Huawei Cloud Cost Estimation logo

Huawei Cloud Cost Estimation

Organization
huaweicloud
huawei-cloud-cost-estimation

Generates Huawei Cloud pre-order estimates, provisions allowlisted resources through hcloud, and routes unsubscribe requests to console guidance. Use for Huawei Cloud pricing, budgets, creation, provisioning, or unsubscribe. Creates require runtime help, --dryrun, fee review, and confirmation. Never emits or runs unsubscribe operations, accepts credentials, or performs non-allowlisted writes. Triggers include: "华为云报价", "报价", "价格估算", "费用预估", "比价", "询价", "开通报价", "创建报价", "华为云价格", "价格查询", "预算评估", "费用计算", "price estimate", "cost estimation", "budget", "quote", "pricing", "provision", "create", "purchase", "价格", "费用", "华为云多少钱".

Overview

Publisherhuaweicloud
Repositoryhuaweicloud-skills
Skill namehuawei-cloud-cost-estimation
Stars
59
Forks
24
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by huaweicloud on GitHub. Read the source before you install it.

Installation

Install the Huawei Cloud Cost Estimation AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/huaweicloud/huaweicloud-skills/tree/master/skills/bss/billing/huawei-cloud-cost-estimation
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/huaweicloud/huaweicloud-skills.git /tmp/huaweicloud-skills
mkdir -p .claude/skills
cp -r /tmp/huaweicloud-skills/skills/bss/billing/huawei-cloud-cost-estimation .claude/skills/huawei-cloud-cost-estimation
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Huawei Cloud Cost Estimation in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Huawei Cloud Cost Estimation on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Huawei Cloud Cost Estimation is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Huawei Cloud Cost Estimation and Provisioning

Prices come only from the current response: never guess, analogize, or recall them. Provisioning is the only permitted write path; unsubscribe is console guidance only.

Overview

Estimates Huawei Cloud pre-order costs and, when the user wants to buy or create, provisions resources through an allowlisted hcloud command set, then routes unsubscribe requests to console guidance. Use when the user asks about Huawei Cloud / 华为云 / hcloud pricing, budgets, creation or provisioning in Chinese or English: 报价, 询价, 价格估算, 费用预估, 比价, 开通, 创建, price estimate, budget, quote, pricing, provision, create, purchase. Answer: how much a resource will cost, which spec/billing-mode combination fits, whether a resource can be provisioned, and how to unsubscribe — never by guessing prices, inventing parameters, or running non-allowlisted writes.

  • Pricing runs a 4-step RFQ flow (Parse → Clarify → Query → Verify & Present) over hcloud BSS read-only APIs in the fixed region cn-north-1.
  • Lifecycle Create is limited to the 74 allowlisted operations in references/lifecycle/commands.md and only after --help, fee review, --dryrun, and explicit confirmation.
  • Unsubscribe is console guidance only; no unsubscribe CLI/API is ever emitted or executed.

Prerequisites

Prerequisite check: Huawei Cloud CLI (hcloud) >= 7.2.2 and an authenticated profile with BSS read-only + lifecycle dependency IAM permissions (see references/iam-policies.md). hcloud BSS always uses the fixed region --cli-region=cn-north-1; the resource deploy region is carried inside each quote line's region field.

bash
hcloud version
hcloud configure list
hcloud BSS ListServiceTypes --cli-region=cn-north-1 --cli-output=json --limit=1

If not installed or authenticated, point the user to references/cli-installation-guide.md. Do NOT configure credentials on the user's behalf and do NOT accept AK/SK/token pasted in chat.

Environment dependency (BSS pricing chain): the price-inquiry chain (ListServiceTypes, ListServiceResources, ListResourceSpecs, ListUsageTypes, ListMeasureUnits, ListRateOnPeriodDetail, ListOnDemandResourceRatings) runs against the authenticated account's BSS (Business Support System) APIs. In sandboxed or restricted environments where BSS access is not provisioned (no service metadata, no executor mapping), the pricing chain cannot be verified end-to-end. In that case state clearly that prices cannot be queried in the current environment, then stop — never guess, estimate from memory, or fabricate amounts.

