SKILLEMALL.ai
GitHub ↗ RU Sign in

CC axolotl

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

synthetic-sciences/OpenScience Hermes author: synthetic-sciences Apache-2.0 5 files body ≈ 1 094 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

As a process C 50/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
C
84/100
safety, quality, tests
Safety 60%
86
Quality 40%
82
Run on models
none yet
Process rating
C
50/100
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

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Obfuscation medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

Dangerous commands medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
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 · 6

✓ No critical or high findings

Medium and low: 6
  • medium Obfuscation obf-base64-blob references/api.md:3241
    Long base64-looking blob
    This implementation is based on the Vicuna PR and the fastchat repo, see also: https://github.com/lm-sys/FastChat/blob/cdd7…4f3/fastchat/conversation.py#L847
  • medium Dangerous commands cmd-pipe-to-shell-known-host references/other.md:310
    Pipe-to-shell installer from a well-known host (still executes remote code)
    curl -LsSf https://astral.sh/uv/install.sh | sh
  • low Secrets in code secret-high-entropy-token references/api.md:3230
    High-entropy token-like string (may be an id, hash or a credential)
    - LLam…egy
  • low Secrets in code secret-high-entropy-token references/api.md:4907
    High-entropy token-like string (may be an id, hash or a credential)
    - Batc…Seq
  • low Secrets in code secret-high-entropy-token references/api.md:4910
    High-entropy token-like string (may be an id, hash or a credential)
    - Pret…Seq
  • low Secrets in code secret-high-entropy-token references/api.md:4911
    High-entropy token-like string (may be an id, hash or a credential)
    - V2Ba…Seq

Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 128 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 50/100

  • 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
  • 60Tools and files. Uses tools (python) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 18 steps, 1 vague phrases
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 1094 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)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 128: enough signal without eating the budget
  • +4Structure: 16 headings
  • +3Step-by-step instructions: 18 items
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (3 of 4)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.