ClaudeCodeMod

All shelves / Skills

huawei-cloud-billing-scout

huaweicloud/huaweicloud-skills · 15.7k installs · 52 stars

Skill

Marked Command Execution · External Downloads · Remote Code Execution · Privilege Escalation

Install

In your shell
npx -y skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-billing-scout --agent claude-code

Run in a terminal. Claude loads the skill when a task calls for it. Check the repo's README before you run it.

Open the repo

Files

SKILL.md

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.

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.

Phase Task Reference File Forbidden
Lock Money Basis Lock three-set catalog.yml → required_context Ask one at a time if missing, not all together
Select Entry Point Match triggers to get entry_point, obtain ontology_entities catalog.yml → entry_points No cross-entry-point summing or borrowing
Gather Evidence Minimal read-only queries within evidence_boundary; first query copy from related-commands.md current entry #### template billing-ontology.yml + related-commands.md No --help to discover operations; no self-constructed JSON; no full detail list first
Deliver Conclusion first then facts; conclusion must be reducible to quadruple This 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

Reference Description
references/semantic/catalog.yml Thin routing layer that maps scope/time/money_basis to billing-ontology.yml entities
references/semantic/billing-ontology.yml Semantic ontology defining facts, scope, money basis, and read-only BSS operations
references/related-commands.md Provides copyable BSS CLI command templates with parameter formats
references/iam-policies.md Defines minimum IAM read-only permissions required for BSS queries
references/cli-installation-guide.md Huawei Cloud KooCLI Installation Guide

Facts

Kind
Skill
Repo
huaweicloud/huaweicloud-skills
Group
Uncategorized
Installs
15.7k
Stars
52

More on this shelf

  1. 1find-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.3.8M
  2. 2grill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.3M
  3. 3grill-with-docsmattpocock/skillsA relentless interview to sharpen a plan or design, which also creates docs (ADR's and glossary) as we go.1.1M
  4. 4agent-browservercel-labs/agent-browserBrowser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.1.1M
  5. 5improve-codebase-architecturemattpocock/skillsScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.1.1M
  6. 6tddmattpocock/skillsTest-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.1.1M