AB doc-to-lora
Internalize a document into a small language model (Gemma 2 2B) using Doc-to-LoRA so it can answer questions WITHOUT the document in the prompt. Use when the user wants to: feed a document to a local model, internalize knowledge from a file or URL, create a LoRA adapter from a document, answer questions from a document using a small on-device model, or run knowledge-grounded inference on a Mac. Also use when asked about Doc-to-LoRA, HyperLoRA, or document internalization.
As a process B 65/100 · Nearly there — weak spots: result and completion, consistency, progress reporting
How to improve
- 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: 7. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 65/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (doc-to-lora) differs from the folder (doc-to-lora-hyper)
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 13 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Execution cost. Instruction body is 1500 tokens
- 100Running it twice. Mutating operations check current state
- 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
- +4Description does not say when NOT to use the skill (false activations)
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +3Description length 476: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 13 items
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 3 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 92.