finetuning-method-selection
100 / 100 · Low risk
Fine to try.
Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use when starting any fine-tuning effort, when unsure whether RAG or prompting would suffice, or when choosing between preference-optimization and reinforcement methods.
What this skill can do
We found nothing in the files we read that matches our rules. That does not prove the skill is safe: see the limits of static scanning.
Install
Paste this into your terminal. It downloads exactly the version we scanned, not whatever is newest.
if [ -e ~/.agents/skills/'finetuning-method-selection' ] || [ -L ~/.agents/skills/'finetuning-method-selection' ]; then echo 'A skill folder named finetuning-method-selection already exists — not replacing it' >&2; false; else d=$(mktemp -d) && git clone --quiet --filter=blob:none --no-checkout 'https://github.com/wshobson/agents' "$d" && git -C "$d" checkout --quiet '9c61ab243def98f72da12abd41cfcf5bcd91af9d' -- 'plugins/llm-finetuning/skills/finetuning-method-selection' && mkdir -p ~/.agents/skills && cp -R "$d"/'plugins/llm-finetuning/skills/finetuning-method-selection' ~/.agents/skills/'finetuning-method-selection' && rm -rf "$d"; fi
Codex reads ~/.agents/skills directly. For Claude Code, Cursor, Copilot, Gemini CLI, Antigravity or OpenCode, also link it. For Claude Code: ln -s ~/.agents/skills/'finetuning-method-selection' ~/.claude/skills/'finetuning-method-selection' (other agents: ~/.cursor/skills, ~/.copilot/skills, ~/.gemini/skills, ~/.gemini/config/skills, ~/.config/opencode/skills). Or install through the finder skill, which does both.
Badge for your README
[](https://zalavijaysinh.github.io/skilltrust/repos/wshobson/agents/)
Score history
| Date | Version | Score |
|---|---|---|
| 2026-11-11 | 9c61ab2 | 100 |
| 2026-11-08 | 4bde316 | 100 |
| 2026-11-07 | 4bde316 | 100 |