SKILLEMALL.ai
GitHub ↗ RU Sign in

BC research-paper-writing

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

NousResearch/hermes-agent Hermes author: NousResearch MIT 18 files body ≈ 17 680 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Write ML papers for NeurIPS/ICML/ICLR: design→submit.

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

GeneratorLaTeXResearchSoftware developmentInfrastructuretype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
B
86/100
safety, quality, tests
Safety 60%
98
Quality 40%
69
Run on models
none yet
Process rating
C
54/100
Has gaps
Inputs and preconditions w 11
0
Execution cost w 6
10
Running it twice w 4
30
the three weakest of ten parameters · all ten

How to improve

  1. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
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 · 2

✓ No critical or high findings

Medium and low: 2
  • low Secrets in code secret-high-entropy-token SKILL.md:340
    High-entropy token-like string (may be an id, hash or a credential) (placeholder value)
    \cite{PLAC…his}  % TODO: Verify this citation exists
    placeholder
  • low Dangerous commands cmd-background-process SKILL.md:479
    Starts a background / autostarted process
    nohup python run_experiment.py --config config.yaml > logs/expe…log 2>&1 &

Files scanned: 18. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 17680 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 54/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 10Execution cost. Instruction body is 17680 tokens: crowds the task out of the window
  • 30Running it twice. 26 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 50When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, web, git, python) that frontmatter does not declare
  • 60Consistency. The Hermes dialect needs category and tags
  • 85Steps. 160 steps, 3 vague phrases
  • 100Failures and branches. 1 branches, has a failure section
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 18 top-level sections: this looks like several domains in one skill

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 53: 120–800 characters recommended
  • +3Output format is not stated: the model decides each time
  • -5TODO / placeholder text left in the skill
  • +2Single-language instructions
  • +4Structure: 89 headings
  • +3Step-by-step instructions: 160 items
  • +4Has examples (56 code blocks)
  • +4Reference files are cited in the instructions (10 of 10)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 69.