binrogithub/1-3-Cloud-Adoption-Skills - Page 2

huawei-snowflake-to-dataarts-migration

Orchestrate or assist migration from Snowflake to Huawei Cloud DataArts (DLI + Factory)

discover-databricks-assets

Inventory Databricks workspaces for migration discovery, including Unity Catalog catalogs, schemas, tables, views, functions, volumes, canonical DDL, table data and Delta metadata locations, jobs, tasks, pipelines, compute, repositories, workspace objects,…

mgc-cross-region-migration

Execute and troubleshoot Huawei Cloud cross-region server migration with MGC/SMS and Terraform in this repository. Use when users ask to migrate ECS across regions (especially la-north-2 to la-south-2), run the end-to-end workflow (`terraform init/apply` +…

mgc-cross-region-migration

Execute and troubleshoot Huawei Cloud server migration with Terraform in this repository. Prefer SMS first, and fallback to rsync staged migration when source is SMS-incompatible. Use when users ask to migrate ECS/on-prem VMware (especially la-north-2 and…

dsv4-c64-1280tps-ascend-a3

Deploy and benchmark DeepSeek-V4-Flash-0731 W8A8 on Ascend A3 to achieve C64 aggregate output TPS >1280 (per-concurrency >20 tok/s). Use when the user asks to optimize DSV4 C64 throughput, enable Fused MC2, tune DSpark for high concurrency, or reproduce the…

dsv4-dspark-ascend-a3

Deploy and benchmark DeepSeek-V4-Flash-0731 W8A8 with DSpark speculative decoding on Ascend A3 NPU using vLLM 0.25.1. Use when the user asks to deploy DSV4 with DSpark, benchmark DSV4 on Ascend, enable speculative decoding for DeepSeek V4, or reproduce the…

sglang-qwen36-ascend-best-practice

Reproduce the verified best-practice SGLang deployment of Qwen3.6-35B-A3B (MoE) on Huawei Ascend 910 NPU (8 cards × 2 die = 16 die). Hybrid topology: C1 → TP16 single engine, C4+ → TP2/DP8 sticky. BF16 + NEXTN speculative decoding. All 12 data points (3…

ascend-llm-cost-optimization

Benchmark and reduce LLM inference token cost on Huawei Ascend 910 NPUs with vLLM-Ascend and a Mooncake DRAM KV tier. Use when working on Qwen3.6-35B-A3B serving, 64K-context agent workloads, prefix-cache tiering, data-parallel session affinity, concurrency…

hcloud-cli

Manage Huawei Cloud resources through KooCLI. Discover before acting — always query existing resources before creating. Use dryrun to validate, waiter to poll async operations.

multi-account-landing-zone

Build HuaweiCloud multi-account landing zone Terraform code with modular governance (OUs, accounts, SCP, IAM, Identity Center) and per-account infrastructure (VPC, compute, tagging)

huaweicloud-oms-migration

Migrate object storage to Huawei Cloud OBS using OMS (Object Migration Service). Handles cross-cloud (AWS, Azure, Aliyun, Tencent, GCP, on-prem HTTP) S3/bucket migration with Terraform automation, consistency checks, and post-migration verification. Use when…

msi-batch-installer

Install a set of .msi files silently via msiexec with logging, exit-code decoding, and summary reporting. Provides both CMD batch and PowerShell scripts.

windows-msi-inventory

Find, extract, and back up MSI installers for third-party (non-system) applications on Windows. Covers registry LocalPackage discovery, MSI property reading via COM, admin extraction with msiexec /a, and backup workflows.

windows-software-inventory

Scan and enumerate all installed software on Windows systems via registry queries, Get-Package, and CIM/WMI. Includes ready-to-use PowerShell and Python scripts for inventory, export, and auditing.

claude-code-litellm-maas

Configure Claude Code with LiteLLM proxy for Huawei Cloud MaaS models. Covers Node.js/Claude Code installation, venv setup, config generation with Claude model-name aliases, environment variable configuration, startup script, and model switching.

huaweicloud-terraform-planner

Plan and write Terraform for Huawei Cloud by discovering real values from the live cloud and asking the user for decisions. Never guesses — always verifies with the latest provider schema.

opencode-litellm-maas

Configure OpenCode with LiteLLM proxy for Huawei Cloud MaaS models with latency-based routing and fallbacks. Covers venv setup, config generation, opencode integration, and startup script.

huaweicloud-velero-cce-migration-planner

Migrate Huawei Cloud CCE (Cloud Container Engine) workloads between clusters (including different regions) using Velero backup and restore. Covers source environment deployment, SWR image management, Velero installation, backup creation, destination…

pv-migration-planner

Migrate PersistentVolumeClaim (PVC) data between Huawei Cloud CCE clusters using obsutil as the data transfer mechanism via OBS bucket as intermediary storage. Use when Velero's file-level backup (restic/kopia) fails due to Huawei Cloud OBS S3 API…

huaweicloud-cce-deploy-terraform

Deploy Huawei Cloud CCE (Cloud Container Engine) clusters with node pools using Terraform MCP and Huawei Cloud MCP. Covers provider schema discovery, data source references for existing VPC/subnet, cluster and node pool resource creation, keypair management,…

huaweicloud-cce-deployment

Deploy Huawei Cloud CCE (Cloud Container Engine) clusters with node pools using KooCLI and Huawei Cloud MCP. Covers environment discovery, cluster creation, node pool provisioning, SSH keypair setup, kubeconfig generation, and post-deployment validation.

