Back to packageRELEASE DETAILS

0.2.0

PyPI

add-skills

A tool for managing Claude Code skills

Published3 Jul 2026

Direct dependencies9

Transitive dependenciesNot calculated

README

Version 0.2.0 documentation

add-skills

A Python-based CLI for managing AI agent Skills. Install Skills from local paths or GitHub/GitLab repositories.

Installation

No installation required (recommended)

uvx add-skills ludo-technologies/python-best-practices

Or install globally

uv tool install add-skills
pipx install add-skills

Usage

# Add Skills from GitHub (short form)
uvx add-skills ludo-technologies/python-best-practices

# Add Skills from a local directory
uvx add-skills ./my-skills

# Add Skills from full GitHub URL
uvx add-skills https://github.com/owner/repo

# List available Skills without installing
uvx add-skills ludo-technologies/python-best-practices --list

# Install globally (default: local to project)
uvx add-skills ludo-technologies/python-best-practices --global

# Install for a specific agent
uvx add-skills ludo-technologies/python-best-practices --global --agent cursor

# Skip confirmation prompt
uvx add-skills ludo-technologies/python-best-practices --yes

# Install a specific Skill by name
uvx add-skills ludo-technologies/python-best-practices --skill coding-standards

Options

Option	Short	Description
`--global`	`-g`	Install globally instead of locally to project
`--agent`	`-a`	Target agent (default: `claude-code`)
`--skill`	`-s`	Install specific Skill by name
`--list`	`-l`	List available Skills without installing
`--yes`	`-y`	Skip confirmation prompt

Supported Agents

amp, antigravity, claude-code, clawdbot, cline, codebuddy, codex, command-code, continue, crush, cursor, droid, gemini-cli, github-copilot, goose, kilo, kiro-cli, mcpjam, mux, neovate, opencode, openhands, pi, qoder, qwen-code, roo, trae, windsurf, zencoder

Creating Skills

Create a SKILL.md file in your Skill directory:

---
name: my-skill
description: A brief description of what this skill does
---

# My Skill

Instructions for the AI agent...

How It Works

Parses the source (local path, owner/repo, or full URL)
For remote sources, performs a shallow clone
Discovers all SKILL.md files in the source
Copies Skill files to the target agent's Skills directory

Installation paths (example for claude-code):

Local: .claude/skills/<skill-name>
Global: ~/.claude/skills/<skill-name>

License

MIT

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Declared dependencies 9

Native requirements

9 direct targetsNot calculated transitive count

Package / target	Requirement	Relationship
typer Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`typer>=0.9.0`	runtime
rich Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`rich>=10.0.0`	runtime
python-frontmatter Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`python-frontmatter>=1.0.0`	runtime
GitPython Environment { "extras": "", "marker": null, "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`GitPython>=3.1.0`	runtime
pytest Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pytest>=6.0; extra == "dev"`	runtime
build Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`build>=0.7.0; extra == "dev"`	runtime
twine Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`twine>=3.0.0; extra == "dev"`	runtime
ruff Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`ruff>=0.8.0; extra == "dev"`	runtime
pyright Environment { "extras": "", "marker": "extra == \"dev\"", "requires_python": ">=3.10", "evaluation": "NOT_EVALUATED" }	`pyright>=1.1.0; extra == "dev"`	runtime