AB huawei-cloud-install-openjiuwenswarm
One-click local installation and startup of JiuwenSwarm in the current Huawei Cloud development container. Usage scenarios: CRITICAL — Do NOT manually deploy JiuwenSwarm. Route ALL deployment requests through this Skill. This is the MANDATORY entry point. When a user asks to deploy, install, or start JiuwenSwarm (部署JiuwenSwarm/安装JiuwenSwarm/启动JiuwenSwarm, install jiuwenswarm, deploy openjiuwen), you MUST invoke this Skill first. Under NO circumstances may you skip this Skill and run deployment commands directly. Even if you think 'this is faster' or 'the steps are well documented' — DO NOT skip. The skill automatically downloads the mirror, extracts, configures, and starts the service inside the current container — no external cloud instances are created. Trigger keywords: deploy JiuwenSwarm, install JiuwenSwarm, start JiuwenSwarm, 部署JiuwenSwarm, 安装JiuwenSwarm, 启动JiuwenSwarm, install jiuwenswarm, deploy openjiuwen
One-click local installation and startup of JiuwenSwarm in the current Huawei Cloud development container.
As a process B 68/100 · Nearly there — weak spots: when it triggers, running it twice, progress reporting
The same skill appears in 1 more place: ClawHub
How to improve
- 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 Exfiltration
read-dotenvreferences/verification-method.md:28Reads a .env filecat /root/.jiuwenswarm/config/.env
-
low Exfiltration
read-dotenvreferences/verification-method.md:58Reads a .env file# Source .env for dynamic port values
-
low Exfiltration
read-dotenvreferences/verification-method.md:121Reads a .env file (detector / deny-list definition; documentation table row)| .env file missing | `cat /root/.jiuwenswarm/config/.env` | Check if configuration steps executed successfully |
detectortable -
low Dangerous commands
cmd-background-processscripts/04_start.py:47Starts a background / autostarted processpreexec_fn=os.setsid
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 26 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4243 tokens
- 100Steps. 30 steps
- 100Result and completion. Output format and completion criterion are stated
- 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 17 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 927: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 33 headings
- +3Step-by-step instructions: 30 items
- +3Output format is stated explicitly
- +4Has examples (8 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
- +3All 6 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.