New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

LLM Finetuning

by RightNow-AI in RightNow-AI/openfang

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

Apache-2.0Auto-check passedAI & LLM Engineering

Install LLM Finetuning

skills CLI
$ npx skills add RightNow-AI/openfang --skill llm-finetuning -a claude-code

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

GitHub CLI
$ gh skill install RightNow-AI/openfang llm-finetuning --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/RightNow-AI/openfang.git skills-src && mkdir -p .claude/skills && cp -r skills-src/crates/openfang-skills/bundled/llm-finetuning .claude/skills/llm-finetuning && 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
llm-finetuning
GitHub stars
18k
Token cost
~986 tokens
SKILL.md length
517 words
Files
1
Skills in repo
68
Repo updated
First seen
Licence
Apache-2.0

At a glance

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

  • Tasks that involve Fine-tuning
  • SKILL.md covers Key Principles, Techniques, Common Patterns and Pitfalls to Avoid
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

LLM Finetuning is an agent skill from RightNow-AI/openfang. LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

Its SKILL.md is about 990 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 AI & LLM Engineering, covering Fine-tuning. The repository describes itself as: Open-source Agent Operating System. The licence is Apache-2.0.

When your agent uses it

  • Tasks that involve Fine-tuning

Example prompts

  • “/llm-finetuning”

What it can do on your machine

Read from SKILL.md and the folder at commit acf2587. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

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

  • Network

    No URLs in SKILL.md.

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

  • Credentials

    Names no API keys, tokens, secrets or passwords.

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

Context cost

LLM Finetuning loads about 986 tokens when it runs. Until then it costs about 25 tokens; SKILL.md has 517 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~25
When it runs · the whole SKILL.md, loaded when a task matches
~986

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 RightNow-AI/openfang at commit acf2587, republished under its Apache-2.0 licence (© RightNow-AI). 517 words, ~986 tokens.

Download SKILL.mdSave it as .claude/skills/llm-finetuning/SKILL.md (or your agent's skills folder).
name
llm-finetuning
description
LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization

LLM Fine-Tuning Expert

A deep learning specialist with hands-on expertise in fine-tuning large language models using parameter-efficient methods, dataset curation, and training optimization. This skill provides guidance for adapting foundation models to specific domains and tasks using LoRA, QLoRA, and the Hugging Face PEFT ecosystem, covering dataset preparation, hyperparameter selection, evaluation strategies, and adapter deployment.

Key Principles

  • Fine-tuning is about teaching a model your task format and domain knowledge, not about teaching it language; start with the strongest base model you can afford to run
  • Dataset quality matters far more than quantity; 1,000 carefully curated, diverse, high-quality examples often outperform 100,000 noisy ones
  • Use parameter-efficient fine-tuning (LoRA/QLoRA) to reduce memory requirements by orders of magnitude while achieving performance comparable to full fine-tuning
  • Evaluate with task-specific metrics and human review, not just perplexity; a model with lower perplexity may still produce worse outputs for your specific use case
  • Track every experiment with exact hyperparameters, dataset versions, and base model checkpoints so that results are reproducible and comparable

Techniques

  • Configure LoRA with appropriate rank (r=8 to 64), alpha (typically 2x rank), and target modules (q_proj, v_proj for attention, or all linear layers for broader adaptation)
  • Use QLoRA for memory-constrained setups: load the base model in 4-bit NormalFloat quantization, attach LoRA adapters in fp16/bf16, and train with paged optimizers to handle memory spikes
  • Format datasets as instruction-response pairs with consistent templates; include a system field for persona or context, an instruction field for the task, and a response field for the expected output
  • Apply the PEFT library workflow: load base model, create LoRA config, get_peft_model(), train with the Hugging Face Trainer or a custom loop, then save and load adapters independently
  • Set training hyperparameters carefully: learning rate between 1e-5 and 2e-4 with cosine schedule, 1-5 epochs (watch for overfitting), warmup ratio of 0.03-0.1, and gradient accumulation to simulate larger batch sizes
  • Evaluate with multiple signals: validation loss for overfitting detection, task-specific metrics (ROUGE for summarization, exact match for QA), and structured human evaluation on a held-out set
Show full SKILL.md (183 more words)Show less

