fine-tuning

fine-tuning is a skill for Claude Code, Codex from nimadorostkar/Claude-Skills-collection. It costs 46 tokens per session (1,456 once invoked), scanned A, original, MIT.

Guidance for deciding whether to fine-tune a language model—train it further on examples for a specific task—and for carrying out that work. It covers data preparation, lightweight or full training, and evaluation against the original model.

In plain words
What is it for?
Use it when prompting has stopped meeting an accuracy, format, style, vocabulary, cost, or latency requirement, or when reviewing an existing fine-tuned model.
Why use it?
It helps avoid training when better prompts or search-based context would solve the problem. It also focuses on clean datasets and tests, which are common sources of failed fine-tuning projects.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: positional $N argument.

Good fit Use it when prompting has stopped meeting an accuracy, format, style, vocabulary, cost, or latency requirement, or when reviewing an existing fine-tuned model.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nimadorostkar/claude-skills-collection/fine-tuning
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add nimadorostkar/Claude-Skills-collection --skill fine-tuning
Clone the repo
git clone --depth 1 https://github.com/nimadorostkar/Claude-Skills-collection

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for fine-tuning

README.md
[![agentmods](https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/fine-tuning/github.svg)](https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/fine-tuning)
Your own site
<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/fine-tuning"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/fine-tuning/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for fine-tuning

Your own site · 80×15
<a href="https://agentmods.dev/skills/nimadorostkar/claude-skills-collection/fine-tuning"><img src="https://agentmods.dev/badge/skills/nimadorostkar/claude-skills-collection/fine-tuning.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 46 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00046 $0.01456
Opus 5 $0.00023 $0.00728
Sonnet 5 $0.00009 $0.00291
Haiku 4.5 $0.00005 $0.00146

Measured 12d ago against content hash 0143da6fc7d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

fine-tuning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/ai/fine-tuning/SKILL.md · 121 lines

How it starts

The opening of the file, as written. The whole thing — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Fine-Tuning

Purpose

Decide whether fine-tuning is warranted, and do it properly if it is. Most fine-tuning projects should have been prompt engineering or retrieval, and the ones that should be fine-tuning usually fail on dataset quality rather than on the training.

When to Use

  • A task where prompting has plateaued below the required accuracy.
  • A specific output format, style, or domain vocabulary the model will not adopt reliably.
  • Reducing cost by making a small model do what currently requires a large one.
  • Evaluating an existing fine-tuned model that underperforms.

Capabilities

  • Deciding between prompting, RAG, and fine-tuning.
  • Dataset construction, curation, and splitting.
  • LoRA and QLoRA versus full fine-tuning.
  • Hyperparameter selection and overfitting detection.
  • Evaluation against the base model on the same set.

Inputs

  • The task, and the accuracy prompting achieves on it.
  • Available training data — its volume, and honestly, its quality.
  • Latency and cost constraints.

Outputs

  • A justified decision to fine-tune, or not to.
  • A curated dataset with clean train/validation/test splits.
  • A model measurably better than the base model on a held-out set.

Workflow

  1. Exhaust prompting first — Few-shot examples, a clearer output contract, a better model. Fine-tuning cannot teach knowledge the model lacks; it teaches behavior. If the problem is that the model does not know something, use retrieval instead.
  2. Decide what fine-tuning is actually for — Format adherence, tone, a domain-specific classification boundary, or distilling a large model's behavior into a small one. Those are the cases where it works.
  3. Build the dataset carefully — This is where the project succeeds or fails. A thousand clean, consistent examples beat fifty thousand noisy ones. Inconsistent labels teach the model to be inconsistent.
  4. Split before you look — Train, validation, test. The test set is touched once, at the end. Selecting a checkpoint on the test set is how you produce a model that scores well and performs badly.
  5. Start with LoRA — It is cheap, fast, and sufficient for the majority of tasks. Full fine-tuning is warranted rarely.
  6. Compare against the base model on the same test set — With the same prompt. A fine-tuned model that does not beat a well-prompted base model is a liability, not an asset.

Read the full file on GitHub · 121 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 12d ago First seen · 121 lines · 46 tokens per session scan A 0143da6fc7d8

Subscribe to this mod's changes

fine-tuning is a skill published in the GitHub repository nimadorostkar/Claude-Skills-collection (26 stars, last pushed 25d ago), licensed MIT. It adds 46 tokens to every session and 1,456 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

datarobot-agent-assist

Use when the user wants to design, build, code, simulate, or deploy an AI agent (not a predictive model) to DataRobot; mentions agentspec.md, dr-assist, datarobot-agent-assist, dress rehearsal, swarm simulation, or the DataRobot agent template; wants to scaffold a LangGraph, CrewAI, LlamaIndex, NAT, or Base agent…

datarobot-oss/datarobot-agent-skills · 182 tokens

datarobot-agent-assist-build

Use when the user wants to design, build, code, or deploy an AI agent on DataRobot; mentions agentspec.md, dress rehearsal, the DataRobot agent template, LangGraph, CrewAI, LlamaIndex, NAT, Base agents, MCP servers, backend APIs, custom frontends, or the DataRobot CLI.

datarobot-oss/datarobot-agent-skills · 74 tokens

datarobot-model-explainability

Tools and guidance for model explainability, prediction explanations, feature impact analysis, SHAP values, SHAP distributions, anomaly assessment, and model diagnostics. Use when analyzing model explanations, feature impact, SHAP values, SHAP distributions, anomaly assessment, or diagnosing model behavior.

datarobot-oss/datarobot-agent-skills · 63 tokens

datarobot-model-training

Comprehensive guidance for training models in DataRobot, including project creation, AutoML configuration, feature engineering, and model selection. Use when training models, creating AutoML projects, or selecting models in DataRobot.

datarobot-oss/datarobot-agent-skills · 48 tokens

datarobot-predictions

Tools and guidance for making predictions with DataRobot deployments, including real-time predictions, batch scoring, prediction dataset generation, and prediction explanations (SHAP/XEMP). Use when making predictions, running batch scoring, generating prediction datasets, or explaining individual predictions from a…

datarobot-oss/datarobot-agent-skills · 60 tokens

datarobot-setup

Sets up DataRobot for local development including Python SDK, dr-cli, Agent Assist, and all required dependencies. Use when the user has not yet worked with DataRobot on this machine, OR when any DataRobot task fails due to missing or invalid credentials. Covers first-time setup, re-authentication, and credential…

datarobot-oss/datarobot-agent-skills · 70 tokens