Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Huawei Cloud Cost Estimation · ontology-of-everything | DecimalAI

devopsby ontology-of-everything

Huawei Cloud Cost Estimation

ontology-of-everything/huawei-cloud-cost-estimation

Source ontology-of-everything/semanticskills ↗License Apache-2.0

Generate Huawei Cloud pre-order price estimates, safely provision allowlisted resources via hcloud, and guide unsubscribe requests to the console only.

SkillScore70Maintained

Automatic

DevOps & SRE pack

Last verified 8/30/2026

What it changes

Passed 13 of 18 test cases with the skill, and 4 of 18 without it.

Without skill22%

With skill70%

Checks it passed that the model alone missed

Avoids GFM Markdown table syntax in the response output.
Presents 2 to 4 candidate options for missing parameters.
Refuses to execute Huawei Cloud CLI tools for AWS requests.

and 18 more in the full report

12 fixed4 passed either way6 still failing1 broke

Pass-rate lift: +48 pp
Tokens: +80%
Agent turns: 0%
Response time: +23%

Model gemini-3.6-flashMeasured 8/30/2026v316 of 23 cases passed with skill · 18 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ontology-of-everything-huawei-cloud-cost-estimation/SKILL.md https://app.decimal.ai/s/ontology-of-everything-huawei-cloud-cost-estimation/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ontology-of-everything-huawei-cloud-cost-estimation, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ontology-of-everything-huawei-cloud-cost-estimation/ and pins it in .decimal/skills.lock

decimalai skills add ontology-of-everything-huawei-cloud-cost-estimation

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ontology-of-everything-huawei-cloud-cost-estimation/SKILL.md https://app.decimal.ai/s/ontology-of-everything-huawei-cloud-cost-estimation/SKILL.md

Raw file: /s/ontology-of-everything-huawei-cloud-cost-estimation/SKILL.md ↗ · machine-readable summary at /s/ontology-of-everything-huawei-cloud-cost-estimation.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

Calculate the monthly cost for 1 c6.xlarge.2 instance (4 vCPU, 8GB) in Beijing 4 region at ¥300/month and 1 100GB EVS disk at ¥50/month. Show the final calculated total cost output.

What was checked, without and with the skill
Checked	Without skill	With skill
Formats individual itemized cost lines with service, spec, region, quantity, duration, and calculated price.	Missed	Passed
Calculates the total price as the sum of the individual itemized costs.	Passed	Passed

case-17 · gemini-3.6-flash · 8/30/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md71 lines3 files

华为云成本估算与资源开通

华为社区版 · 社区维护，非华为云官方；结论以当次 hcloud 响应为准。

价格只认当次响应，不臆造、不类比、不记忆；仅开通可写，退订只指引官网控制台。

Route

询价 / 预算 / 比价 → Pricing。
开通 / 购买 / 创建资源 → Lifecycle Create（仅 references/lifecycle/commands.md 白名单内）。
退订 / 停止使用资源 → Unsubscribe Guidance（仅控制台指引，不调用 CLI/API）。
历史账单/余额/对账 → 费用中心或 BSS 账单只读 API；非华为云 → 拒绝；白名单外写操作 → 给控制台指引。

Execution Pace

预计不超过 3 条 hcloud 时直达下一安全门禁；超过 3 条时每轮只执行 2–3 条（复用/并行只读/合并询价），说明已完成与下一步并友好询问是否继续。用户要求一次完成可连续执行；澄清、未知费用、--dryrun、写入确认不跳过。

Pricing

Parse — 抽取四元组 cloud_service_type / resource_type / region / resource_spec + 周期或使用量；读 references/pricing/semantic/catalog.yml 路由 period / on-demand。
Clarify — 缺 region/数量/周期或用量/线性 size，或类目模糊、多变种未定 → 停下一轮问完（2–4 候选）。仅 safe-default 缺失（OS=linux、AZ=空、fee_installment_mode=NA）→ 披露后继续。口语四元组确认，不暴露内部名。
Query — 按 Execution Pace 与 references/pricing/commands.md： ListServiceResources → ListResourceSpecs → 按需 ListUsageTypes(--resource_type_code) → Measure Resolve → 询价。多候选则问；Specs 命中仍可能失败；禁默认 Duration、禁容量槽/用量槽混用。
Verify & Present — 分项加和=总价；币种/周期/数量对齐。分项 [服务] [规格] [region] [数量×周期] = ¥<金额> + 加总 + 「非最终账单」；默认官网价，有折扣才附折后。

Lifecycle Create

读 references/lifecycle/concepts.md 后按序执行，跳步即违规：

Allowlist — 意图映射到 references/lifecycle/commands.md 命令主体；未命中即拒绝。
Help — hcloud <Service> <Operation> --help 取必填/条件必填；[APIE_ERROR] 或无 schema 即停止，不猜参数。
Resolve — 跑必要只读依赖（VPC/子网/AZ/镜像/规格等）；多候选让用户选，缺失项一轮问完；长链按 Execution Pace 交付。
Cost — 能询价先走 Pricing 回表；不能询价则声明「价格未知且可能收费」并取得额外确认。
Dry — 完整命令强制加全局 --dryrun（本地构造请求，非接口级 dry_run）；失败则修正重跑，不得转正式。
Confirm — 回显资源/region/规格/数量/计费/金额或未知费用/批次顺序，等用户明确确认。
Execute — 仅移除 --dryrun，其余不变；多命令顺序执行、失败即停、不自动回滚，报告成功/失败/未执行。

任何参数、region、数量或 operation 变化 → dry 与确认作废，回到 Help 重来。

Track record

Benchmark

13 / 18

test cases passed, vs 4 / 18 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v5 — 8/30/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ontology-of-everything / semanticskills

skills/huawei-cloud-cost-estimation/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/30/2026Version v3Bundled 2 files

More skills from the same source and nearby in the registry, with their headline benchmark lift.