DB huawei-cloud-ecs-manage
Use when managing Huawei Cloud ECS (Elastic Cloud Server / 弹性云服务器) instances — lifecycle management (create / start / stop / restart / delete), instance querying, quota/flavor/image inspection, and multi-step root-cause diagnosis of ECS instance creation failures (quota → flavor → image → network → keypair → disk). Provides 12 huawei_* actions: huawei_list_ecs_instances, huawei_get_ecs_instance, huawei_list_ecs_flavors, huawei_list_ecs_images, huawei_list_ecs_quotas, huawei_diagnose_ecs_create_failure, huawei_analyze_ecs_health, huawei_create_ecs_instance, huawei_start_ecs_instance, huawei_stop_ecs_instance, huawei_restart_ecs_instance, huawei_delete_ecs_instance. Service keywords: ECS, elastic cloud server, instance, VM, server, flavor, image, quota, keypair, security group, subnet, EIP, 云服务器, 弹性云服务器, 实例, 规格, 镜像, 配额, 密钥对, 安全组, 子网, 创建失败, 启动, 停止, 重启, 删除. Triggers include: "ECS 创建失败", "云服务器创建失败", "创建云主机失败", "ECS 创建不了", "create ECS failed", "instance creation failed", "创建云服务器", "启动云服务器", "停止云服务器", "重启云服务器", "删除云服务器", "ECS 规格", "ECS 配额", "ECS 镜像", "list ECS instances", "diagnose ECS", "ECS health", "ecs create diagnose".
Use when managing Huawei Cloud ECS (Elastic Cloud Server / 弹性云服务器) instances — lifecycle management (create / start / stop / restart / delete), instance…
As a process B 68/100 · Nearly there — weak spots: result and completion, when it triggers, 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
- Shorten the description to 1024 characters.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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
-
medium Dangerous commands
cmd-shell-rcscripts/ensure_cli.sh:19Writes to a shell startup fileecho 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
-
medium Dangerous commands
cmd-shell-rcscripts/ensure_cli.sh:22Writes to a shell startup fileecho 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.profile
-
medium Dangerous commands
cmd-shell-rcscripts/ensure_cli.sh:77Writes to a shell startup fileecho "PATH 已导出并持久化(~/.bashrc ~/.profile), 可直接执行: skill-quality-cli ..."
Files scanned: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1135 chars, limit 1024 - warning
body-longSKILL.md body ≈ 6053 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 68/100
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Result and completion. Does not say what the result is
- 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 6053 tokens
- 100Steps. 29 steps
- 100Failures and branches. 1 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 11 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (10 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)
- +3Description length 1134: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 18 example trigger phrases
- +4Structure: 18 headings
- +3Step-by-step instructions: 29 items
- +4Has examples (17 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: 58.