CC hugging-face-model-trainer
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on 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, and model persistence. Should be invoked for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
This skill should be used when users want to train or fine-tune language models using TRL (Transformer Reinforcement Learning) on Hugging Face Jobs…
As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, running it twice
How to improve
- For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-long-hermesdescription is 629 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period) - warning
body-longSKILL.md body ≈ 6682 tokens (recommended < 5000); move details to references/ - note
frontmatter-keyunknown frontmatter key "dependencies"
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 19 mutating operations with no state check
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 60Steps. 137 steps, 5 vague phrases
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 6682 tokens
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 21 top-level sections: this looks like several domains in one skill
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- -215 emoji in the instructions: noise for the model
- +2Single-language instructions
- +3Description length 629: enough signal without eating the budget
- +4Structure: 56 headings
- +3Step-by-step instructions: 137 items
- +4Has examples (26 code blocks)
- +4Reference files are cited in the instructions (7 of 8)
- +3All 6 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.