finetuning-method-selection
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.
Agent Skill from wshobson/agents
Copilot Studio
Passes documented load rulesNo documented load rule failed.
Microsoft 365 Copilot Preview, Frontier tenants only
Passes documented load rulesNo documented load rule failed.
An agent can have at most 8 skills. Custom skills aren't available in tenants that use Microsoft Purview Information Barriers.
Standards signals
Meets the agentskills.io required fields.
| Frontmatter | Present and parsed Spec: frontmatter |
| name | Meets the spec (1-64 chars, a-z 0-9 hyphens) Spec: name |
| description | Present, 1-1,024 characters Spec: description |
| compatibility | Absent or under 500 characters Spec: compatibility |
| Name matches folder | Yes (finetuning-method-selection)Spec: name |
Observed from the public SKILL.md at the commit above on 2026-10-23. Not a certification: AAIF and the Agent Skills project don't certify skills. Validate your own skill with skills-ref validate.
| Source repo | wshobson/agents |
| Path | plugins/llm-finetuning/skills/finetuning-method-selection/SKILL.md |
| Commit checked | 0874a27b17a2 |
| Repo license | MIT |
| Files | 3 |
| Scripts | None |
| Instructions | 7,469 characters |
| Deepest folder | 1 below the skill folder |
| Rules version | 2026-10-22 |
Re-check the latest version How skill checks work
Rule-based checks of public files against Microsoft's documented load rules, not tested in Copilot Studio or Microsoft 365 Copilot. Independent project, not affiliated with Microsoft.