Common Patterns

  • Domain Adaptation: Fine-tune on domain-specific text (legal, medical, financial) to teach the model terminology, reasoning patterns, and output formats unique to that field
  • Instruction Following: Train on diverse instruction-response pairs to improve the model's ability to follow complex multi-step instructions and produce structured outputs
  • Adapter Merging: After training, merge the LoRA adapter weights back into the base model with merge_and_unload() for inference without the PEFT overhead
  • Multi-task Training: Mix datasets from different tasks (summarization, classification, extraction) in a single fine-tuning run to create a versatile adapter

Pitfalls to Avoid

  • Do not fine-tune on data that contains personally identifiable information, copyrighted content, or harmful material without proper review and filtering
  • Do not train for too many epochs on a small dataset; language models memorize quickly, and overfitting manifests as repetitive, templated outputs that lack generalization
  • Do not skip decontamination between training and evaluation sets; if evaluation examples appear in training data, metrics will be artificially inflated
  • Do not assume a single set of hyperparameters works across base models; different architectures and sizes respond differently to learning rates, LoRA ranks, and batch sizes

© RightNow-AI, 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 crates/openfang-skills/bundled/llm-finetuning of RightNow-AI/openfang.

Open the folder on GitHubat commit acf2587

Compare with similar skills

LLM Finetuning 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.

LLM Finetuning compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
LLM Finetuning this skillRightNow-AI/openfang18k—~986Automated safety check: PassApache-2.0
Sentence-Transformers Training Routerhuggingface/skills11k1 repos~2.6kAutomated safety check: PassApache-2.0
Train RlOpenPipe/ART11k—~2.4kAutomated safety check: PassApache-2.0
Qwopus27b Rl TrainingR6410418/Jackrong-llm-finetuning-guide1.7k—~830Automated safety check: PassApache-2.0
Dataset Evaluationawslabs/agent-plugins9161 repos~1.3kAutomated safety check: PassApache-2.0
Train SftOpenPipe/ART11k—~2.9kAutomated safety check: PassApache-2.0

Similar skills

  • Sentence-Transformers Training Router

    huggingface/skills

    Official

    Routes a sentence-transformers training task to the right model type and required reference docs and example scripts, covering bi-encoders, rerankers, sparse and multi-vector models.

    11k GitHub starsUsed in 1 repo~2.6k tokens
    AI & LLM EngineeringAuto-check passed

  • Train Rl

    OpenPipe/ART

    RL training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.4k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Qwopus27b Rl Training

    R6410418/Jackrong-llm-finetuning-guide

    Prepare, validate, launch-plan, monitor, resume, and stop configurable Qwopus 27B reinforcement-learning workflows for GRPO or GSPO.

    1.7k GitHub stars~830 tokensUpdated 3 mo ago
    AI & LLM EngineeringAuto-check passed

  • Dataset Evaluation

    awslabs/agent-plugins

    Official

    Validates dataset formatting and quality for SageMaker model fine-tuning (SFT, DPO, or RLVR).

    916 GitHub starsUsed in 1 repo~1.3k tokens
    AI & LLM EngineeringAuto-check passed

  • Train Sft

    OpenPipe/ART

    SFT training reference for the ART framework. An agent skill from OpenPipe/ART.

    11k GitHub stars~2.9k tokensUpdated today
    AI & LLM EngineeringAuto-check passed

  • Fine Tuning With Trl

    Orchestra-Research/AI-Research-SKILLs

    Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training.

    13k GitHub starsUsed in 6 repos~2.9k tokens
    AI & LLM EngineeringAuto-check passed

More from RightNow-AI/openfang

All 68 skills in this repo

  • Playwright Browser Automation Patterns

    RightNow-AI/openfang

    Reference of CSS selectors, step-by-step web workflows and error recovery tactics for an agent that browses, fills forms and compares prices on live sites.

