A skill your agent uses when the user wants to set up synthetic data generation for the first time, or when sdghub is not yet installed/configured in the current environment.

Apache-2.0Auto-check passedTesting & QA

Install Setup Guide

skills CLI
$ npx skills add Red-Hat-AI-Innovation-Team/sdg_hub --skill setup-guide -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Red-Hat-AI-Innovation-Team/sdg_hub setup-guide --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Red-Hat-AI-Innovation-Team/sdg_hub.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/setup-guide .claude/skills/setup-guide && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
setup-guide
GitHub stars
164
Token cost
~1.1k tokens
SKILL.md length
501 words
Files
1
Skills in repo
4
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses when the user wants to set up synthetic data generation for the first time, or when sdghub is not yet installed/configured in the current environment.

  • Works in 7 steps: Detect Environment → Install if Needed → Quick Setup or Custom → …
  • The user wants to set up synthetic data generation for the first time
  • SKILL.md covers Step 1: Detect Environment, Step 2: Install if Needed, Step 3: Quick Setup or Custom and Step 4: Collect Configuration, plus 4 more sections
  • Calls uv and pip; needs OPENAI_API_KEY and ANTHROPIC_API_KEY

What it does

Setup Guide is an agent skill from Red-Hat-AI-Innovation-Team/sdg_hub. Use when the user wants to set up synthetic data generation for the first time, or when sdghub is not yet installed/configured in the current environment.

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Testing & QA, covering Test data and fixtures. It works with OpenAI. The repository describes itself as: Synthetic Data Generation Toolkit for LLMs. The licence is Apache-2.0.

When your agent uses it

  • The user wants to set up synthetic data generation for the first time
  • Sdghub is not yet installed/configured in the current environment

Example prompts

  • “/setup-guide”

Requirements

  • Python 3
  • A credential in OPENAI_API_KEY
  • A credential in ANTHROPIC_API_KEY
  • Pre-approved tools (allowed-tools): Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_detect.sh:*), Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_flows.sh:*)

Workflow steps

7 steps, taken from the step headings in SKILL.md.

  1. Detect Environment
  2. Install if Needed
  3. Quick Setup or Custom
  4. Collect Configuration
  5. Ensure API Key
  6. Save Config
  7. Verify

What it can do on your machine

Read from SKILL.md and the folder at commit 31efcbe. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves these tools, so the agent can use them without asking each time:

    • Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_detect.sh:*)
    • Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_flows.sh:*)

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • uv
    • pip

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use uv and pip, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • OPENAI_API_KEY
    • ANTHROPIC_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Setup Guide loads about 1.1k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 501 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~42
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Red-Hat-AI-Innovation-Team/sdg_hub at commit 31efcbe, republished under its Apache-2.0 licence (© Red-Hat-AI-Innovation-Team). 501 words, ~1,064 tokens.

Download SKILL.mdSave it as .claude/skills/setup-guide/SKILL.md (or your agent's skills folder).
name
setup-guide
description
Use when the user wants to set up synthetic data generation for the first time, or when sdg_hub is not yet installed/configured in the current environment.
allowed-tools
Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_detect.sh:*), Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_flows.sh:*)

sdg_hub Setup Guide

You are helping the user set up synthetic data generation.

Step 1: Detect Environment

"${CLAUDE_PLUGIN_ROOT}/scripts/sdg_detect.sh"

Step 2: Install if Needed

If library=missing:

  • Explain: "sdg_hub is a framework for synthetic data generation — it uses composable blocks and YAML-defined flows to build LLM training datasets from seed data."
  • Ask permission: "I can install it for you. Want me to proceed?"
  • If yes and installer=uv: run uv pip install sdg_hub
  • If yes and installer=pip: run pip install sdg_hub
  • If installer=none: tell the user they need Python and pip/uv installed first

Step 3: Quick Setup or Custom

Also check for API keys in the environment:

echo "openai_key=${OPENAI_API_KEY:+found}" "anthropic_key=${ANTHROPIC_API_KEY:+found}"

If an API key was detected, offer a one-question fast path:

"I detected your OpenAI API key. I can set up with these defaults:

  • Model: openai/gpt-4o-mini
  • Temperature: 0.7
  • Concurrency: 5

Accept these defaults, or would you like to customize?"

If the user accepts, skip to Step 5 using the detected key and defaults.

For Anthropic keys, default to anthropic/claude-sonnet-4-20250514.

If no API key was detected, or the user wants to customize, proceed to Step 4.

