CB huawei-cloud-sg-manage
Use when managing or diagnosing Huawei Cloud security groups (安全组) — VPC subnet-level firewalls. Covers listing/querying security groups and rules, port connectivity diagnosis (ingress/egress rule matching), rule conflict detection, over-exposure security audit (e.g. 0.0.0.0/0 world-open rules), and full CRUD (create/update/delete security groups and rules). Managed actions run with preview + explicit confirmation (R2/R1); query and diagnose actions are read-only and auto-execute (R3). Uses the local hcloud (KooCLI) VPC CLI with AK/SK environment variables or a local hcloud profile. Provides 11 huawei_* actions: huawei_list_security_groups, huawei_list_security_group_rules, huawei_get_security_group, huawei_diagnose_sg_port_connectivity, huawei_analyze_sg_rule_conflict, huawei_audit_sg_overexposed_rules, huawei_create_security_group, huawei_create_sg_rule, huawei_update_security_group, huawei_delete_security_group, huawei_delete_sg_rule. Triggers include: "安全组", "安全组规则", "防火墙规则", "端口连通性", "端口诊断", "规则冲突", "过度开放", "全开放", "0.0.0.0/0", "security group", "security group rule", "SG rule", "ingress", "egress", "inbound", "outbound", "port connectivity", "port diagnosis", "rule conflict", "over-exposed", "world-open", "VPC", "安全审计", "防火墙".
Covers listing/querying security groups and rules, port connectivity diagnosis (ingress/egress rule matching), rule conflict detection, over-exposure security…
As a process B 66/100 · Nearly there — weak spots: result and completion, progress reporting
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 · 0
✓ No critical or high findings
Files scanned: 22. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1252 chars, limit 1024 - warning
body-longSKILL.md body ≈ 5347 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 66/100
- 0Progress reporting. Says nothing while it works
- 40Result and completion. Does not say what the result is
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 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 5347 tokens
- 100Steps. 32 steps
- 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 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (3 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 1251: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -31 of 3 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +5Description quotes 13 example trigger phrases
- +4Structure: 24 headings
- +3Step-by-step instructions: 32 items
- +4Has examples (13 code blocks)
- +4Reference files are cited in the instructions (5 of 6)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.