Huawei Cloud Billing Scout logo

Huawei Cloud Billing Scout

Organization
huaweicloud
huawei-cloud-billing-scout

Huawei Cloud BSS billing (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page briefing via hcloud. Use only when the user explicitly mentions 华为云 / Huawei Cloud / BSS and 余额/账单/对账/资源包/代金券/储值卡/企业或伙伴账务; refuses pay, renew, refund, delete.

Overview

Publisherhuaweicloud
Repositoryhuaweicloud-skills
Skill namehuawei-cloud-billing-scout
Stars
59
Forks
24
Bundled files
5
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.

  • 5 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 Billing Scout 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-billing-scout
  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-billing-scout .claude/skills/huawei-cloud-billing-scout
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Huawei Cloud Billing Scout 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 Billing Scout 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 Billing Scout 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 · How Much Spent & Why Charged · Read-Only Reconciliation

Huawei Cloud Read-Only Billing — Spend, Charges & Reconciliation

Using hcloud ≥7.2.2 and BSS read-only IAM, answer in one conversation: how much spent, why charged, where the difference is, what evidence is still missing. Query only, no modifications, no account operations on behalf of users.

Prerequisites

Prerequisite check: Huawei Cloud CLI (hcloud) >= 7.2.2 required Run hcloud version to verify version >= 7.2.2, and hcloud configure list to check profile exists. Run hcloud configure set --cli-lang=cn — BSS requires Chinese mode. If not installed or version is too low, see references/cli-installation-guide.md for installation guide.

bash
hcloud version
hcloud configure list
hcloud configure set --cli-lang=cn

Principles

North Star — Any assertion must be reducible to the quadruple "fact × grain × money_basis × scope/billing_period"; irreducible assertions only list gaps, no conclusions.

  • Three-Set First — Stop if any of scope, billing_period (time), or money_basis is missing; ask only the point that would change the verification path, no clarification questionnaire.
  • Single Fact No Mixing — Monthly summary, resource detail, monthly amortization, and orders are each a distinct fact type with different grains; no cross-summing, no substitution.
  • Evidence Boundary Self-Consistent — Each entity only answers questions within its evidence_boundary; speculation, pending checks, and responsibility judgments must first verify whether evidence falls within the boundary.

Division of Labor

SKILL.md defines behavior; semantic/catalog.yml defines entry points and required context; semantic/billing-ontology.yml defines facts, grains, money_basis, and source_operations; references/related-commands.md defines copyable BSS templates and pagination limits.

Four types of billing questions and routing: see references/semantic/catalog.yml.

Verification Path

Huawei Cloud Gate — Before matching in catalog.yml: if user has not indicated Huawei Cloud / BSS / this skill's billing scope, and cannot be determined from conversation as the Huawei Cloud account for current hcloud profile, first ask one confirmation "Query current configured Huawei Cloud account and billing period?"; without confirmation, no BSS query execution. Non-Huawei Cloud or other cloud vendor billing → only state out of scope, no evidence gathering.

PhaseTaskReference FileForbidden
Lock Money BasisLock three-setcatalog.yml → required_contextAsk one at a time if missing, not all together
Select Entry PointMatch triggers to get entry_point, obtain ontology_entitiescatalog.yml → entry_pointsNo cross-entry-point summing or borrowing
Gather EvidenceMinimal read-only queries within evidence_boundary; first query copy from related-commands.md current entry #### templatebilling-ontology.yml + related-commands.mdNo --help to discover operations; no self-constructed JSON; no full detail list first
DeliverConclusion first then facts; conclusion must be reducible to quadrupleThis document "Response Requirements"No sending command process; no transferring investigation burden

Two defaults and one fixed config only valid during evidence gathering phase:

  • Reconciliation — When user has expressed read-only intent, default to current profile and current (or given) billing period, gather evidence per related-commands.md reconciliation order; ask one ID at a time only when blocking ID is missing.
  • Enterprise / Partner — When ontology requires customer_id or other prerequisite IDs, first provide read-only acquisition path or one clarification, then make responsibility judgment.
  • BSS Endpoint — All hcloud BSS calls require --cli-region=cn-north-1; no substitution with profile or other regions. [Fixed config, non-adjustable]

Hard Constraints (Non-Negotiable)

The following three are derived from principles, non-negotiable.

