Skip to main content

The AI Skill Manager for Data Science Agents

Project description

dhub-cli: The AI Skill Manager for Data Science 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-0.3.3.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-0.3.3-py3-none-any.whl (26.6 kB view details)

Uploaded Python 3

File details

Details for the file dhub_cli-0.3.3.tar.gz.

File metadata

  • Download URL: dhub_cli-0.3.3.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-0.3.3.tar.gz
Algorithm Hash digest
SHA256 414bd04bc98a0a40bcb7f6548d74a59a17a9454c5f3bb50ae3dd9e63428e2018
MD5 4d71f87fabefbdb596052a57b1201143
BLAKE2b-256 43eb0872bbdb3952e6b82ff9f8e378ab3ebbccc4ef707e8399cd1696eb3886ba

See more details on using hashes here.

File details

Details for the file dhub_cli-0.3.3-py3-none-any.whl.

File metadata

  • Download URL: dhub_cli-0.3.3-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-0.3.3-py3-none-any.whl
Algorithm Hash digest
SHA256 aa5580842dbec8c0c2183d8f0bb7df04e112e241369ce5b655e694a7f13ae976
MD5 0de37dd1d3486835df2c63acf8fc4341
BLAKE2b-256 9094694f6d31dc9d66b9dc36d4e36029447d1cf285dfe27d6a11d9f9d32b01b7

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