Open-source AI job search agent and job finder: scan job boards, score each job 1-5 against your CV before you apply, tailor an ATS-friendly resume and cover letter, get…
Aspm
A Git-based package manager designed for AI-assisted development, similar to npm but supporting skills, agents, commands, hooks, and any AI resource types.
Install
git clone https://github.com/arkylab/aspmInstall command taken from the project's README or registry entry. Always review code before running it.
README excerpt
Read full README on GitHub →aspm - AI Skill Package Manager
A Git-based package manager designed for AI-assisted development, similar to npm but supporting skills, agents, commands, hooks, and any AI resource types.
Features
- 📦 Two Project Modes: Publish project (
aspub.yaml) and consumer project (aspkg.yaml) - 🔗 Distributed Dependency Management: Reference packages directly via Git URL, no central registry needed
- 🏷️ Flexible Version Control: Support for Git tag/branch/commit
- 📥 Simplified Version Rules: Auto-selects the maximum version satisfying all dependencies
- 🔧 Universal Design: Not limited to skills, supports any AI resource type
- 🔌 Multi-Format Support: Install both aspm packages and Claude Code plugin repositories
- 🎯 Three Install Modes: Plain, Claude, and Compatible modes for different AI tool directory structures
Installation
Quick Install
Linux / macOS:
curl -fsSL https://raw.githubusercontent.com/arkylab/aspm/main/scripts/install.sh | sh
Windows (PowerShell):
irm https://raw.githubusercontent.com/arkylab/aspm/main/scripts/install.ps1 | iex
Build from Source
git clone https://github.com/arkylab/aspm.git
cd aspm
cargo build --release
The compiled binary will be at target/release/aspm (or aspm.exe on Windows).
Quick Start
Creating a Consumer Project (If you are a skill consumer)
# Initialize a consumer project
aspm init --consumer
# This creates aspkg.yaml
Configure aspkg.yaml
# Installation target directory
install_to:
- .claude # Install to Claude Code plugin directory
dependencies:
superpowers:
git: "https://github.com/obra/superpowers.git"
branch: "main"
Install Dependencies
aspm install
# After running `aspm install`, all dependencies are ready. If you are using Claude Code, you can now restart Claude code to load the new skills. Sometimes, you may need to restart it twice.
✅ That's all you need to do as a skill consumer
Creating a Publish Project (If you are a skill provider)
Publish projects allow you to share your AI resources with others.
Supported Repository Formats:
| Format | Description | Recommended |
|---|---|---|
| aspm Format | Repository with aspub.yaml at root |
✅ Yes |
| Claude Plugin Format | Repository with skills/, agents/, etc. directories at root |
⚠️ No |
| Single Skill Format | Repository with only SKILL.md at root |
⚠️ No |
aspm recommends the aspm Format because it provides:
- ✅ Explicit control over what gets published
- ✅ Support for transitive dependencies
- ✅ Automatic dependency resolution
# Initialize a publish project
aspm init my-skill-pack
# This creates aspub.yaml (publish configuration).
# aspub.yaml and aspkg.yaml can coexist in the same project - one for publishing your own resources, one for consuming dependencies.
Configure aspub.yaml
name: my-skill-pack
version: 1.0.0
description: "A pack of useful AI resources"
author: "Your Name"
license: MIT
# Install target for this package's own dependencies (optional)
install_to:
- .claude
# Dependencies (optional)
dependencies:
core-utils:
git: "https://github.com/user/utils.git"
tag: "v1.0.0"
Similar plugs
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Editorial diagram design for Claude Code, Codex, GitHub Copilot, Cursor, Factory Droid, and Pi. 44 diagram types. Self-contained HTML + SVG. No shadows. No Mermaid slop.
AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs
Secure, fast, efficient, battle-tested at Alibaba's scale. Hybrid architecture code review tool: deterministic pipelines + LLM Agent, precise line-level comments, built-in…
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection…