alicloud-platform-multicloud-docs-api-benchmark

Use this skill when the user wants cross-cloud documentation/API comparison for similar products. Run the benchmark script: Example: LLM platform benchmark example (Bailian/Bedrock/Azure OpenAI/Vertex AI/Hunyuan/Ark/Pangu): If --preset is omitted, script attempts to auto-match preset based on keyword. Scoring weights can be switched by profile (see references/scoring.json ): Auto-discovery may miss pages. For stricter comparison, pass official links manually: Available manual flags: Each flag accepts comma-separated URLs. All artifacts must be written under: output/alicloud-platform-multicloud-docs-api-benchmark/ Per run: When answering the user: Pass criteria: command exits 0 and output/alicloud-platform-multicloud-docs-api-benchmark/validate.txt is generated. - Alibaba Cloud - AWS - Azure - GCP - Tencent Cloud - Volcano Engine - Huawei Cloud - L0 (highest): user-pinned official links via -- -links - L1 : machine-readable official metadata/source - GCP: Discovery API - AWS: API Models repository - Azure: REST API Specs repository - L2 : official-domain constrained web discovery fallback - L3 : insufficient discovery (low confidence) - --alicloud-links - --aws-links - --azure-links - --gcp-links - --tencent-links - --volcengine-links - --huawei-links - benchmark_evidence.json - benchmark_report.md - Show score ranking across all providers. - Highlight top gaps (P0/P1/P2) and...