resume-worthy agent setups, or individuals experimenting with repos like blader/humanizer across Claude and Codex.

Verdict

Try skm if you're deep into AI agent workflows – its polished CLI, clear docs, and tests make it usable now despite 46 stars and 1.0% credibility score signaling early maturity. Pair it with uv for quick install, but watch for agent path overrides in production.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.