AF train-style-model
Fine-tune a reusable brand, style, or character model (a LoRA) from a small set of reference images, then generate on-brand imagery from any prompt. Use when the user says "train a model on our brand style", "make a LoRA from these images", "fine-tune on our look", "a custom model that draws in our style", or "consistent illustrations at scale". An async training job, not one-shot generation. To upload a model you already trained elsewhere, use bring-your-own-model. For same-identity output without training, use character-consistency.
Fine-tune a reusable brand, style, or character model (a LoRA) from a small set of reference images, then generate on-brand imagery from any prompt.
As a process F 56/100 · Will not run — References files that are not bundled: references/examples.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: 0. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/examples.md
Process rating: all ten parameters 56/100
- 0Tools and files. 1 referenced file(s) missing: references/examples.md
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 1 mutating operations with no state check
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 30 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1564 tokens
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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +4No input/output examples
- +1No license
- +2Single-language instructions
- +5Description quotes 5 example trigger phrases
- +3Description length 540: enough signal without eating the budget
- +4Structure: 8 headings
- +3Step-by-step instructions: 30 items
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.