    18k GitHub stars~1k tokensUpdated 3 mo ago
    Auto-check passed

  • Intelligence Collection Methodology

    RightNow-AI/openfang

    Reference knowledge for open-source intelligence collection: the collection cycle, source reliability tiers, search query patterns and entity extraction.

    18k GitHub stars~2.1k tokensUpdated 3 mo ago
    Auto-check passed

  • Lead Generation Research Guide

    RightNow-AI/openfang

    Reference knowledge for AI lead generation: building an ideal customer profile, researching prospects on the web, enriching lead records and finding email formats.

    18k GitHub stars~1.8k tokensUpdated 3 mo ago
    Auto-check passed

  • Video Clipping Reference

    RightNow-AI/openfang

    Command reference for cutting clips from online video: yt-dlp downloads, whisper transcription, SRT subtitle files and ffmpeg processing, with Windows, macOS and Linux differences.

    18k GitHub stars~4.1k tokensUpdated 3 mo ago
    Auto-check: warnings

  • Forecasting Expert Knowledge

    RightNow-AI/openfang

    Reference knowledge for AI forecasting: superforecasting principles, a signal taxonomy, confidence calibration rules and reasoning chains for making and tracking predictions.

    18k GitHub stars~2.5k tokensUpdated 3 mo ago
    Auto-check passed

  • Deep Research Methodology

    RightNow-AI/openfang

    Reference knowledge for AI deep research: a five-phase process, strategies by question type, CRAAP source scoring, cross-referencing, synthesis and citation formats.

    18k GitHub stars~2.6k tokensUpdated 3 mo ago
    Auto-check passed

Categories

Questions about LLM Finetuning

What does LLM Finetuning do?

LLM fine-tuning expert for LoRA, QLoRA, dataset preparation, and training optimization. LLM Finetuning is an agent skill from RightNow-AI/openfang.

When should I use LLM Finetuning?

LLM Finetuning fits situations like: tasks that involve Fine-tuning.

How do I install LLM Finetuning in Claude Code?

Run `npx skills add RightNow-AI/openfang --skill llm-finetuning -a claude-code`. Or copy the skill folder (crates/openfang-skills/bundled/llm-finetuning in RightNow-AI/openfang) into .claude/skills/llm-finetuning in your project. Claude Code loads it when a task matches its description.

How do I install LLM Finetuning in Codex?

Run `npx skills add RightNow-AI/openfang --skill llm-finetuning -a codex`. Or copy the skill folder (crates/openfang-skills/bundled/llm-finetuning in RightNow-AI/openfang) into .agents/skills/llm-finetuning in your project. Codex loads it when a task matches its description.

Can I use LLM Finetuning 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 RightNow-AI/openfang --skill llm-finetuning -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/llm-finetuning, .gemini/skills/llm-finetuning, .github/skills/llm-finetuning and .opencode/skills/llm-finetuning in your project.

What does LLM Finetuning need to run?

SKILL.md names no scripts, command-line tools or credentials: LLM Finetuning is instructions for the agent only.

Does LLM Finetuning access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is LLM Finetuning 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 LLM Finetuning use?

LLM Finetuning 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 LLM Finetuning use?

About 986 tokens (SKILL.md is roughly 3.9k 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 LLM Finetuning?

Skills that share tags, products or a category with LLM Finetuning: Sentence-Transformers Training Router (huggingface/skills, 11k stars), Train Rl (OpenPipe/ART, 11k stars), Qwopus27b Rl Training (R6410418/Jackrong-llm-finetuning-guide, 1.7k stars) and Dataset Evaluation (awslabs/agent-plugins, 916 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LLM Finetuning?

RightNow-AI (a GitHub organization) maintains it in RightNow-AI/openfang, which has 18,214 GitHub stars. The repository holds 68 skills in this directory. The repository was last updated on July 2, 2026.

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