OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Agent Frameworks

AI Agent Skills

AI Agent Skills is a JavaScript CLI and terminal user interface for installing reusable skills into AI coding agents and managing curated skill libraries. It includes a bundled collection and supports creating workspaces with categorized entries, provenance, and curator notes. The project states that it works with Agent Skills-compatible agents.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Agent Skills — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when you want a CLI-based way to select skills for a compatible coding agent or maintain a categorized personal or team catalog instead of managing an unstructured set of skill folders.

Who it is for

  • Developers who want to browse and install reusable skills for a compatible coding agent.
  • Individuals curating a focused personal library of agent skills.
  • Teams organizing skills into a managed library that can be shared through a repository.

Documented uses

  • List and browse skill collections and shelves.
  • Install a bundled skill or skills from an upstream repository.
  • Create a managed library, categorize entries, and record why each skill is included.
  • Import an existing skills directory and generate workspace documentation.
Before you choose

Requirements & limits

The repository is public source code under the MIT license. The documented workflows use npx commands.

  • The project distinguishes local bundled copies from upstream catalog entries, which are fetched from their source repositories when requested.
  • Default install targets are ~/.claude/skills/ globally and .agents/skills/ for a project; a legacy agent-specific target can be selected with --agent.
  • Workspace commands support categorization, curator rationale, importing, syncing, and documentation generation.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Create and document a managed skills library

Set up a workspace, add a bundled skill with its shelf and rationale, install it, and build library documentation.

Before you start

  • Node.js/npm access to run the documented npx commands
  • An Agent Skills-compatible agent for using the installed skill

Steps

  1. Run the command below and enter the workspace with cd my-library.

    Documented command
    npx ai-agent-skills init-library my-library

  2. Add a bundled skill with the command below.

    Documented command
    npx ai-agent-skills add frontend-design --area frontend --branch Implementation --why "I want this on my shelf."

  3. Install it to the project target with the command below.

    Documented command
    npx ai-agent-skills install frontend-design -p

  4. Generate the workspace documentation with the command below.

    Documented command
    npx ai-agent-skills build-docs

Expected outcome

A managed workspace with a categorized skill, an installation in the project-level target, and generated library documentation.

Guide limitations

  • The documented project target is .agents/skills/; the global default is ~/.claude/skills/.
  • Agent use requires an Agent Skills-compatible agent.
Documentation 1 ↗
Source-based practical guide

Import and browse an existing skills repository

Initialize a flat repository of skills as a managed library and browse its imported contents.

Before you start

  • An existing local repository or directory of skills
  • Node.js/npm access to run the documented npx commands

Steps

  1. Change to the existing skills directory.

  2. Run the command below.

    Documented command
    npx ai-agent-skills init-library . --areas "mobile,workflow,agent-engineering" --import --auto-classify

  3. Run the command below.

    Documented command
    npx ai-agent-skills browse

Expected outcome

The existing directory is initialized as a library with the specified areas and imported skills available to browse.

Guide limitations

  • Invalid private-only names are skipped and reported.
  • Low-confidence imports fall back to the workflow area with a needs-curation label.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
AI Agent SkillsList and browse skill collections and shelves.CLIThe repository is public source code under the MIT license. The documented workflows use npx commands.
DextoDefine agents in YAML with a model, tools, storage and permissions.CLI
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
11 October 2026
Original website title
MoizIbnYousaf/ai-agent-skills · Official homepage title · retained in its source language
How we review sourcesSuggest a correction