Skip to content
Back to search

sdg-hub

MarketplaceWorks with Claude CodeGitHub

Synthetic Data Generation Toolkit for LLMs

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026. Its scripts were only partly scanned.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/red-hat-ai-innovation-team--sdg-hub/badge.svg)](/listings/red-hat-ai-innovation-team--sdg-hub)

HTML

<a href="/listings/red-hat-ai-innovation-team--sdg-hub"><img src="/api/listings/red-hat-ai-innovation-team--sdg-hub/badge.svg" alt="findsafeskills safety rating" /></a>

Install

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 19 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "sdg-hub",
  3. "metadata": {
  4. "description": "Synthetic data generation — composable blocks and YAML-defined flows for building LLM training datasets"
  5. },
  6. "owner": {
  7. "name": "Red Hat AI Innovation Team"
  8. },
  9. "plugins": [
  10. {
  11. "name": "sdg-hub",
  12. "description": "Synthetic data generation — composable blocks and YAML-defined flows for building LLM training datasets",
  13. "author": {
  14. "name": "Red Hat AI Innovation Team"
  15. },
  16. "source": "./"
  17. }
  18. ]
  19. }
README.md · README · 111 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <p align="center">
  2. <picture>
  3. <source media="(prefers-color-scheme: dark)" srcset="docs/assets/logo-banner-dark.svg">
  4. <source media="(prefers-color-scheme: light)" srcset="docs/assets/logo-banner-light.svg">
  5. <img alt="SDG Hub" src="docs/assets/logo-banner-light.svg" width="320">
  6. </picture>
  7. </p>
  8. <p align="center"><em>Composable blocks and flows for synthetic data generation</em></p>
  9. <p align="center">
  10. <a href="https://ai-innovation.team/sdg_hub/"><img src="https://img.shields.io/badge/docs-ai--innovation.team-e8975d?style=flat-square" alt="Docs"></a>
  11. <a href="https://pypi.org/project/sdg-hub/"><img src="https://img.shields.io/pypi/v/sdg-hub?style=flat-square" alt="PyPI"></a>
  12. <a href="https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/actions/workflows/test.yml"><img src="https://img.shields.io/github/actions/workflow/status/Red-Hat-AI-Innovation-Team/sdg_hub/test.yml?style=flat-square&label=tests" alt="Tests"></a>
  13. <img src="https://img.shields.io/badge/python-3.10%2B-brightgreen?style=flat-square" alt="Python 3.10+">
  14. <a href="https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub/blob/main/LICENSE"><img src="https://img.shields.io/github/license/Red-Hat-AI-Innovation-Team/sdg_hub?style=flat-square" alt="License"></a>
  15. <a href="https://codecov.io/gh/Red-Hat-AI-Innovation-Team/sdg_hub"><img src="https://img.shields.io/codecov/c/github/Red-Hat-AI-Innovation-Team/sdg_hub?style=flat-square" alt="Coverage"></a>
  16. <a href="https://deepwiki.com/Red-Hat-AI-Innovation-Team/sdg_hub"><img src="https://deepwiki.com/badge.svg" alt="Ask DeepWiki"></a>
  17. </p>
  18. ---
  19. <p align="center">
  20. <img src="docs/assets/demo.gif" alt="SDG Hub Demo" width="700">
  21. </p>
  22. SDG Hub is a Python framework for building synthetic data generation pipelines. Chain LLM, parsing, transform, filtering, and agent blocks into YAML-defined flows -- then generate training data at scale.
  23. ## Get Started
  24. ```bash
  25. pip install sdg-hub
  26. ```
  27. ```python
  28. from sdg_hub import FlowRegistry, Flow
  29. # Discover and load a built-in flow
  30. FlowRegistry.discover_flows()
  31. flow = Flow.from_yaml(FlowRegistry.get_flow_path("MCP Server Distillation"))
  32. # Configure and run
  33. flow.set_model_config(model="openai/gpt-4o")
  34. result = flow.generate(dataset)
  35. ```
  36. See the [Quick Start](docs/quickstart.md) for a full walkthrough, or browse [all built-in flows](docs/flows/built-in-flows.md).
  37. ## Documentation
  38. **[Full documentation at ai-innovation.team/sdg_hub](https://ai-innovation.team/sdg_hub/)**
  39. - [Installation](docs/installation.md) -- setup, optional dependencies, development install
  40. - [Quick Start](docs/quickstart.md) -- end-to-end walkthrough from loading a flow to generating data
  41. - [Core Concepts](docs/concepts.md) -- blocks, flows, registries, and dataset handling
  42. - [Block Reference](docs/blocks/) -- LLM, parsing, transform, filtering, agent, and custom blocks
  43. - [Flow Reference](docs/flows/) -- YAML schema, built-in flows, custom flows
  44. - [API Reference](docs/reference/) -- auto-generated from source
  45. - [Contributing](CONTRIBUTING.md) -- development setup and contribution guidelines
  46. ## Coding Agent Plugin
  47. SDG Hub is available as a plugin for two coding agents, bringing synthetic data generation directly into your coding workflow.
  48. <details>
  49. <summary><strong>Claude Code</strong></summary>
  50. **Via org marketplace** (recommended — includes all Red Hat AI plugins):
  51. ```bash
  52. /plugin marketplace add Red-Hat-AI-Innovation-Team/plugins
  53. /plugin install sdg-hub@Red-Hat-AI-Innovation-Team/plugins
  54. ```
  55. **Via this repo directly:**
  56. ```bash
  57. /plugin marketplace add Red-Hat-AI-Innovation-Team/sdg_hub
  58. /plugin install sdg-hub@Red-Hat-AI-Innovation-Team/sdg_hub
  59. ```
  60. **From a local clone:**
  61. ```bash
  62. git clone https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub.git
  63. /plugin marketplace add /path/to/sdg_hub
  64. ```
  65. </details>
  66. <details>
  67. <summary><strong>Codex CLI</strong></summary>
  68. ```bash
  69. codex plugin marketplace add Red-Hat-AI-Innovation-Team/plugins
  70. ```
  71. Then install the plugin from the marketplace. See `.codex-plugin/INSTALL.md` for manual installation.
  72. </details>
  73. ### After Installing
  74. Invoke the `setup-guide` skill to configure your LLM provider and model.
  75. | Skill | Description |
  76. |---|---|
  77. | `setup-guide` | Guided first-time configuration |
  78. | `data-generation` | Run synthetic data generation using a flow |
  79. | `flow-browser` | Browse and inspect available flows |
  80. ## License
  81. Apache License 2.0 -- see [LICENSE](LICENSE).
  82. ---
  83. Built by the [Red Hat AI Innovation Team](https://ai-innovation.team)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.