Step 4: Collect Configuration

Ask these questions one at a time:

  1. Model: "Which LLM model do you want to use for generation?" — e.g., openai/gpt-4o-mini, meta-llama/Llama-3.3-70B-Instruct, anthropic/claude-sonnet-4-20250514
  2. API endpoint: "What's your model endpoint URL?" — e.g., http://localhost:8000/v1 for vLLM, or leave empty for cloud provider defaults
  3. Temperature: "What temperature for generation?" (default: 0.7)
  4. Max concurrency: "How many parallel LLM requests?" (default: 5) — higher is faster but may hit rate limits
  5. Checkpoint directory: "Where should generation checkpoints be saved?" (default: ./checkpoints) — allows resuming interrupted runs
Show full SKILL.md (236 more words)Show less

Step 5: Ensure API Key

API keys are read from environment variables — never store them in the config file. LiteLLM (used by sdg_hub) reads standard env vars automatically.

If no API key was detected in Step 3, tell the user to set the appropriate environment variable:

"Set your API key as an environment variable before running generation:

bash
export OPENAI_API_KEY="sk-..."        # OpenAI models
export ANTHROPIC_API_KEY="sk-ant-..."  # Anthropic models

For local endpoints (vLLM, Ollama) that don't require authentication, no API key is needed. LiteLLM picks up these env vars automatically — no extra configuration required."

Step 6: Save Config

Write the config to .sdg-hub/config.json:

json
{
  "model": "<model>",
  "api_base": "<endpoint>",
  "temperature": 0.7,
  "max_concurrency": 5,
  "checkpoint_dir": "./checkpoints"
}

Add .sdg-hub/ to .gitignore if not already present.

Confirm the config file was written, then report success:

"Setup complete! To run generation, use the data-generation skill, or the flow-browser skill to browse available flows.

API keys are read from environment variables, not the config file. Make sure the appropriate variable is set in your shell:

bash
export OPENAI_API_KEY="sk-..."        # OpenAI models
export ANTHROPIC_API_KEY="sk-ant-..."  # Anthropic models

Local endpoints (vLLM, Ollama) don't need an API key."

Step 7: Verify

List available flows to confirm the installation works:

"${CLAUDE_PLUGIN_ROOT}/scripts/sdg_flows.sh" list

Report success and remind the user they can now use the data-generation skill to run generation, or the flow-browser skill to browse available flows.

Updating Config

If this skill is invoked again and a config already exists, ask: "You already have a configuration. Do you want to update it or start fresh?"

© Red-Hat-AI-Innovation-Team, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .claude/skills/setup-guide of Red-Hat-AI-Innovation-Team/sdg_hub.

Open the folder on GitHubat commit 31efcbe

Compare with similar skills

Setup Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Setup Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Setup Guide this skillRed-Hat-AI-Innovation-Team/sdg_hub164—~1.1kAutomated safety check: PassApache-2.0
Datagen Standard Launchopen-thoughts/OpenThoughts-Agent301—~947Automated safety check: PassApache-2.0
Reasoning Serialization Teststailcallhq/forgecode7.6k—~1kAutomated safety check: PassApache-2.0
LLM Providercaliber-ai-org/ai-setup1.3k—~2.7kAutomated safety check: PassMIT
Rsibench Data Factoryevolvent-ai/RSIBench-Data171—~640Automated safety check: NotesNone
Kiln Prerelease CheckKiln-AI/Kiln5.2k—~7.8kAutomated safety check: NotesCustom licence

Similar skills

  • Datagen Standard Launch

    open-thoughts/OpenThoughts-Agent

    Launch NON-AGENTIC (standard) data generation — plain vLLM/API completion generation with NO Harbor agent loop or Daytona sandboxes.

    301 GitHub stars~947 tokensUpdated 11 days ago
    AI & LLM EngineeringAuto-check passed
  • Reasoning Serialization Tests

    tailcallhq/forgecode

    Checks that ReasoningConfig fields are serialized into the right provider-specific JSON for OpenRouter, Anthropic, GitHub Copilot and Codex requests.

    7.6k GitHub stars~1k tokensUpdated today
    Testing & QAAuto-check passed
  • LLM Provider

    caliber-ai-org/ai-setup

    Adds a new LLM provider implementing LLMProvider interface with call() and stream() methods.