cce-local-kind-setup

Set up a local Kubernetes cluster using Kind that is compatible with Huawei Cloud CCE for development and migration exercises. Covers prerequisites check, cluster creation, NGINX Ingress Controller installation with pre-loaded images, local-path provisioner,…

kind-to-cce-migration

Migrate a Kubernetes application from a local Kind cluster to Huawei Cloud CCE. Covers CCE cluster creation, node pool provisioning, public API access via EIP, ELB setup for Ingress, SWR image push, Nginx Ingress Controller installation, application…

huaweicloud-drs-migration

Migrate databases to Huawei Cloud RDS using DRS (Data Replication Service). Handles AWS and other-cloud MySQL to Huawei Cloud MySQL with full+incremental replication, parameter alignment, network connectivity, and Terraform automation. Use when the user wants…

claude-code-oauth-delegate-router

Deploy task-level hybrid routing for Claude Code — plain `claude` stays on Claude.ai OAuth as premium pool + orchestrator (policy in CLAUDE.md, UserPromptSubmit hint hook), while execution-class tasks and token-burn workflows (multi-agent fan-out, batch…

dataarts-architecture-automation

Automate Huawei Cloud DataArts Studio DataArts Architecture metadata creation from source tables, CSVs, SQL DDL, catalog exports, or business descriptions. Use when Codex needs to infer domains, subjects, standards, code tables, table models, dimensions,…

codex-maas-hybrid-router

Install, configure, verify, or troubleshoot a side-by-side `codex-forky` command that routes normal Codex tool/code-execution turns through an existing external forky service to the MaaS execution backend such as LiteLLM/Huawei MaaS GLM, while routing…

glm-repo-summary

MaaS-twin repo summarization on the GLM-5.1 execution pool. Use for generating repo-wide README updates, architecture docs, module overviews, and changelog summaries. Delegates to ds-executor on Huawei MaaS GLM-5.1.

glm-review

MaaS-twin reviewer on the GLM-5.1 execution pool. Use for low/medium-risk PR review, repo-wide review passes, and code quality checks. Delegates to the ds-reviewer subagent on Huawei MaaS GLM-5.1. NOT for high-risk paths (payment, auth, pci, infra,…

glm-test-batch

MaaS-twin batch test generator on the GLM-5.1 execution pool. Use for generating unit tests across multiple modules and test data fixtures. Delegates bounded test-generation briefs to ds-executor on Huawei MaaS GLM-5.1.

maas-delegate-router

Task-level hybrid routing for OpenCode. Premium model GLM-5.2 handles architecture, complex debugging, security, incidents, high-risk review, images, and raw context over 128K. Execution tasks such as unit tests, docs, CI fixes, codegen, batch refactors,…

cloudera-to-huawei-mrs

Use this skill when migrating Cloudera/CDH Hadoop, Hive, Spark, or Impala workloads to Huawei Cloud MRS. It covers source simulation, MRS cluster provisioning, OBS data landing, Hive external table creation, Spark SQL migration, report view migration, and…

databricks-to-huawei-cloud-skill

Use this skill when migrating Databricks tables, notebooks, SQL warehouse flows, or Spark pipelines to Huawei Cloud. It helps analyze the source workload, map Databricks patterns to OBS plus MRS Spark and Hive, generate sanitized migration scripts, validate…

databricks-to-huawei-mrs-hudi-demo

Use when analyzing or migrating Databricks CDC/Delta workflow scripts into a Huawei Cloud Chile MRS + OBS + Apache Hudi demo, including synthetic CDC data generation, notebook-triggered automation, Delta-to-Hudi replacement, deployment troubleshooting, and…

teradata-to-huawei-dws

Build, run, or adapt a Teradata-to-Huawei-Cloud-DWS migration demo or migration toolkit, especially for finance analytics workloads. Use when Codex needs to scaffold a local Teradata-source simulation, create a minimal Huawei Cloud DWS cluster, migrate…

gaussdb-adaptation

Use this skill when porting SQL Server or vanilla PostgreSQL code to Huawei GaussDB (Kernel 505.x / openGauss-based). TRIGGER when source code or SQL contains any of — `Microsoft.Data.SqlClient`, `SqlBulkCopy`, `NEXT VALUE FOR`, `ON COMMIT DROP`, `CREATE…

sqlserver-babelfish-finance-demo

Build, adapt, or explain a local finance migration demo from SQL Server to PostgreSQL through Babelfish. Use when Codex needs to create a small host-local SQL Server source database, initialize Babelfish/PostgreSQL, migrate a banking FinanceDemo workload…

mrs-dws-finance-skill

Use this skill when setting up a financial risk control pipeline on Huawei Cloud. It helps configure OBS for raw and result data storage, MRS for Spark-based risk analysis and anomaly detection, and DWS for data warehousing and regulatory reporting. The skill…

cursor-maas-delegate-router

USER-GLOBAL hybrid routing for Cursor (all workspaces): after install, writes ~/.cursor/rules + ~/.cursor/memory + ~/.cursor/hooks (sessionStart + beforeSubmitPrompt). Code execution (HTML/CSS/JS, Hello World, greenfield, 输出代码, tests, docs, CI) MUST use…

glm-repo-summary

Repo-wide summarization/documentation on the GLM execution pool. Use for "summarize this repo/module", "write docs for X" over many files.