SKILLEMALL.ai
GitHub ↗ RU Sign in

BF moe-training

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.

synthetic-sciences/OpenScience Hermes author: synthetic-sciences Apache-2.0 4 files body ≈ 3 554 tokens Open the sourcegithub.com↗ analyzed 5 d ago

Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace.

As a process F 33/100 · No process to follow — References files that are not bundled: expert_input

GeneratorAI and agentstype and topics are labelled automatically from the skill text
Runs in: Hermes Agent
JSON
Technical rating
B
90/100
safety, quality, tests
Safety 60%
99
Quality 40%
76
Run on models
none yet
Process rating
F
33/100
No process to follow
References files that are not bundled: expert_input
Tools and files w 18
0
Result and completion w 14
0
Inputs and preconditions w 11
0
the three weakest of ten parameters · all ten

How to improve

  1. For Hermes the description must be one sentence under 60 characters; move the conditions to a "When to Use" section.
  2. The text references files that are not there: add them or drop the references.
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/architectures.md:321
    High-entropy token-like string (may be an id, hash or a credential)
    class Swit…ter(nn.Module):

Files scanned: 4. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 407 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)
  • warning missing-ref reference to a missing file: expert_input
  • note frontmatter-key unknown frontmatter key "dependencies"

Process rating: all ten parameters 33/100

Will not run. References files that are not bundled: expert_input
  • 0Tools and files. 1 referenced file(s) missing: expert_input
  • 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
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 1 mutating operations with no state check
  • 100Steps. 18 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 3554 tokens
  • low 10 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)
  • +3Output format is not stated: the model decides each time
  • +2Single-language instructions
  • +3Description length 407: enough signal without eating the budget
  • +4Structure: 27 headings
  • +3Step-by-step instructions: 18 items
  • +4Has examples (20 code blocks)
  • +4Reference files are cited in the instructions (3 of 3)
  • +1License stated

Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.