SKILLEMALL.ai

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.

ClawHub Agent Skills author: Manoj Bhat v1.2.0 MIT-0 7 files · 1 script body ≈ 1 500 tokens Open the sourceclawhub.ai analyzed 3 d ago

As a process B 65/100 · Nearly there — weak spots: result and completion, consistency, progress reporting

ProcedureAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
97/100
safety, quality, tests
Safety 60%
100
Quality 40%
92
Run on models
none yet
Process rating
B
65/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
Consistency w 8
40
the three weakest of ten parameters · all ten

How to improve

    For the model run — optional
    • 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.

    External checks

    ClawHub: suspicious
    This skill has a coherent document-to-model purpose, but installation and checkpoint loading create real review-worthy supply-chain and unsafe-deserialization risks.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026