AB alibabacloud-lingjun-cluster-manage
What it does: manages Alibaba Cloud Lingjun cluster lifecycle via eflo-controller CLI — create / list / describe / delete clusters, list nodes, query machine types & images, tag / untag / list tags, change resource group. When to use it: when the user asks to create, query or delete a Lingjun cluster, list clusters or nodes, look up machine types or images, manage cluster tags, or change its resource group. Run: bash prefix: export LJ_SKILL_DIR="${LJ_SKILL_DIR:-$HOME/.qoder/skills/alibabacloud-lingjun-cluster-manage}" && source "$LJ_SKILL_DIR/lib/lj_init.sh"; i18n: CJK ratio 0.30+ → LJ_LANG=zh else en; stdout (skip ===...=== envelope blocks) is final reply; __LJ_EXEC__ or [Widget interaction] prefix → confirmed → one && chain. Triggers: "lingjun cluster", "灵骏集群", "create cluster", "创建集群", "delete cluster", "删集群", "list clusters", "describe cluster", "查集群", "machine type", "机型", "image", "镜像", "tag", "打标", "untag", "解标", "查标", "resource group", "资源组", "移资源组", "改资源组", "GPU", "CUDA", "集群管理", "cluster lifecycle"
What it does: manages Alibaba Cloud Lingjun cluster lifecycle via eflo-controller CLI — create / list / describe / delete clusters, list nodes, query machine…
As a process B 66/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
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 · 2
✓ No critical or high findings
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shellreferences/cli-installation.md:18Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| macOS / Linux x86_64 | `curl -fsSL --connect-timeout 10 --max-time 120 https://aliyuncli.alicdn.com/setup.sh \| bash` |
table -
low Dangerous commands
cmd-privilegereferences/cli-installation.md:19Privilege escalation / world-writable permissions (documentation table row)| Linux ARM64 | `wget https://aliyuncli.alicdn.com/aliy…tgz && tar -xzf aliy…tgz && sudo mv aliyun /usr/local/bin/` |
table
Files scanned: 9. 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 66/100
- 0Result and completion. Does not say what the result is
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 27 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 100Steps. 22 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3408 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (15 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
- +3Description length 1023: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 10 headings
- +3Step-by-step instructions: 22 items
- +4Has examples (4 code blocks)
- +4Reference files are cited in the instructions (5 of 5)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 97.