SKILLEMALL.ai

AB huawei-cloud-flexus-l-deploy-jiuwenswarm

One-click deployment of JiuwenSwarm multi-Agent collaboration platform on Huawei Cloud Flexus L instances. Usage scenarios: When users need to quickly deploy JiuwenSwarm/JiuwenClaw on Huawei Cloud Flexus L instances, when they need to automatically create cloud instances and deploy AI Agent platforms, when they need to configure model APIs and message channels (Xiaoyi/Feishu/DingTalk). Automatically create instances, deploy applications via COC, configure models and message channels. Trigger keywords: JiuwenSwarm deployment, JiuwenClaw deployment, 九问Swarm部署, 九问Claw部署, 一键部署JiuwenSwarm, AI智能体平台部署, 部署九问Swarm, 部署九问Claw,云服务器部署AI平台.

ClawHub Agent Skills author: huaweicloud-skills-team v1.0.2 MIT-0 22 files · 1 script body ≈ 5 174 tokens Open the sourceclawhub.ai analyzed 2 d ago

One-click deployment of JiuwenSwarm multi-Agent collaboration platform on Huawei Cloud Flexus L instances.

As a process B 71/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting

IntegrationAI and agentstype and topics are labelled automatically from the skill text
JSON
Technical rating
A
91/100
safety, quality, tests
Safety 60%
96
Quality 40%
84
Run on models
none yet
Process rating
B
71/100
Nearly there
Progress reporting w 2
0
When it triggers w 12
20
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 · 4

✓ No critical or high findings

Medium and low: 4
  • low Dangerous commands cmd-background-process assets/deploy_script_template.sh:227
    Starts a background / autostarted process
    systemctl enable jiuwenswarm
  • low Exfiltration read-dotenv references/troubleshooting.md:133
    Reads a .env file
    cat /opt/jiuwenswarm-env/jiuwenswarm/.env
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/install_deps.py:482
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    curl -fsSL https://deb.nodesource.com/setup_18.x | bash -
    code literal
  • low Dangerous commands cmd-pipe-to-shell-known-host scripts/install_deps.py:488
    Pipe-to-shell installer from a well-known host (still executes remote code) (string literal in code, not executed)
    curl -fsSL https://deb.nodesource.com/setup_18.x | bash -
    code literal

Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 5174 tokens (recommended < 5000); move details to references/

Process rating: all ten parameters 71/100

  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 30Running it twice. 32 mutating operations with no state check
  • 60Tools and files. Uses tools (bash, web, python) that frontmatter does not declare
  • 70Inputs and preconditions. Inputs and preconditions are listed
  • 70Execution cost. Instruction body is 5174 tokens
  • 85Steps. 89 steps, 2 vague phrases
  • 100Result and completion. Output format and completion criterion are stated
  • 100Failures and branches. 1 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low 14 top-level sections: this looks like several domains in one skill
  • low The response is described with custom markup (4 tags): a typed call is more reliable

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)
  • +1No license
  • +2Single-language instructions
  • +3Description length 634: enough signal without eating the budget
  • +4Structure: 48 headings
  • +3Step-by-step instructions: 89 items
  • +3Output format is stated explicitly
  • +4Has examples (12 code blocks)
  • +4Reference files are cited in the instructions (6 of 6)
  • +3All 9 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

External checks

ClawHub: suspicious
This looks like a real Huawei Cloud deployment skill, but it needs Review because it weakens stored cloud credentials and handles secrets, public access, and root cloud execution in risky ways.
LLM: suspicious (high) · 29 Aug 2026