Scope

In scope

RequestHandling
Quote, budget, or comparisonPricing (4-step RFQ)
Provision, purchase, or createLifecycle Create, limited to references/lifecycle/commands.md
Unsubscribe or stop usingconsole-only Unsubscribe Guidance

Out of scope — route, don't execute

RequestRouting
Historical bills, balance, or reconciliation费用中心 or read-only BSS billing APIs (do not use this skill)
Non-Huawei cloud pricingrefuse politely
Non-allowlisted writesconsole guidance; never run them
AK/SK/token in chatpoint to references/cli-installation-guide.md
Remembering or guessing pricesprices only from the current hcloud response

Execution Pace

Complete chains of at most three hcloud commands directly to the next safety gate. For longer chains, run only two or three commands per round, report progress and the next step, then ask whether to continue. A user may request uninterrupted execution, but clarification, unknown-cost approval, --dryrun, and write confirmation remain mandatory.

Workflow

Pricing — 4-Step RFQ

  1. Parse cloud_service_type / resource_type / region / resource_spec plus period or usage; route through references/pricing/semantic/catalog.yml.
  2. Clarify missing region, quantity, duration/usage, linear size, ambiguous categories, or unresolved variants in one question with two to four candidates. Disclose and apply only safe defaults: OS=linux, empty AZ, and fee_installment_mode=NA.
  3. Query using references/pricing/commands.md: ListServiceResources → ListResourceSpecs → on-demand ListUsageTypes(--resource_type_code) → measure resolution → quotation. Ask on multiple matches; a spec match may still fail. Never invent duration or mix capacity and usage slots.
  4. Verify and present that line items sum to the total and currency, period, and quantity align. Present [service] [spec] [region] [quantity × period] = amount, total, and “not a final bill.” Show discounts only when returned.

Lifecycle Create — 7 Gates

Read references/lifecycle/concepts.md, then perform every gate in order:

  1. Allowlist — Map intent to an operation in references/lifecycle/commands.md; refuse misses.
  2. Help — Run hcloud <Service> <Operation> --help for required and conditional fields. Stop on [APIE_ERROR] or missing schema; never guess.
  3. Resolve — Run required read-only dependencies such as VPC, subnet, AZ, image, and flavor. Let the user choose among multiple matches.
  4. Cost — Use Pricing when possible. Otherwise disclose “price unknown and may incur charges” and obtain separate approval.
  5. Dry — Add global --dryrun to the complete command. Fix and rerun failures; never promote a failed dry run.
  6. Confirm — Show resource, region, spec, quantity, billing, known or unknown price, and batch order; wait for explicit confirmation.
  7. Execute — Remove only --dryrun. Run multiple commands in order, stop on failure, never auto-rollback, and report succeeded, failed, and unexecuted items.

Any parameter, region, quantity, or operation change invalidates the dry run and confirmation and returns to Help.

Unsubscribe Guidance

Never run or generate unsubscribe CLI/API operations, and never use --dryrun as a substitute for console preview.

  • Subscription resources: direct the user to Huawei Cloud Console → Cost Center → Orders → Unsubscriptions. Ask them to back up or migrate data and verify the account, resource, related resources, refund, fees, and refund destination before submission.
  • Pay-per-use resources: unsubscribe does not apply. Direct the user to the service console to delete the resource after backup; do not delete it for them.

If automation is requested, preserve this boundary and provide the official unsubscribe rules.

Core Commands

All hcloud BSS commands use --cli-region=cn-north-1. Arrays use dot notation (--product_infos.N.*); output with --cli-output=json. Full contracts and exact templates live in references/pricing/commands.md and references/lifecycle/commands.md.

Resolve project scope (IAM read-only)

bash
hcloud IAM KeystoneListAuthProjects --cli-region={region} --cli-output=json
hcloud IAM KeystoneListProjects --domain_id={domain_id} --cli-region={region} --cli-output=json

Pricing dimensions (BSS read-only)

bash
hcloud BSS ListServiceTypes --cli-region=cn-north-1 --cli-output=json --limit=10 --offset=0
hcloud BSS ListServiceResources --service_type_code={cloud_service_type} --cli-region=cn-north-1 --cli-output=json --limit=10 --offset=0
hcloud BSS ListResourceSpecs --charge_mode=1 --cloud_service_type={cst} --resource_type={rt} --region_code={region} --filters.1.key=RESOURCE_SPEC --filters.1.value={spec_hint} --limit=100 --cli-region=cn-north-1 --cli-output=json
hcloud BSS ListUsageTypes --resource_type_code={rt} --cli-region=cn-north-1 --cli-output=json --limit=100 --offset=0
hcloud BSS ListMeasureUnits --cli-region=cn-north-1 --cli-output=json

