SKILLEMALL.ai
GitHub ↗ RU Sign in

CB alibabacloud-ebs-disk-snapshot-management

This skill should be used when the user asks about Alibaba Cloud ECS disk snapshots, including creating snapshots, listing snapshots, deleting snapshots, rolling back disks, configuring auto snapshot policies, calculating snapshot costs, managing snapshot lifecycle, or using snapshot consistency groups for crash-consistent backup of an entire instance. Triggers on phrases like "create ECS snapshot", "query snapshot list", "delete snapshot", "rollback disk", "auto snapshot policy", "snapshot cost", "snapshot consistency group", "crash-consistent backup", "consistency backup", or Chinese equivalents "创建快照", "查询快照列表", "删除快照", "回滚云盘", "自动快照策略", "快照费用", "快照一致性组", "一致性备份", "整机备份", "崩溃一致性备份", "整机崩溃一致性备份", and broader ECS disk maintenance intents such as "帮我处理一下 ECS 实例", "给云盘做备份", "ECS 云盘运维".

Not recommendedcritical or high security findings
ClawHub Agent Skills author: alibabacloud-skills-team v0.0.1 MIT-0 13 files · 4 scripts body ≈ 17 504 tokens Open the sourceclawhub.ai↗ analyzed 14 d ago

This skill should be used when the user asks about Alibaba Cloud ECS disk snapshots, including creating snapshots, listing snapshots, deleting snapshots…

As a process B 70/100 · Nearly there — weak spots: result and completion, execution cost, running it twice

ProcedureInfrastructureAI and agentsWriting and documentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
84/100
safety, quality, tests
Safety 60%
82
Quality 40%
86
Run on models
none yet
Process rating
B
70/100
Nearly there
Execution cost w 6
10
Running it twice w 4
30
Result and completion w 14
40
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

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.

For the author

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

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. 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 · 1

  • high Dangerous commands cmd-pipe-to-shell references/cli-installation-guide.md:23
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL https://aliyuncli.alicdn.com/setup.sh | bash

Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 17504 tokens (recommended < 5000); move details to references/
  • note edit-residue the text marks something as outdated (lines 331): check that old rules are not kept next to new ones — the full check reads the text for contradictions

Process rating: all ten parameters 70/100

  • 10Execution cost. Instruction body is 17504 tokens: crowds the task out of the window
  • 30Running it twice. 147 mutating operations with no state check
  • 40Result and completion. Does not say what the result is
  • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
  • 70When it triggers. States when to use, but not when not to
  • 85Steps. 142 steps, 3 vague phrases
  • 100Inputs and preconditions. Inputs and preconditions are listed
  • 100Failures and branches. 18 branches, has a failure section
  • 100Consistency. Name and required fields are in place
  • 100Progress reporting. Reports progress
  • low 19 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

  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +5Description quotes 17 example trigger phrases
  • +3Description length 795: enough signal without eating the budget
  • +4Structure: 38 headings
  • +3Step-by-step instructions: 142 items
  • +4Has examples (2 code blocks)
  • +4Reference files are cited in the instructions (7 of 7)
  • +3All 4 scripts are documented

Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.

External checks

ClawHub: suspicious
The skill is mostly coherent for Alibaba Cloud snapshot management, but it includes one network-troubleshooting instruction that may bypass configured proxy controls in a high-impact cloud-operations context.
LLM: suspicious (medium) · VirusTotal: · 30 Jul 2026