Finetuning is an AI Engineering skill for Claude Code, published by evo-hq in evo.
Finetuning selects or diagnoses a training move—SFT, LoRA, DPO/KTO/ORPO, RFT, GRPO/PPO/RLOO, RLHF—based on reward shape and literature, then gates runs with smoke tests, early stopping, and diagnostics. Use it when fine-tuning, post-training, reward design, or weight updates come up.
Finetuning is cataloged under AI Engineering on DirSkills. Finetuning comes from a repository tagged agent-skills, autonomous-agents, autoresearch, claude-code and code-optimization.
Documentation
Priors, not rules. Only firm guardrails: held-out eval you never train on, no leakage, trust evo's recorded numbers over the run's self-report. Override anything else against the gate.
Decide on the reward first, technique second. Choosing the comfortable technique over the matching one is the most common failure.
This is the opening of the README. Read the full README on GitHub.
Finetuning is one of 8 skills that DirSkills catalogs from evo-hq/evo, the repository it ships in. Its siblings there include Discover, Evo Report and Evo Subagent Protocol. Each one is a separate skill with its own page in this directory, installs the same way Finetuning does, and is maintained by evo-hq in that same repository. The rest of the collection is listed on the evo-hq/evo page.
Finetuning ranks #1069 by stars among the 2451 AI Engineering skills in this catalog. The most-starred ones next to it are Architecture Decision Records, AI-First Engineering and Agentic OS. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Finetuning against them. Open each page to compare what they document and how they install.
Finetuning is one of 8 skills cataloged on DirSkills from evo-hq/evo.
Finetuning is one of 2451 AI Engineering skills cataloged on DirSkills, ranked #1069 by stars among them.