AB huawei-cloud-maas-model-guidance
Huawei Cloud MaaS (Model as a Service) model invocation guidance skill. Provides comprehensive guidance for customers to invoke AI models on MaaS platform, including model selection, API calling methods, code examples, API Key management, and development tool integration. Use when users need to call MaaS models, select AI models, get API invocation examples, manage API Keys, or integrate MaaS with development tools. Triggers: "MaaS模型调用", "MaaS model invoke", "调用模型", "invoke model", "MaaS API", "模型API调用", "华为云MaaS", "Huawei Cloud MaaS", "深度思考", "deep thinking", "文本生成", "text generation", "图像理解", "image understanding", "图片生成", "image generation", "视频生成", "video generation", "向量化", "embedding", "重排序", "rerank", "API Key", "开发工具集成", "OpenClaw", "OpenCode", "Claude Code", "Dify", "Cherry Studio", "Cursor", "Cline", "RAGFlow", "Deep Research"
Huawei Cloud MaaS (Model as a Service) model invocation guidance skill.
As a process B 76/100 · Nearly there — weak spots: when it triggers
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 1
✓ No critical or high findings
Medium and low: 1
-
low Dangerous commands
cmd-pipe-to-shellreferences/dev-tools-integration.md:26Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host; quoted — discussed, not commanded)- macOS/Linux: `curl -fsSL https://openclaw.ai/install.sh | bash` or `npm install -g openclaw@latest`
vendor-hostquoted
Files scanned: 14. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 215): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 76/100
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (web, python) that frontmatter does not declare
- 70Inputs and preconditions. Inputs and preconditions are listed
- 70Execution cost. Instruction body is 4477 tokens
- 85Steps. 108 steps, 1 vague phrases
- 100Result and completion. Output format and completion criterion are stated
- 100Failures and branches. 2 branches, has a failure section
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 10 top-level sections: this looks like several domains in one skill
- low The skill ranks results itself: that belongs to the system behind the tool, not the model
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 848: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +5Description quotes 23 example trigger phrases
- +4Structure: 41 headings
- +3Step-by-step instructions: 108 items
- +3Output format is stated explicitly
- +4Has examples (2 code blocks)
- +4Reference files are cited in the instructions (12 of 12)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.