Skip to main content

Interactive CLI to scaffold AI production projects using uv

Project description

devskills-cli

An interactive CLI to scaffold AI/ML production projects using the uv package manager. No flags — just prompts.

Installation

pip install devskills-cli

Requires Python 3.10+ and uv.


Commands

dev start — Scaffold a new project

Run this inside any directory:

dev start

It will ask you four questions:

  1. Project name — type a name to create a new folder, or . to scaffold in the current directory
  2. Project structure — choose one:
    • AI / ML — includes app/, src/inference/, src/services/, src/database/, models/, tests/, docs/, config/, .github/
    • API — includes app/, src/services/, src/database/, tests/, docs/, config/
    • Minimal — includes app/, tests/, config/
    • None — empty project (just pyproject.toml + .gitignore)
  3. Optional features — space to toggle, enter to confirm:
    • Docker — adds Dockerfile and .dockerignore
    • Claude — adds .claude/ folder for Claude Code integration
  4. Create .venv now? — runs uv venv immediately if yes

After confirming, your project is ready with next steps printed on screen.


dev skills — Manage Claude Code skills

These commands require a .claude/ folder in your current directory (created by dev start when you select the Claude feature).

Search and install a skill

dev skills find <keyword>

Searches skills.sh for matching skills, lets you pick one, and installs it into .claude/skills/.

Example:

dev skills find debugging

Install a specific skill directly

dev skills install <owner/repo>

Install one or more skills by their reference without searching:

dev skills install anthropics/skills
dev skills install anthropics/skills some-other/skill

Browse top skills

dev skills list

Shows the top skills from the skills.sh leaderboard in a table.


Example Workflow

# Install the CLI
pip install devskills-cli

# Scaffold a new AI project
dev start
# > Project name: my-agent
# > Structure: AI / ML
# > Features: [x] Claude  [ ] Docker
# > Create .venv? Yes

cd my-agent
uv sync
cp .env.example .env

# Browse and install Claude Code skills
dev skills list
dev skills find pdf

Requirements

Tool Purpose
Python 3.10+ Runtime
uv Project init and virtualenv
Node.js / npx Only needed for dev skills commands

Links

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

devskills_cli-0.1.2.tar.gz (636.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

devskills_cli-0.1.2-py3-none-any.whl (12.3 kB view details)

Uploaded Python 3

File details

Details for the file devskills_cli-0.1.2.tar.gz.

File metadata

  • Download URL: devskills_cli-0.1.2.tar.gz
  • Upload date:
  • Size: 636.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.8

File hashes

Hashes for devskills_cli-0.1.2.tar.gz
Algorithm Hash digest
SHA256 b32602aa9db06e5d7bea94152a8556d1a4cb5d809408e50e68a4b03cca8944f6
MD5 d6ad1e07184b0051089033675acdbfb8
BLAKE2b-256 30537f2e6413f167b78a1e440f764cbe42fa0dfa4b0688e82f0d22571d84f34c

See more details on using hashes here.

File details

Details for the file devskills_cli-0.1.2-py3-none-any.whl.

File metadata

File hashes

Hashes for devskills_cli-0.1.2-py3-none-any.whl
Algorithm Hash digest
SHA256 d22526ce6e008b666f8776b68108f5aeccb4e7852b4e6acdaa5f25136b7bbca6
MD5 88984c2691916fa4d4e1c8be744f742b
BLAKE2b-256 ca7a505accfefa5c227ad04ac188e78ca82dd6ad203d8bf8471857706819385e

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page