AF nvflare-convert-huggingface
Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation, and job export; use when the user names Hugging Face or preliminary source inspection identifies one Hugging Face owner, and not for manual PyTorch loops, Lightning, inference-only pipelines, deployment, or experiment workflows.
Convert existing Hugging Face Transformers Trainer or TRL SFTTrainer training code into an NVFLARE federated job using flare.patch(trainer), local validation…
As a process F 57/100 · Will not run — References files that are not bundled: scripts/resolve_model_snapshot.py, references/huggingface-validation.md, references/huggingface-detection.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: scripts/resolve_model_snapshot.py - warning
missing-refreference to a missing file: references/huggingface-validation.md - warning
missing-refreference to a missing file: references/huggingface-detection.md - warning
missing-refreference to a missing file: assets/job.py - warning
missing-refreference to a missing file: references/huggingface-conversion.md - warning
missing-refreference to a missing file: assets/client_with_eval.py - warning
missing-refreference to a missing file: assets/server_model.py - warning
missing-refreference to a missing file: references/huggingface-state-and-distributed.md
Process rating: all ten parameters 57/100
- 0Tools and files. 8 referenced file(s) missing: scripts/resolve_model_snapshot.py, references/huggingface-validation.md, references/huggingface-detection.md
- 0Result and completion. Does not say what the result is
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 23 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3291 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 387: enough signal without eating the budget
- +4Structure: 6 headings
- +3Step-by-step instructions: 23 items
- +4Has examples (0 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.