
Finetuning
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders)
- Scripts
- Python
- Platforms
- Claude Code, Codex, Cursor
- GitHub stars
- 3.2K
- Last commit
- today
- License
- MIT
- Listing updated
- today
When your agent uses it
Fine-tune models on Microsoft Foundry using SFT (supervised), DPO (preference), or RFT (reinforcement with graders). Covers dataset preparation, training job submission, deployment, and evaluation. USE FOR: fine-tune, SFT, DPO, RFT, training data, grader, distillation, fine-tuned model, training job, large file upload, calibrate grader, deploy fine-tuned model, evaluate fine-tuned model. DO NOT USE FOR: general model deployment without fine-tuning (use deploy-model), agent creation (use agents), prompt optimization without training (use prompt-optimizer).
From the skill's SKILL.md. Your agent reads this description to decide when to load the skill.
What it can access
- Runs Python scripts(see the files on GitHub)
- Network calls found in its scripts(see the files on GitHub)
- License: MIT(see the files on GitHub)
From a static check of its 34 files (184 KB) on GitHub on 17 November 2026. Nothing was run. Read the files before you install a skill: it can tell your agent to run anything its tools allow.
Install
Copy the skill folder to ~/.claude/skills/finetuning to use it in all your projects:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.claude/skills &&
rm -rf ~/.claude/skills/finetuning &&
cp -R "$tmp/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning" ~/.claude/skills/finetuning &&
rm -rf "$tmp"For one project only, put the folder in .claude/skills/finetuning inside it instead.
Copy the skill folder to ~/.agents/skills/finetuning to use it in every repository:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.agents/skills &&
rm -rf ~/.agents/skills/finetuning &&
cp -R "$tmp/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning" ~/.agents/skills/finetuning &&
rm -rf "$tmp"For one repository only, put the folder in .agents/skills/finetuning inside it instead.
Copy the skill folder to ~/.cursor/skills/finetuning to use it in every project:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.cursor/skills &&
rm -rf ~/.cursor/skills/finetuning &&
cp -R "$tmp/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning" ~/.cursor/skills/finetuning &&
rm -rf "$tmp"For one project only, put the folder in .cursor/skills/finetuning inside it instead.
Run in a terminal (add --scope workspace to install it for the current workspace only):
gemini skills install https://github.com/microsoft/skills.git --path .github/plugins/azure-skills/skills/microsoft-foundry/finetuningOr copy the folder to ~/.gemini/skills/finetuning yourself.
For GitHub Copilot in VS Code, copy the skill folder to ~/.copilot/skills/finetuning:
tmp=$(mktemp -d) &&
git clone --depth 1 https://github.com/microsoft/skills.git "$tmp" &&
mkdir -p ~/.copilot/skills &&
rm -rf ~/.copilot/skills/finetuning &&
cp -R "$tmp/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning" ~/.copilot/skills/finetuning &&
rm -rf "$tmp"For one project only, put the folder in .github/skills/finetuning inside it instead.
Get the folder:
git clone --depth 1 https://github.com/microsoft/skills.gitThen copy skills/.github/plugins/azure-skills/skills/microsoft-foundry/finetuning into your agent's skills folder as finetuning. Agents that support SKILL.md read one folder per skill.
Finetuning FAQ
How do I install Finetuning in Claude Code?
Copy the skill folder from GitHub to ~/.claude/skills/finetuning to use it in all your projects, or to .claude/skills/finetuning in one project.
Does Finetuning run scripts?
Yes. It runs Python scripts. Its scripts contain network calls. This comes from a static check of the files on GitHub; nothing was run. Read the files before you install it.
Which AI agents can use Finetuning?
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, Windsurf and Goose. Each reads skills in the SKILL.md format from its own folder; the install steps on this page list them.
What are the best alternatives to Finetuning?
The closest alternatives to Finetuning are Academy guide, MCP builder, Claude API, Nano banana pro openrouter and Generate image.
More from microsoft/skills


Diagnose Day-2 AKS GPU and KAITO incidents using profile-aware, read-only evidence
- Open source
- 3.2K GitHub stars

Lookup documented AKS fixes only when the prompt includes an exact catalog signature and all of its qualifiers: VMCannotFitEphemeralOSDisk;
- Open source
- 3.2K GitHub stars

Collects bounded packet captures from AKS nodes and Azure network configuration for wire-level evidence
- Open source
- 3.2K GitHub stars

Debug live Azure Kubernetes Service (AKS) incidents with a read-only, evidence-first investigation
- Open source
- 3.2K GitHub stars

Builds an Azure portal deep link to a specific blade/menu item for supported Microsoft.ContainerService, Microsoft.Kubernetes, and Microsoft
- Open source
- 3.2K GitHub stars
- Cloud and infrastructure
Alternatives to Finetuning

Academy guide
SkillStop and check this skill before finishing any reply to a question about how to use Claude or a Claude product — it recommends matching cour
- 196K GitHub stars
- AI models and LLM tooling

MCP builder
SkillGuide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-design
- 196K GitHub stars
- AI models and LLM tooling

Claude API
SkillReference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model
- 196K GitHub stars
- AI models and LLM tooling

Generate or edit images via OpenRouter with the Gemini 3 Pro Image model
- Open source
- 41.3K GitHub stars
- Design and media


Phoenix evals
SkillBuild and run evaluators for AI/LLM applications using Phoenix.
- Open source
- 41.3K GitHub stars
- AI models and LLM tooling