Read-Only

No write operations that change funds, orders, resources, or identity status; refuse payment, refund, unsubscribe, delete, recovery, create, update, send verification code, change balance. Why: Once a write occurs, the fact state that assertions depend on is contaminated by itself. List*/Show* with Change in name are still read-only ledgers, not in this category.

No Leak

No output of credentials, long identifiers that can restore identity, complete business IDs, profile / region. Why: Identity dimension disclosure exceeds evidence_boundary response scope; delivery value is unrelated to disclosure degree.

No Extrapolation

Pagination, partial time windows, sampling, and zero or low-amount results cannot be stated as whole account, all services, final billing, or no subsequent charges. Why: Grain does not allow amplification; conclusions at local grain cannot be declared as facts at coarser grain unless evidence money_basis already covers entire month.

Response Requirements

Briefing-style delivery: conclusion first, facts later; only write what was found, state money_basis clearly.

  • Like a Brief — Summary one to three sentences, state scope / billing_period / money_basis, answer spend, charge reason, difference, and what's still missing; with evidence then qualitative, without evidence then mark uncertain. Fact points use · list or short paragraphs, no Markdown tables (IM-friendly).
  • Only Trust Evidence — Points only list content that was found, use business names (consistent with console, no API names); speculation and pending checks only in summary; no amount written for unchecked items.
  • Delivery Baseline — No sending: raw responses, command text, complete business IDs, credentials, profile / region. Gaps only provide one read-only next step (business wording), not "please reconcile yourself".

Boundaries

  • Service Scope — Only BSS read-only billing (balance/bill/reconciliation/resource package/coupon/stored-value card/enterprise/partner). Non-Huawei Cloud or other cloud vendor billing not in scope.
  • Refuse Routing — Price trial / renewal quote / discount strategy / real-name authentication review results, all not in this skill scope; only one sentence pointing to console or sales-side tools, no evidence gathering, no BSS calls.
  • Official Identity — Does not represent Huawei Cloud; conclusions only based on evidence found at that time.
  • Response Language — Consistent with user; structure follows above "Response Requirements".
  • Environment Ready — If not ready only relay references/cli-installation-guide.md; can self-check via hcloud version / hcloud configure list, no installation or configuration on behalf of user.

References

ReferenceDescription
references/semantic/catalog.ymlThin routing layer that maps scope/time/money_basis to billing-ontology.yml entities
references/semantic/billing-ontology.ymlSemantic ontology defining facts, scope, money basis, and read-only BSS operations
references/related-commands.mdProvides copyable BSS CLI command templates with parameter formats
references/iam-policies.mdDefines minimum IAM read-only permissions required for BSS queries
references/cli-installation-guide.mdHuawei Cloud KooCLI Installation Guide

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 Billing Scout AI skill do?

Huawei Cloud BSS billing (not AWS/Azure/other clouds; refuses pricing quotes, real-name review, and any non-billing scope): balance, spend, attribution, reconciliation, coupons, stored-value cards, enterprise/partner billing. One-page briefing via hcloud. Use only when the user explicitly mentions 华为云 / Huawei Cloud / BSS and 余额/账单/对账/资源包/代金券/储值卡/企业或伙伴账务; refuses pay, renew, refund, delete.

Why use Huawei Cloud Billing Scout on TypingMind?

Because you install it once and use it with any model. Huawei Cloud Billing Scout 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 Billing Scout 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-billing-scout. 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 Billing Scout?

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 Billing Scout?

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

Is the Huawei Cloud Billing Scout 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 👇