SKILLEMALL.ai
GitHub ↗ RU Sign in

BC unsloth

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

NousResearch/hermes-agent Hermes author: NousResearch MIT 3 files body ≈ 473 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Unsloth: 2-5x faster LoRA/QLoRA fine-tuning, less VRAM.

As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureSoftware developmenttype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
B
89/100
safety, quality, tests
Safety 60%
99
Quality 40%
73
Run on models
none yet
Process rating
C
54/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • low Secrets in code secret-high-entropy-token references/llms.md:44
      High-entropy token-like string (may be an id, hash or a credential)
      - [Qwen…er: How to Run Locally](/models/qwen3-coder-how-to-run-locally.md): Run Qwen…uct and 480B-A35B locally with Unsloth Dynamic quants.

    Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    • note frontmatter-key unknown frontmatter key "dependencies"

    Process rating: all ten parameters 54/100

    • 0Result and completion. Does not say what the result is
    • 0Inputs and preconditions. Does not say what the process needs to start
    • 0Failures and branches. Linear process with no failure handling
    • 0Progress reporting. Says nothing while it works
    • 60Consistency. The Hermes dialect needs category and tags
    • 70When it triggers. States when to use, but not when not to
    • 85Steps. 16 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Execution cost. Instruction body is 473 tokens
    • 100Running it twice. No mutating operations

    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)
    • +3Description length 55: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • +4No input/output examples
    • -42 reference files, but SKILL.md never points to them: the model will not open them
    • +2Single-language instructions
    • +4Structure: 15 headings
    • +3Step-by-step instructions: 16 items
    • +1License stated

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.