Period quote (BSS/ListRateOnPeriodDetail, read-only POST)

bash
hcloud BSS ListRateOnPeriodDetail \
  --project_id={project_id} \
  --product_infos.1.id=1 \
  --product_infos.1.cloud_service_type={cst} \
  --product_infos.1.resource_type={rt} \
  --product_infos.1.resource_spec={spec} \
  --product_infos.1.region={deploy_region} \
  --product_infos.1.period_type={0|2|3|4} --product_infos.1.period_num={n} --product_infos.1.subscription_num={qty} \
  --cli-region=cn-north-1 --cli-output=json

Linear products (volume / bandwidth / share_bandwidth) additionally require --product_infos.N.resource_size={size} --product_infos.N.size_measure_id={17|15}.

On-demand quote (BSS/ListOnDemandResourceRatings, read-only POST)

bash
hcloud BSS ListOnDemandResourceRatings \
  --project_id={project_id} \
  --product_infos.1.id=1 \
  --product_infos.1.cloud_service_type={cst} \
  --product_infos.1.resource_type={rt} \
  --product_infos.1.resource_spec={spec} \
  --product_infos.1.region={deploy_region} \
  --product_infos.1.usage_factor={factor} --product_infos.1.usage_value={value} --product_infos.1.usage_measure_id={mid} \
  --product_infos.1.subscription_num={qty} \
  --cli-region=cn-north-1 --cli-output=json

Lifecycle create (allowlisted write path)

The 74 allowlisted operations (e.g. ECS/CreateServers, DDS/CreateInstance, RDS/CreateInstance) are enumerated in references/lifecycle/commands.md. Parameters always come from the current --help, never from memory. Minimal executable example (VPC is allowlisted, VPC/CreateVpc is a readily dry-runnable create):

bash
hcloud VPC CreateVpc --help
hcloud VPC CreateVpc --vpc.name={name} --vpc.cidr=172.16.0.0/16 --cli-region={region} --dryrun

Every other allowlisted operation follows the same shape: run --help first, then build the full command from the help output, add --dryrun, and only remove --dryrun after the dry-run gate and explicit confirmation. Pass the --dryrun gate and explicit confirmation before executing without --dryrun; one failure stops the batch, no auto-rollback.

Lifecycle dependency lookups (read-only)

Run only the dependencies the help output marks required (references/lifecycle/commands.md):

bash
hcloud EPS ListEnterpriseProject --cli-region=cn-north-4 --cli-output=json
hcloud VPC ListVpcs --cli-region={region} --cli-output=json
hcloud VPC ListSubnets --cli-region={region} --cli-output=json
hcloud ECS NovaListAvailabilityZones --cli-region={region} --cli-output=json
hcloud IMS ListImages --cli-region={region} --cli-output=json
hcloud EVS CinderListVolumeTypes --cli-region={region} --cli-output=json
hcloud ECS NovaListKeypairs --cli-region={region} --cli-output=json
hcloud ECS NovaListFlavors --cli-region={region} --cli-output=json

EPS region note: EPS does not support cn-north-1. Query enterprise projects with --cli-region=cn-north-4 (or another EPS-enabled region such as ru-moscow-1 / my-kualalumpur-1); the returned enterprise_project_id is region-independent for lifecycle create parameters. The BSS fixed region cn-north-1 applies to price inquiry only, never to EPS.

Parameter Confirmation

ParameterRequiredDescriptionExample
--cli-regionYes (auto)fixed cn-north-1 for all BSS commands--cli-region=cn-north-1
--project_idYesresolved via KeystoneListAuthProjects--project_id=xxx
--product_infos.N.cloud_service_typeYesraw code from ListServiceTypeshws.service.type.ec2
--product_infos.N.resource_typeYesraw code from ListServiceResourceshws.resource.type.vm
--product_infos.N.resource_specYesraw code from ListResourceSpecs (never fabricate)c6.2xlarge.2.linux
--product_infos.N.regionYesactual deploy region of the resourcecn-north-4
--product_infos.N.subscription_numYesquantity, 1..100001
--product_infos.N.period_typeConditionalperiod quote only: 0 day / 2 month / 3 year / 4 hour2
--product_infos.N.period_numConditionalperiod quote only: number of periods1
--product_infos.N.usage_factorConditionalon-demand only: raw code from ListUsageTypesDuration
--product_infos.N.usage_valueConditionalon-demand only: scalar per Measure Resolve rules2
--product_infos.N.usage_measure_idConditionalon-demand only: usage slot from ListMeasureUnits (≠ size_measure_id)4
--product_infos.N.resource_sizeConditionallinear products only (volume / bandwidth / share_bandwidth)40
--product_infos.N.size_measure_idConditional17 GB (volume), 15 Mbps (bandwidth / share_bandwidth)17
--dryrunYes (lifecycle)global dry-run gate before any create; never --dry-run--dryrun

Missing region, quantity, duration/usage, or linear size is clarified in one question with two to four candidates before any command runs.

