huggingface-llm-trainer

Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.

Agent Skill from huggingface/skills

Copilot Studio

Passes documented load rules

No documented load rule failed.

Microsoft 365 Copilot Preview, Frontier tenants only

Needs changes

Fails: Instructions are under 20,000 characters (M365-INSTRUCTIONS)
instructions are 27,947 characters
rule · Microsoft 365 Copilot: What is a skill

Warnings (don't change the verdict):

Warning: No sign of network access, package installs or authenticated calls (M365-SANDBOX)
scripts: scripts/convert_to_gguf.py (system package install); scripts/dataset_inspector.py (Python HTTP client, fetch()); scripts/hf_benchmarks.py (Python HTTP client, credentials / authenticated call)
rule · Microsoft 365 Copilot: Script execution sandbox

An agent can have at most 8 skills. Custom skills aren't available in tenants that use Microsoft Purview Information Barriers.

Compatible isn't the same as safe. These verdicts only say whether a skill's files follow Microsoft's documented load rules. The checker reads files and never runs them, and it doesn't review what a skill or its scripts actually do. Read a skill's instructions and scripts before you add it to an agent.

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 (`huggingface-llm-trainer`) 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	huggingface/skills
Path	skills/huggingface-llm-trainer/SKILL.md
Commit checked	`c3ff942be3e0`
Repo license	Apache-2.0
Files	19
Scripts	8 (8 scanned for the sandbox heuristic)
Instructions	27,947 characters
Deepest folder	1 below the skill folder
Rules version	2026-10-22

Re-check the latest version How skill checks work

Is this wrong or out of date? Email us. Skills data built 2026-10-23; rules as of 2026-10-22.

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.