finetuning-method-selection
Decide whether to fine-tune at all, and route to the right method
by wshobsonFree
Description
finetuning-method-selection is an agent skill from the wshobson/agents collection that decides whether fine-tuning is the right tool for a model problem at all, and if it is, which method and which base-model size class to use. It is the router for the fine-tuning lifecycle. The other skills in that sequence assume this routing has already happened, so it is the place to start before working on training data, recipes or training runs. The methods it routes between include supervised fine-tuning (SFT), preference methods such as DPO, ORPO and KTO, reinforcement learning methods such as GRPO and RLVR, and continued pretraining. Each has a different job: SFT teaches a model to produce target responses, preference methods teach it which of two responses is better, and continued pretraining adds knowledge from large amounts of domain text. The skill helps the agent weigh those options against the problem, the data available and the size of the model that can be trained. Its job is to avoid the common mistake of reaching for fine-tuning when prompting, retrieval or a smaller change would do the job. The skill is installed with the skills CLI from the wshobson/agents repository, and its skills.sh page showed about 2.4K installs and passing results from three security audits at the time of the scan.…
Highlights
- Decides whether fine-tuning is the right tool
- Routes to SFT, DPO, ORPO, KTO, GRPO or continued pretraining
- Selects a base-model size class
- Starting point for the fine-tuning workflow
- Installs with the skills CLI
Ratings & Reviews
No ratings yet
Be the first to rate finetuning-method-selection.
People also visit
trace-to-training-data
Convert evaluation traces and production logs into SFT examples
finetuning-method-selection FAQ
What does this skill decide?
Whether fine-tuning is right for a problem, and if so the training method and the base-model size class.
Which methods does it cover?
Supervised fine-tuning, preference methods such as DPO, ORPO and KTO, reinforcement methods such as GRPO and RLVR, and continued pretraining.
Should I start here?
Yes. The skill says the other skills in the fine-tuning sequence assume this routing has already happened.
Is fine-tuning always the answer?
No. The skill is there to check whether fine-tuning is the right tool at all before a method is chosen.
How do I install it?
Run npx skills add https://github.com/wshobson/agents --skill finetuning-method-selection.
What security audits does it have?
skills.sh lists three audits: Gen Agent Trust Hub Pass, Socket Pass and Snyk Pass.
What are the best finetuning-method-selection alternatives?
Popular alternatives to finetuning-method-selection include dataset-curation, trace-to-training-data and fine-tuning-expert. See all finetuning-method-selection alternatives