Unsubscribe Console Path

Never run or generate unsubscribe CLI/API operations; --dryrun previews request construction only and never replaces the console. Subscription resources go through Console → Cost Center → Orders → Unsubscriptions after data backup and account/resource/refund verification; pay-per-use resources are deleted by the user in the service console after backup.

Critical Rules

  1. Prices come from the current response; parameters come from current help.
  2. No real create call without a successful --dryrun and explicit confirmation.
  3. Never automate or emit unsubscribe operations.
  4. Refuse AK, SK, and tokens in chat; point to references/cli-installation-guide.md for self-configuration.
  5. Every BSS call uses --cli-region=cn-north-1; product_infos.N.region remains the deployment region.
  6. Route out-of-scope work to Cost Center, the appropriate console, or read-only billing.

Use bullets or numbered items, not GFM tables, in user-facing responses. For command-level traps, read references/pricing/commands.md.

KooCLI Command Format Standard

Every command follows the generic KooCLI shape: hcloud <Service> <Operation> --cli-region=<region> [--key=value ...].

FeatureDescriptionExample
Service nameExact KooCLI Service name beginning with uppercase/title caseBSS, IAM, ECS, VPC, DDS
Operation namePascalCaseListRateOnPeriodDetail, CreateServers
Region parameter--cli-region=<value>--cli-region=cn-north-1
Simple parameter--key=value--project_id=xxx
Indexed parameter--key.N=value dot notation--product_infos.1.id=1
Global dry-run--dryrun (not --dry-run)--dryrun

Placeholder tokens above (e.g. <Service>) are illustrative only — never run them literally.

Reference Documents

DocumentContent
references/lifecycle/concepts.mdLifecycle execution concepts: allowlist, help, lookup, dry-run, fee status, batch invariants, unsubscribe console path
references/lifecycle/commands.mdThe 74 allowlisted create operations and dependency lookup commands
references/pricing/commands.mdPricing command contracts, response fields, universal traps, Measure Resolve table
references/pricing/semantic/catalog.ymlRouting catalog: period / on-demand / dimension_lookup
references/pricing/semantic/rfq-ondemand-model.ymlOn-demand quote fact/line model
references/pricing/semantic/rfq-period-model.ymlPeriod quote fact/line model
references/pricing/semantic/rfq-shared-dimensions.ymlShared conformed dimensions
references/iam-policies.mdLeast-privilege IAM policies
references/cli-installation-guide.mdKooCLI install and auth guide (only to relay to user)

For 403 or permission failures, read references/iam-policies.md. If hcloud is unavailable, relay references/cli-installation-guide.md; never install it for the user.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Huawei Cloud Cost Estimation AI skill do?

Generates Huawei Cloud pre-order estimates, provisions allowlisted resources through hcloud, and routes unsubscribe requests to console guidance. Use for Huawei Cloud pricing, budgets, creation, provisioning, or unsubscribe. Creates require runtime help, --dryrun, fee review, and confirmation. Never emits or runs unsubscribe operations, accepts credentials, or performs non-allowlisted writes. Triggers include: "华为云报价", "报价", "价格估算", "费用预估", "比价", "询价", "开通报价", "创建报价", "华为云价格", "价格查询", "预算评估", "费用计算", "price estimate", "cost estimation", "budget", "quote", "pricing", "provision", "create", "...

Why use Huawei Cloud Cost Estimation on TypingMind?

Because you install it once and use it with any model. Huawei Cloud Cost Estimation is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Huawei Cloud Cost Estimation in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/huaweicloud/huaweicloud-skills/tree/master/skills/bss/billing/huawei-cloud-cost-estimation. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Huawei Cloud Cost Estimation?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Huawei Cloud Cost Estimation?

As many as you like. As long as a model supports skills, you can use Huawei Cloud Cost Estimation with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Huawei Cloud Cost Estimation AI skill free?

Yes. It is published on GitHub by huaweicloud under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