    1.3k GitHub stars~2.7k tokensUpdated 16 days ago
    Testing & QAAuto-check passed
  • Rsibench Data Factory

    evolvent-ai/RSIBench-Data

    Use inside RSIBench-Data when testing whether an automation agent can improve a target model on a configured benchmark through synthetic Tinker SFT data, Tinker sampling, and E2B-based Harbor…

    171 GitHub stars~640 tokensUpdated 1 mo ago
    Testing & QAAuto-check: notes
  • Run the Kiln pre-release smoke test suite plus the standard CI checks (checks.sh), diagnose every prerelease test that broke (and why), and write a clean readable report with recommended actions.

    5.2k GitHub stars~7.8k tokensUpdated today
    Testing & QAAuto-check: notes
  • Seed Test Data

    langfuse/langfuse

    Seed reproducible local Langfuse data in ClickHouse and Postgres.

    36k GitHub stars~5.8k tokensUpdated today
    Testing & QAAuto-check passed

More from Red-Hat-AI-Innovation-Team/sdg_hub

  • Synthetic Data Generation

    Red-Hat-AI-Innovation-Team/sdg_hub

    Generate synthetic data using sdghub with composable blocks and YAML flows.

    164 GitHub stars~3.1k tokensUpdated today
    Auto-check passed
  • Data Generation

    Red-Hat-AI-Innovation-Team/sdg_hub

    A skill your agent uses when the user wants to run synthetic data generation via scripts — detect environment, execute a flow, and present results.

    164 GitHub stars~381 tokensUpdated today
    Auto-check passed
  • Flow Browser

    Red-Hat-AI-Innovation-Team/sdg_hub

    A skill your agent uses when the user wants to list, search, or inspect available SDG flows and data generation pipelines.

    164 GitHub stars~343 tokensUpdated today
    Auto-check passed

Works with

Questions about Setup Guide

What does Setup Guide do?

A skill your agent uses when the user wants to set up synthetic data generation for the first time, or when sdghub is not yet installed/configured in the current environment. Setup Guide is an agent skill from Red-Hat-AI-Innovation-Team/sdg_hub. Use when the user wants to set up synthetic data generation for the first time, or when sdghub is not yet installed/configured in the current environment.

When should I use Setup Guide?

Setup Guide fits situations like: the user wants to set up synthetic data generation for the first time; sdghub is not yet installed/configured in the current environment.

How do I install Setup Guide in Claude Code?

Run `npx skills add Red-Hat-AI-Innovation-Team/sdg_hub --skill setup-guide -a claude-code`. Or copy the skill folder (.claude/skills/setup-guide in Red-Hat-AI-Innovation-Team/sdg_hub) into .claude/skills/setup-guide in your project. Claude Code loads it when a task matches its description.

How do I install Setup Guide in Codex?

Run `npx skills add Red-Hat-AI-Innovation-Team/sdg_hub --skill setup-guide -a codex`. Or copy the skill folder (.claude/skills/setup-guide in Red-Hat-AI-Innovation-Team/sdg_hub) into .agents/skills/setup-guide in your project. Codex loads it when a task matches its description.

Can I use Setup Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Red-Hat-AI-Innovation-Team/sdg_hub --skill setup-guide -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/setup-guide, .gemini/skills/setup-guide, .github/skills/setup-guide and .opencode/skills/setup-guide in your project.

What does Setup Guide need to run?

Going by SKILL.md and its folder, Setup Guide needs the command-line tools its instructions call (uv and pip) and credentials named OPENAI_API_KEY and ANTHROPIC_API_KEY. Our summary lists: Python 3; A credential in OPENAI_API_KEY; A credential in ANTHROPIC_API_KEY. Its frontmatter pre-approves these tools: Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_detect.sh:*), Bash(${CLAUDE_PLUGIN_ROOT}/scripts/sdg_flows.sh:*).

Does Setup Guide access the network?

SKILL.md contains no URLs. Its commands use uv and pip, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Setup Guide safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Setup Guide use?

Setup Guide is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Setup Guide use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Setup Guide?

Skills that share tags, products or a category with Setup Guide: Datagen Standard Launch (open-thoughts/OpenThoughts-Agent, 301 stars), Reasoning Serialization Tests (tailcallhq/forgecode, 7.6k stars), LLM Provider (caliber-ai-org/ai-setup, 1.3k stars) and Rsibench Data Factory (evolvent-ai/RSIBench-Data, 171 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Setup Guide?

Red-Hat-AI-Innovation-Team (a GitHub organization) maintains it in Red-Hat-AI-Innovation-Team/sdg_hub, which has 164 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 9, 2026.

Source: Red-Hat-AI-Innovation-Team/sdg_hub on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.