Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huaweicloud/huaweicloud-skills --skill huawei-cloud-maas-model-guidancegit clone --depth 1 https://github.com/huaweicloud/huaweicloud-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-maas-model-guidance)<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-maas-model-guidance"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-maas-model-guidance/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huaweicloud/huaweicloud-skills/huawei-cloud-maas-model-guidance"><img src="https://agentmods.dev/badge/skills/huaweicloud/huaweicloud-skills/huawei-cloud-maas-model-guidance.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00247 | $0.04243 |
| Opus 5.5 | $0.00099 | $0.01697 |
| Sonnet 5.5 | $0.00049 | $0.00849 |
| Haiku 4.5 | $0.00025 | $0.00424 |
Grade B, and why
huawei-cloud-maas-model-guidance scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 18d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
**This skill only provides invocation guidance, does not execute any commands, and does not require installing Huawei Cloud CLI (hcloud).** How it starts
The opening of the file, as written. The whole thing — 341 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Huawei Cloud MaaS Model Invocation Guidance Skill
You are a professional Huawei Cloud MaaS (Model as a Service) assistant responsible for guiding customers to invoke AI models on the MaaS platform. Follow the structured workflow to provide comprehensive invocation guidance.
This skill only provides invocation guidance, does not execute any commands, and does not require installing Huawei Cloud CLI (hcloud).
1. Overview
Functional Overview
Huawei Cloud MaaS model invocation guidance skill provides comprehensive guidance for customers to invoke AI models on the MaaS platform. It covers model selection, API calling methods, code examples (Python, Curl, OpenAI Python SDK, Java), API Key management, and development tool integration.
Architecture Diagram
Customer Request → Model Selection → API Key Preparation → Preset Service Activation → API Invocation
↓ ↓ ↓ ↓
Model List/ API Key Management Activate Preset Code Examples
Recommendation (Create/Get) Service (Python/Curl/Java/OpenAI)
Application Scenarios
- Guide customers to invoke MaaS models (text generation, deep thinking, image understanding, image generation, video generation, embedding, rerank)
- Help customers select appropriate models based on their use case
- Provide API calling examples in multiple programming languages
- Guide API Key creation and management
- Provide development tool integration guidance (OpenClaw, OpenCode, Claude Code, Dify, Cherry Studio, Cursor, Cline, RAGFlow, Deep Research)
- Explain differences between MaaS Standard API, OpenAI Compatible API, and Anthropic Compatible API
User Scenario Examples
- Basic invocation: "How do I call DeepSeek-V3.2 model?"
- Model selection: "Which model should I use for code generation?"
- API Key management: "How do I create an API Key for MaaS?"
- Code examples: "Give me Python code to call GLM-5"
- Development tool integration: "How do I use MaaS with Cursor?"
- Deep thinking: "How do I enable deep thinking mode?"
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/acceptance-criteria.md 5.1 KB
- references/api-interfaces.md 6.0 KB
- references/best-practices.md 9.9 KB
- references/code-examples-advanced.md 7.4 KB
- references/code-examples.md 6.5 KB
- references/dev-tools-integration.md 6.4 KB
- references/iam-policies.md 8.2 KB
- references/invocation-output-template.md 9.6 KB
- references/model-list.md 7.8 KB
- references/token-plan.md 5.9 KB
- references/troubleshooting-guide.md 9.1 KB
- references/verification-method.md 9.2 KB
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 18d ago First seen · 341 lines · 247 tokens per session scan B 8b03df5bdeca
huawei-cloud-maas-model-guidance is a skill published in the GitHub repository huaweicloud/huaweicloud-skills (59 stars, last pushed yesterday), licensed MIT. It adds 247 tokens to every session and 4,243 once invoked, about $0.0010 per session on Opus 5.5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-10.
Other skills, from other repositories
llm-app-patterns
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
prompt-engineer
Writes, refactors, and evaluates prompts for LLMs — generating optimized prompt templates, structured output schemas, evaluation rubrics, and test suites. Use when designing prompts for new LLM applications, refactoring existing prompts for better accuracy or token efficiency, implementing chain-of-thought or few-shot…
prompt-optimization
Improve a prompt on the evaluations workbench through a measured loop. Score the baseline first, then duplicate the target column, form a hypothesis from failing rows, edit the copy's prompt draft, run, compare pass rate and cost, and repeat until the numbers hold. Use when the user asks to optimize or improve a…
omh-model-optimization
This is a Hermes-native model-optimization workflow skill.
ideogram4
Prompting patterns for Ideogram 4 text-to-image — best-in-class in-image text rendering and exact color/layout control via structured JSON captions. Use when generating images that need legible on-image text (title cards, thumbnails, logos, signage, CTAs), precise brand colors, or controlled spatial layout. Triggers…
prompt-library-for-startups
AWS-curated copy-paste prompts for AI coding agents (MVP scaffolding, RAG chatbot with Claude on Bedrock, security baseline evaluation, cost anomaly detection, GPU quota requests, EKS deployment, Well-Architected review, etc.) plus downloadable installable agents (Multi-Account Transition Advisor, Bill Shock…