Skip to main content

The Skill Manager for Data Science AI Agents

Project description

dhub-cli: The Skill Manager for Data Science AI Agents

Decision Hub is a CLI-first registry for publishing, discovering, and installing Skills — modular packages of code and prompts that AI coding agents (Claude, Cursor, Codex, Gemini, OpenCode) can use.

Why Decision Hub?

  • 🏢 Organization Namespaces: Publish skills to your GitHub organization's namespace (acme-corp/deploy-tool) for your team to use. Zero config—just login and publish.
  • 🛡️ Secure by Default: Every skill runs in an isolated environment (via uv) and passes a "Security Gauntlet" scan before publishing. No more running untrusted code on your bare metal.
  • ⚡ Agent-Agnostic: Install a skill once, and it's instantly available to all your AI agents (Claude, Cursor, Gemini).
  • 🧪 Automated Evals: Skills aren't just hosted; they're graded. Automated sandboxed evaluations ensure skills actually work before you install them.
  • 🧠 Natural Language Search: Don't remember the package name? Just dhub ask "tool to analyze logs" and let the LLM find it for you.
  • 🔓 Open Source & Self-Hostable: Run the public CLI or deploy your own private registry server. Your skills, your infrastructure.

Installation

# Via uv (recommended)
uv tool install dhub-cli

# Via pipx
pipx install dhub-cli

Quick Start

# 1. Authenticate via GitHub
dhub login

# 2. Search for skills using natural language
dhub ask "analyze A/B test results"

# 3. Install a skill for all your agents
dhub install pymc-labs/causalpy

# 4. Scaffold a new skill
dhub init my-new-skill

# 5. Publish it under your namespace
# (Run this inside the skill directory)
dhub publish .

Supported Agents

Skills are installed as symlinks into each agent's skill directory, making them immediately available:

  • Claude: ~/.claude/skills
  • Cursor: ~/.cursor/skills
  • Gemini: ~/.gemini/skills
  • OpenCode: ~/.config/opencode/skills

Documentation

For full documentation on creating skills, the SKILL.md format, and running your own registry server, see the main repository.

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

dhub_cli-0.3.2.tar.gz (34.9 kB view details)

Uploaded Source

Built Distribution

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

dhub_cli-0.3.2-py3-none-any.whl (26.6 kB view details)

Uploaded Python 3

File details

Details for the file dhub_cli-0.3.2.tar.gz.

File metadata

  • Download URL: dhub_cli-0.3.2.tar.gz
  • Upload date:
  • Size: 34.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.12

File hashes

Hashes for dhub_cli-0.3.2.tar.gz
Algorithm Hash digest
SHA256 ed37515c1f586f35507db72fb4b3863361f6c068168c787756924c49ef99540b
MD5 484e461e557ecb514c54b00a9c3ab942
BLAKE2b-256 fee72a038c1265c054c2bce101d57af46a245a6f2328f6a7375ebcce46c5ef88

See more details on using hashes here.

File details

Details for the file dhub_cli-0.3.2-py3-none-any.whl.

File metadata

  • Download URL: dhub_cli-0.3.2-py3-none-any.whl
  • Upload date:
  • Size: 26.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.6.12

File hashes

Hashes for dhub_cli-0.3.2-py3-none-any.whl
Algorithm Hash digest
SHA256 48799acd5b18c5ebf3c24b66e0f334925bb92fd1d17a13148ab55febeff41093
MD5 64368b55cbbdbea998498d98e124493f
BLAKE2b-256 865e7d5129c33842c1e25fa4db38b4c35ed1db46ce5b892546d94f63e87b951e

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