SKILLEMALL.ai
RU Sign in

AB huawei-cloud-flexus-l-server-hermes-deployment

One-click deployment tool for Hermes on Huawei Cloud Flexus L instances. Supports one-click deployment, ModelArts large model configuration, and robot channel configuration. This skill provides a complete workflow for deploying and configuring Hermes AI Agent platform. Trigger words: "Deploy Hermes", "Install Hermes", "Configure Model", "Configure Channel", "部署Hermes", "安装Hermes", "配置大模型", "配置机器人通道"

ClawHub Hermes author: huaweiclouddev-dev v1.0.0 MIT-0 14 files body ≈ 4 146 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 69/100 · Nearly there — weak spots: when it triggers

ProcedureInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Hermes Agent
JSON
Technical rating
A
90/100
safety, quality, tests
Safety 60%
97
Quality 40%
79
Run on models
none yet
Process rating
B
69/100
Nearly there
When it triggers w 12
20
Tools and files w 18
60
Result and completion w 14
60
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ClawHub

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 · 3

✓ No critical or high findings

Medium and low: 3
  • low Dangerous commands cmd-privilege scripts/lib.py:345
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    sudo curl -sL https://github.com/mikefarah/yq/releases/download/v4.35.1/yq_l…d64 -o /usr/local/bin/yq
    code literal
  • low Dangerous commands cmd-privilege scripts/lib.py:347
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    sudo wget -qO /usr/local/bin/yq https://github.com/mikefarah/yq/releases/download/v4.35.1/yq_l…d64
    code literal
  • low Dangerous commands cmd-privilege scripts/lib.py:349
    Privilege escalation / world-writable permissions (string literal in code, not executed)
    sudo chmod +x /usr/local/bin/yq
    code literal

Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-long-hermes description is 403 chars; the Hermes authoring standard requires ≤ 60 (one sentence, ending with a period)

Process rating: all ten parameters 69/100

  • 20When it triggers. No condition that starts the skill
  • 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
  • 60Result and completion. Output format stated, no completion criterion
  • 60Consistency. The Hermes dialect needs category and tags
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 4146 tokens
  • 100Steps. 81 steps
  • 100Failures and branches. 2 branches, has a failure section
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • 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

  • +4Description does not say when NOT to use the skill (false activations)
  • -42 reference files, but SKILL.md never points to them: the model will not open them
  • -33 of 9 scripts are never mentioned in SKILL.md
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 7 example trigger phrases
  • +3Description length 402: enough signal without eating the budget
  • +4Structure: 43 headings
  • +3Step-by-step instructions: 81 items
  • +3Output format is stated explicitly
  • +4Has examples (16 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.

External checks

ClawHub: suspicious
The skill matches its Hermes deployment purpose, but it uses powerful cloud credentials to create paid auto-renewing resources, run remote root scripts, and handle secrets in ways users should review carefully.
LLM: suspicious (high) · 3 Aug 2026